diff --git a/.gitignore b/.gitignore index 64267de..3d94e84 100644 --- a/.gitignore +++ b/.gitignore @@ -5,7 +5,20 @@ build/ dist/ site/ -data/ +data/* +!data/README.md +!data/searchqa_id_split/ +!data/searchqa_id_split/** +!data/livemathematicianbench_id_split/ +!data/livemathematicianbench_id_split/** +!data/docvqa_id_split/ +!data/docvqa_id_split/** +!data/officeqa_id_split/ +!data/officeqa_id_split/** +!data/spreadsheetbench_id_split/ +!data/spreadsheetbench_id_split/** +!data/alfworld_path_split/ +!data/alfworld_path_split/** outputs/ logs/ external/ diff --git a/README.md b/README.md index 54f9a75..3110bcc 100644 --- a/README.md +++ b/README.md @@ -139,7 +139,7 @@ python scripts/train.py \ # Train on ALFWorld: python scripts/train.py \ --config configs/alfworld/default.yaml \ - --split_dir /path/to/your/alfworld_split \ + --split_dir data/alfworld_path_split \ --azure_openai_endpoint https://your-resource.openai.azure.com/ \ --optimizer_model gpt-5.5 \ --target_model gpt-5.5 diff --git a/configs/alfworld/default.yaml b/configs/alfworld/default.yaml index 48ce6f0..9504140 100644 --- a/configs/alfworld/default.yaml +++ b/configs/alfworld/default.yaml @@ -19,7 +19,7 @@ env: name: alfworld skill_init: skillopt/envs/alfworld/skills/initial.md split_mode: split_dir - split_dir: data/ablation_splits/alfworld/2-1-7_seed42 + split_dir: data/alfworld_path_split data_path: "" split_output_dir: "" max_steps: 50 diff --git a/configs/livemathematicianbench/default.yaml b/configs/livemathematicianbench/default.yaml index 465a331..19401ab 100644 --- a/configs/livemathematicianbench/default.yaml +++ b/configs/livemathematicianbench/default.yaml @@ -9,7 +9,7 @@ env: name: livemathematicianbench skill_init: skillopt/envs/livemathematicianbench/skills/initial.md split_mode: split_dir - split_dir: data/ablation_splits/livemathematicianbench/2-1-7_seed42 + split_dir: data/livemathematicianbench_split data_path: "" split_output_dir: "" max_turns: 1 diff --git a/data/README.md b/data/README.md new file mode 100644 index 0000000..8cb5fd7 --- /dev/null +++ b/data/README.md @@ -0,0 +1,223 @@ +# Data Manifests + +This directory releases lightweight split manifests for the SkillOpt paper +splits. These manifests are not full runnable benchmark payloads. To evaluate a +benchmark, first materialize the full examples from the raw data source when +needed, then point `--split_dir` at the split directory listed below. + +In this README, "coverage" describes which part of the upstream benchmark the +manifest references. It does not mean the released manifest directory contains +the full runnable examples. + +## Layout + +Every released manifest directory uses the same file layout: + +```text +data/_/ +|-- split_manifest.json +|-- train/items.json +|-- val/items.json +`-- test/items.json +``` + +`split_manifest.json` records source metadata, split counts, and item fields. +Each `items.json` contains only stable IDs or source-path hints. + +## Released Splits + +| Manifest directory | Benchmark | Counts | Coverage | Raw data source | `split_dir` | +|---|---|---:|---|---|---| +| `searchqa_id_split/` | SearchQA | 400 / 200 / 1400 | Official HF dataset IDs | [lucadiliello/searchqa](https://huggingface.co/datasets/lucadiliello/searchqa) | `data/searchqa_split` | +| `livemathematicianbench_id_split/` | LiveMathematicianBench | 35 / 18 / 124 | Four official monthly files | [LiveMathematicianBench/LiveMathematicianBench](https://huggingface.co/datasets/LiveMathematicianBench/LiveMathematicianBench) | `data/livemathematicianbench_split` | +| `docvqa_id_split/` | DocVQA | 107 / 53 / 374 | 10% subset of validation | [lmms-lab/DocVQA](https://huggingface.co/datasets/lmms-lab/DocVQA) | `data/docvqa/splits` | +| `officeqa_id_split/` | OfficeQA | 50 / 24 / 172 | OfficeQA Full | [databricks/officeqa](https://huggingface.co/datasets/databricks/officeqa) | `data/officeqa_split` | +| `spreadsheetbench_id_split/` | SpreadsheetBench | 80 / 40 / 280 | SpreadsheetBench Verified 400 | [KAKA22/SpreadsheetBench](https://huggingface.co/datasets/KAKA22/SpreadsheetBench) | `data/spreadsheetbench_split` | +| `alfworld_path_split/` | ALFWorld | 39 / 18 / 134 | ALFWorld `json_2.1.1` paths | [alfworld/alfworld](https://github.com/alfworld/alfworld) | `data/alfworld_path_split` | + +Counts are ordered as train / val / test. + +## Direct Use + +Only `alfworld_path_split/` can be used directly as `--split_dir` from this +release, because the ALFWorld loader reads `gamefile` and `task_type` from the +split items. + +This does not mean the ALFWorld raw data is included. You still need to +download ALFWorld separately with `alfworld-download` and set `$ALFWORLD_DATA` +to the data root containing `json_2.1.1`. + +The other manifest directories are lookup manifests. They intentionally omit +full example fields such as questions, answers, contexts, images, or task +instructions. Materialize those benchmarks into the `split_dir` paths listed +above before running SkillOpt. + +## Lookup Keys + +The manifests are sufficient to locate the corresponding raw examples after +the raw data has been downloaded or otherwise made available: + +| Benchmark | Manifest lookup key | +|---|---| +| SearchQA | Match `items.json[].id` to the `key` field in `lucadiliello/searchqa`. | +| LiveMathematicianBench | Open `source_file`, then match `no`; the manifest `id` is `:`. | +| DocVQA | Match `questionId` within the official DocVQA `validation` split; `image_path` records the expected local image path. | +| OfficeQA | Match `uid` in `officeqa_full.csv`; `source_files` and `source_docs` identify the supporting document. | +| SpreadsheetBench | Match `id`; `spreadsheet_path` identifies the referenced spreadsheet directory. | +| ALFWorld | Resolve `gamefile` relative to `$ALFWORLD_DATA`. | + +## Manifest Item Examples + +SearchQA: + +```json +{ + "id": "221c83e6630f4e7983da48fa28da1882" +} +``` + +LiveMathematicianBench: + +```json +{ + "id": "202602:22", + "month": "202602", + "no": 22, + "paper_link": "http://arxiv.org/abs/2602.10700v1", + "source_file": "data/202602/qa_202602_final.json" +} +``` + +DocVQA: + +```json +{ + "id": "50877", + "questionId": "50877", + "docId": "14724", + "image_path": "data/docvqa_images/q50877_d14724.png", + "source_split": "validation" +} +``` + +OfficeQA: + +```json +{ + "id": "UID0002", + "uid": "UID0002", + "category": "easy", + "source_files": "treasury_bulletin_1944_01.txt" +} +``` + +SpreadsheetBench: + +```json +{ + "id": "32438", + "spreadsheet_path": "spreadsheet/32438", + "instruction_type": "Cell-Level Manipulation" +} +``` + +ALFWorld: + +```json +{ + "id": "train:0000", + "gamefile": "json_2.1.1/train/.../game.tw-pddl", + "task_type": "look_at_obj_in_light" +} +``` + +## Benchmark Notes + +### SearchQA + +`searchqa_id_split/` is an ID-only manifest. Each released `id` exactly matches +the `key` field in `lucadiliello/searchqa`. + +Materialized examples must include the fields consumed by the SearchQA +environment, including: + +```text +question +context +answers +``` + +### LiveMathematicianBench + +`livemathematicianbench_id_split/` was generated from these raw files: + +```text +data/202511/qa_202511_final.json +data/202512/qa_202512_final.json +data/202601/qa_202601_final.json +data/202602/qa_202602_final.json +``` + +The manifest stores IDs in the loader format: + +```text +: +``` + +Materialized examples must include: + +```text +question +choices +correct_choice +theorem_type +theorem +sketch +paper_link +``` + +### DocVQA + +`docvqa_id_split/` records `docvqa_validation_10pct`: a 10% subset sampled from +the official DocVQA `validation` split. + +```text +source_split: validation +docvqa_validation_10pct: train=107, val=53, test=374 +``` + +Each manifest item contains question/document IDs plus image location metadata. +Materialized examples must provide `question`, `answer` or `ground_truth`, and +an `image_path` that resolves locally. + +### OfficeQA + +`officeqa_id_split/` records the split over OfficeQA Full +(`officeqa_full.csv`). The official OfficeQA CSVs are gated on Hugging Face, so +materialization requires authorized access. + +Each manifest item contains `uid`, `category`, `source_files`, and +`source_docs` hints. Materialized examples must include `question` and +`ground_truth` or `answer`. + +### SpreadsheetBench + +`spreadsheetbench_id_split/` records the split over SpreadsheetBench Verified +400, from `spreadsheetbench_verified_400.tar.gz`. + +Each manifest item contains task identity metadata such as `id`, +`spreadsheet_path`, and `instruction_type`. Materialization must also place the +referenced spreadsheet directories at: + +```text +data/spreadsheetbench_verified_400 +``` + +### ALFWorld + +`alfworld_path_split/` records `gamefile` paths relative to `$ALFWORLD_DATA`. +The source payload is `json_2.1.1`, which must be downloaded separately with +`alfworld-download`. + +This manifest can be used directly as `--split_dir` after `$ALFWORLD_DATA` +points to the local ALFWorld data root containing `json_2.1.1`. diff --git a/data/alfworld_path_split/split_manifest.json b/data/alfworld_path_split/split_manifest.json new file mode 100644 index 0000000..46352df --- /dev/null +++ b/data/alfworld_path_split/split_manifest.json @@ -0,0 +1,29 @@ +{ + "benchmark": "ALFWorld", + "manifest_type": "path_split", + "source_repo": "alfworld/alfworld", + "source_repo_type": "repository", + "source_url": "https://github.com/alfworld/alfworld", + "source_file": "json_2.1.1", + "source_method": "generated by alfworld-download", + "source_split_files": [ + "split_train.json", + "split_val.json", + "split_test.json" + ], + "counts": { + "train": 39, + "val": 18, + "test": 134 + }, + "item_fields": [ + "id", + "gamefile", + "task_type" + ], + "path_root": "$ALFWORLD_DATA", + "notes": [ + "This is a path manifest, not the ALFWorld game payload.", + "The gamefile field is relative to ALFWORLD_DATA and must be expanded before direct use as split_dir data." + ] +} diff --git a/data/alfworld_path_split/test/items.json b/data/alfworld_path_split/test/items.json new file mode 100644 index 0000000..bbcdb8b --- /dev/null +++ b/data/alfworld_path_split/test/items.json @@ -0,0 +1,672 @@ +[ + { + "id": "test:0000", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-AlarmClock-None-DeskLamp-308/trial_T20190908_222917_366542/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0001", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-AlarmClock-None-DeskLamp-308/trial_T20190908_222933_607649/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0002", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-AlarmClock-None-DeskLamp-308/trial_T20190908_222951_616606/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0003", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Book-None-DeskLamp-308/trial_T20190908_020029_636862/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0004", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Book-None-DeskLamp-308/trial_T20190908_020048_814402/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0005", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Book-None-DeskLamp-308/trial_T20190908_144951_587345/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0006", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Bowl-None-DeskLamp-308/trial_T20190907_133919_856963/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0007", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Bowl-None-DeskLamp-308/trial_T20190907_133935_066606/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0008", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Bowl-None-DeskLamp-308/trial_T20190907_133953_562557/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0009", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-CD-None-DeskLamp-308/trial_T20190908_141942_810052/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0010", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-CD-None-DeskLamp-308/trial_T20190908_141958_463362/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0011", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-CD-None-DeskLamp-308/trial_T20190908_142046_281296/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0012", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Mug-None-DeskLamp-308/trial_T20190908_161733_213242/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0013", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Mug-None-DeskLamp-308/trial_T20190908_201421_021646/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0014", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Mug-None-DeskLamp-308/trial_T20190908_201444_037645/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0015", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Pencil-None-DeskLamp-308/trial_T20190908_220545_153480/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0016", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Pencil-None-DeskLamp-308/trial_T20190908_220604_010430/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0017", + "gamefile": "json_2.1.1/valid_unseen/look_at_obj_in_light-Pencil-None-DeskLamp-308/trial_T20190908_220656_510400/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "test:0018", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Mug-None-Desk-308/trial_T20190908_125200_737896/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0019", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Mug-None-Desk-308/trial_T20190909_203041_433487/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0020", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Mug-None-Desk-308/trial_T20190909_210238_431966/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0021", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Pencil-None-Shelf-308/trial_T20190908_121952_610012/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0022", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Pencil-None-Shelf-308/trial_T20190908_122024_052056/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0023", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Pencil-None-Shelf-308/trial_T20190908_122154_042763/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0024", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-PepperShaker-None-Drawer-10/trial_T20190906_184021_215264/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0025", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-PepperShaker-None-Drawer-10/trial_T20190918_154326_823501/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0026", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-PepperShaker-None-Drawer-10/trial_T20190918_154424_844749/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0027", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Cabinet-10/trial_T20190906_191429_743650/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0028", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Cabinet-10/trial_T20190906_191445_723170/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0029", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Cabinet-10/trial_T20190906_191501_563086/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0030", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Drawer-10/trial_T20190909_021613_077537/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0031", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Drawer-10/trial_T20190909_021650_880235/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0032", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SaltShaker-None-Drawer-10/trial_T20190909_021728_339782/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0033", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SoapBottle-None-Toilet-424/trial_T20190907_004321_405868/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0034", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SoapBottle-None-Toilet-424/trial_T20190907_004351_281384/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0035", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-SoapBottle-None-Toilet-424/trial_T20190907_004404_604165/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0036", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Vase-None-Safe-219/trial_T20190908_205204_244321/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0037", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Vase-None-Safe-219/trial_T20190908_205221_748352/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0038", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Vase-None-Safe-219/trial_T20190908_205246_776817/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0039", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Watch-None-Safe-219/trial_T20190907_074524_006355/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0040", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Watch-None-Safe-219/trial_T20190907_074556_124850/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0041", + "gamefile": "json_2.1.1/valid_unseen/pick_and_place_simple-Watch-None-Safe-219/trial_T20190907_074643_810052/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "test:0042", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Bowl-None-Cabinet-10/trial_T20190909_061130_844814/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0043", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Bowl-None-Cabinet-10/trial_T20190909_061158_110530/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0044", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Bowl-None-Cabinet-10/trial_T20190909_061232_368489/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0045", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Cloth-None-Cabinet-424/trial_T20190908_022321_380927/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0046", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Cloth-None-Cabinet-424/trial_T20190908_022436_073995/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0047", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Cloth-None-CounterTop-424/trial_T20190908_100632_546757/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0048", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Cloth-None-CounterTop-424/trial_T20190908_114340_674467/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0049", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Egg-None-Microwave-10/trial_T20190909_120554_888709/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0050", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Egg-None-Microwave-10/trial_T20190909_120632_691361/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0051", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Egg-None-Microwave-10/trial_T20190909_120712_273910/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0052", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Knife-None-CounterTop-10/trial_T20190909_110347_624008/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0053", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Knife-None-CounterTop-10/trial_T20190909_110445_675754/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0054", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Knife-None-CounterTop-10/trial_T20190909_110531_148235/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0055", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_221208_560499/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0056", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_221300_362511/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0057", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_221355_558505/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0058", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_032434_013084/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0059", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_032518_891433/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0060", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_032543_712058/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0061", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Plate-None-CounterTop-10/trial_T20190908_213356_017769/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0062", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Plate-None-CounterTop-10/trial_T20190908_213420_728917/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0063", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Plate-None-CounterTop-10/trial_T20190908_213533_897289/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0064", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-Cabinet-424/trial_T20190908_214926_337906/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0065", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-Cabinet-424/trial_T20190908_214946_567644/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0066", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-Cabinet-424/trial_T20190908_215019_162873/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0067", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-CounterTop-424/trial_T20190907_074045_109439/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0068", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-CounterTop-424/trial_T20190907_074106_050405/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0069", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-SoapBar-None-CounterTop-424/trial_T20190907_074124_966890/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0070", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Spatula-None-Drawer-10/trial_T20190907_080730_211959/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0071", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Spatula-None-Drawer-10/trial_T20190907_080800_275989/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0072", + "gamefile": "json_2.1.1/valid_unseen/pick_clean_then_place_in_recep-Spatula-None-Drawer-10/trial_T20190907_080825_222432/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "test:0073", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Bread-None-CounterTop-10/trial_T20190908_091747_866951/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0074", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Bread-None-CounterTop-10/trial_T20190908_091811_414150/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0075", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Bread-None-CounterTop-10/trial_T20190908_091835_825830/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0076", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Lettuce-None-CounterTop-10/trial_T20190909_123133_763972/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0077", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Lettuce-None-CounterTop-10/trial_T20190909_174807_646433/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0078", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Lettuce-None-CounterTop-10/trial_T20190909_174840_771703/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0079", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_121559_082363/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0080", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_121635_622676/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0081", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_121710_650938/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0082", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_183715_299073/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0083", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_183807_477267/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0084", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_183853_958104/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0085", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_114545_244903/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0086", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_114622_738670/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0087", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Pan-None-CounterTop-10/trial_T20190908_114656_768805/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0088", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Potato-None-Microwave-10/trial_T20190907_033157_424297/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0089", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Potato-None-Microwave-10/trial_T20190907_033228_194678/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0090", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Potato-None-Microwave-10/trial_T20190907_033306_962974/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0091", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Tomato-None-Microwave-10/trial_T20190909_102608_318800/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0092", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Tomato-None-Microwave-10/trial_T20190909_102644_926781/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0093", + "gamefile": "json_2.1.1/valid_unseen/pick_cool_then_place_in_recep-Tomato-None-Microwave-10/trial_T20190909_102710_795182/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "test:0094", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-Fridge-10/trial_T20190906_182259_116320/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0095", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-Fridge-10/trial_T20190906_182353_418140/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0096", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-Fridge-10/trial_T20190906_182435_622538/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0097", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-GarbageCan-10/trial_T20190908_145050_918567/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0098", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-GarbageCan-10/trial_T20190908_145143_820541/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0099", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Apple-None-GarbageCan-10/trial_T20190908_145356_918528/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0100", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Cup-None-Cabinet-10/trial_T20190907_083346_800823/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0101", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Cup-None-Cabinet-10/trial_T20190907_083429_887065/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0102", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Cup-None-Cabinet-10/trial_T20190907_083507_594820/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0103", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Egg-None-GarbageCan-10/trial_T20190908_113432_673307/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0104", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Egg-None-GarbageCan-10/trial_T20190908_113523_123938/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0105", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Egg-None-GarbageCan-10/trial_T20190908_113610_425142/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0106", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_021100_341887/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0107", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_021200_669381/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0108", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-Cabinet-10/trial_T20190909_021247_306737/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0109", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_171806_406231/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0110", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_171850_960211/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0111", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Mug-None-CoffeeMachine-10/trial_T20190907_171933_349922/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0112", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Potato-None-GarbageCan-10/trial_T20190907_161745_664033/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0113", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Potato-None-GarbageCan-10/trial_T20190907_161853_945788/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0114", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Tomato-None-GarbageCan-10/trial_T20190908_225046_020282/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0115", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Tomato-None-GarbageCan-10/trial_T20190908_225359_617900/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0116", + "gamefile": "json_2.1.1/valid_unseen/pick_heat_then_place_in_recep-Tomato-None-GarbageCan-10/trial_T20190908_225453_272533/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "test:0117", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-CD-None-Safe-308/trial_T20190907_050942_897916/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0118", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-CD-None-Safe-308/trial_T20190907_051013_060265/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0119", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-CD-None-Safe-308/trial_T20190907_051056_585414/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0120", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-KeyChain-None-Safe-219/trial_T20190909_011803_423115/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0121", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-KeyChain-None-Safe-219/trial_T20190909_012027_782483/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0122", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-PepperShaker-None-Drawer-10/trial_T20190908_010306_215435/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0123", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-PepperShaker-None-Drawer-10/trial_T20190912_221016_460197/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0124", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-PepperShaker-None-Drawer-10/trial_T20190912_221141_608117/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0125", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-Pillow-None-Sofa-219/trial_T20190907_163240_345855/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0126", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-Pillow-None-Sofa-219/trial_T20190907_163327_486300/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0127", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-Pillow-None-Sofa-219/trial_T20190907_163408_914117/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0128", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-SoapBar-None-Cabinet-424/trial_T20190909_081720_491733/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0129", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-SoapBar-None-Cabinet-424/trial_T20190909_081746_857594/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0130", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-SoapBar-None-GarbageCan-424/trial_T20190909_064053_839817/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0131", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-SoapBar-None-GarbageCan-424/trial_T20190909_064221_368939/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0132", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-SoapBar-None-GarbageCan-424/trial_T20190909_064309_357168/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "test:0133", + "gamefile": "json_2.1.1/valid_unseen/pick_two_obj_and_place-ToiletPaper-None-Cabinet-424/trial_T20190906_202926_527010/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + } +] diff --git a/data/alfworld_path_split/train/items.json b/data/alfworld_path_split/train/items.json new file mode 100644 index 0000000..0be1082 --- /dev/null +++ b/data/alfworld_path_split/train/items.json @@ -0,0 +1,197 @@ +[ + { + "id": "train:0000", + "gamefile": "json_2.1.1/train/look_at_obj_in_light-AlarmClock-None-DeskLamp-305/trial_T20190908_082736_108723/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "train:0001", + "gamefile": "json_2.1.1/train/look_at_obj_in_light-CD-None-DeskLamp-304/trial_T20190907_185649_782438/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "train:0002", + "gamefile": "json_2.1.1/train/look_at_obj_in_light-CD-None-DeskLamp-320/trial_T20190907_224439_174735/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "train:0003", + "gamefile": "json_2.1.1/train/look_at_obj_in_light-Pillow-None-DeskLamp-316/trial_T20190908_232421_645610/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "train:0004", + "gamefile": "json_2.1.1/train/look_at_obj_in_light-Statue-None-DeskLamp-319/trial_T20190907_035546_167548/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "train:0005", + "gamefile": "json_2.1.1/train/pick_and_place_simple-CellPhone-None-Shelf-313/trial_T20190908_123725_452958/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0006", + "gamefile": "json_2.1.1/train/pick_and_place_simple-Newspaper-None-Sofa-211/trial_T20190906_175004_203092/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0007", + "gamefile": "json_2.1.1/train/pick_and_place_simple-Pencil-None-Desk-302/trial_T20190908_032836_462632/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0008", + "gamefile": "json_2.1.1/train/pick_and_place_simple-SoapBar-None-GarbageCan-416/trial_T20190908_020839_714699/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0009", + "gamefile": "json_2.1.1/train/pick_and_place_simple-Statue-None-CoffeeTable-222/trial_T20190907_131249_788749/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0010", + "gamefile": "json_2.1.1/train/pick_and_place_simple-ToiletPaper-None-ToiletPaperHanger-406/trial_T20190908_122807_136741/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0011", + "gamefile": "json_2.1.1/train/pick_and_place_simple-ToiletPaper-None-ToiletPaperHanger-415/trial_T20190908_050443_333939/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "train:0012", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Apple-None-DiningTable-4/trial_T20190908_104413_450768/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0013", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-DishSponge-None-Shelf-20/trial_T20190907_222429_992578/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0014", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-DishSponge-None-Shelf-401/trial_T20190908_072225_397518/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0015", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Kettle-None-Cabinet-2/trial_T20190909_043103_418752/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0016", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Knife-None-Drawer-22/trial_T20190907_224827_746945/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0017", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Lettuce-None-DiningTable-20/trial_T20190906_191148_519826/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0018", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Lettuce-None-Fridge-13/trial_T20190908_203022_601787/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0019", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Plate-None-Fridge-5/trial_T20190909_112954_869911/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0020", + "gamefile": "json_2.1.1/train/pick_clean_then_place_in_recep-Spoon-None-DiningTable-18/trial_T20190909_102159_277894/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "train:0021", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Bread-None-CounterTop-1/trial_T20190908_212439_711334/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0022", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Bread-None-CounterTop-15/trial_T20190909_085448_256298/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0023", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Bread-None-CounterTop-16/trial_T20190908_143948_082471/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0024", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Pan-None-StoveBurner-27/trial_T20190906_212619_469871/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0025", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Plate-None-DiningTable-17/trial_T20190909_122939_032098/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0026", + "gamefile": "json_2.1.1/train/pick_cool_then_place_in_recep-Pot-None-CounterTop-1/trial_T20190909_124252_504581/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "train:0027", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Apple-None-Fridge-20/trial_T20190908_013911_274341/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0028", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Egg-None-CounterTop-12/trial_T20190908_215527_416490/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0029", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Mug-None-CoffeeMachine-1/trial_T20190907_222924_821086/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0030", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Mug-None-CoffeeMachine-28/trial_T20190908_062730_537428/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0031", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Plate-None-Cabinet-13/trial_T20190907_062749_759882/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0032", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Potato-None-Fridge-2/trial_T20190909_030845_198194/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0033", + "gamefile": "json_2.1.1/train/pick_heat_then_place_in_recep-Tomato-None-CounterTop-26/trial_T20190907_005525_499114/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "train:0034", + "gamefile": "json_2.1.1/train/pick_two_obj_and_place-CD-None-Drawer-319/trial_T20190907_145515_348252/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "train:0035", + "gamefile": "json_2.1.1/train/pick_two_obj_and_place-Candle-None-Drawer-427/trial_T20190909_043917_251333/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "train:0036", + "gamefile": "json_2.1.1/train/pick_two_obj_and_place-KeyChain-None-ArmChair-222/trial_T20190909_100312_677332/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "train:0037", + "gamefile": "json_2.1.1/train/pick_two_obj_and_place-Newspaper-None-Sofa-212/trial_T20190908_112632_208041/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "train:0038", + "gamefile": "json_2.1.1/train/pick_two_obj_and_place-SaltShaker-None-SideTable-21/trial_T20190909_041626_844806/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + } +] diff --git a/data/alfworld_path_split/val/items.json b/data/alfworld_path_split/val/items.json new file mode 100644 index 0000000..e696bd3 --- /dev/null +++ b/data/alfworld_path_split/val/items.json @@ -0,0 +1,92 @@ +[ + { + "id": "val:0000", + "gamefile": "json_2.1.1/valid_seen/look_at_obj_in_light-AlarmClock-None-DeskLamp-323/trial_T20190909_044715_250790/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "val:0001", + "gamefile": "json_2.1.1/valid_seen/look_at_obj_in_light-Bowl-None-DeskLamp-301/trial_T20190909_150719_492274/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "val:0002", + "gamefile": "json_2.1.1/valid_seen/look_at_obj_in_light-Pillow-None-DeskLamp-323/trial_T20190908_053153_077977/game.tw-pddl", + "task_type": "look_at_obj_in_light" + }, + { + "id": "val:0003", + "gamefile": "json_2.1.1/valid_seen/pick_and_place_simple-Mug-None-SideTable-329/trial_T20190909_032318_169393/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "val:0004", + "gamefile": "json_2.1.1/valid_seen/pick_and_place_simple-Mug-None-SideTable-329/trial_T20190909_032340_274147/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "val:0005", + "gamefile": "json_2.1.1/valid_seen/pick_and_place_simple-Pencil-None-Desk-310/trial_T20190909_113054_894334/game.tw-pddl", + "task_type": "pick_and_place_simple" + }, + { + "id": "val:0006", + "gamefile": "json_2.1.1/valid_seen/pick_clean_then_place_in_recep-ButterKnife-None-Drawer-30/trial_T20190908_052007_212776/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "val:0007", + "gamefile": "json_2.1.1/valid_seen/pick_clean_then_place_in_recep-ButterKnife-None-Drawer-8/trial_T20190909_124425_112757/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "val:0008", + "gamefile": "json_2.1.1/valid_seen/pick_clean_then_place_in_recep-SoapBar-None-Cabinet-402/trial_T20190908_055221_984342/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "val:0009", + "gamefile": "json_2.1.1/valid_seen/pick_clean_then_place_in_recep-SoapBar-None-Toilet-410/trial_T20190906_201106_979461/game.tw-pddl", + "task_type": "pick_clean_then_place_in_recep" + }, + { + "id": "val:0010", + "gamefile": "json_2.1.1/valid_seen/pick_cool_then_place_in_recep-Apple-None-Microwave-19/trial_T20190906_210937_878489/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "val:0011", + "gamefile": "json_2.1.1/valid_seen/pick_cool_then_place_in_recep-Plate-None-CounterTop-1/trial_T20190906_205324_559361/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "val:0012", + "gamefile": "json_2.1.1/valid_seen/pick_cool_then_place_in_recep-Tomato-None-Microwave-18/trial_T20190909_012524_159092/game.tw-pddl", + "task_type": "pick_cool_then_place_in_recep" + }, + { + "id": "val:0013", + "gamefile": "json_2.1.1/valid_seen/pick_heat_then_place_in_recep-Apple-None-DiningTable-26/trial_T20190907_060234_011675/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "val:0014", + "gamefile": "json_2.1.1/valid_seen/pick_heat_then_place_in_recep-Tomato-None-Fridge-15/trial_T20190909_020200_054379/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "val:0015", + "gamefile": "json_2.1.1/valid_seen/pick_heat_then_place_in_recep-Tomato-None-Fridge-23/trial_T20190909_082320_103350/game.tw-pddl", + "task_type": "pick_heat_then_place_in_recep" + }, + { + "id": "val:0016", + "gamefile": "json_2.1.1/valid_seen/pick_two_obj_and_place-Book-None-Desk-313/trial_T20190908_125930_920681/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + }, + { + "id": "val:0017", + "gamefile": "json_2.1.1/valid_seen/pick_two_obj_and_place-CreditCard-None-Safe-323/trial_T20190907_001129_214240/game.tw-pddl", + "task_type": "pick_two_obj_and_place" + } +] diff --git a/data/docvqa_id_split/split_manifest.json b/data/docvqa_id_split/split_manifest.json new file mode 100644 index 0000000..48696de --- /dev/null +++ b/data/docvqa_id_split/split_manifest.json @@ -0,0 +1,36 @@ +{ + "benchmark": "DocVQA", + "manifest_type": "id_split", + "source_repo": "lmms-lab/DocVQA", + "source_repo_type": "dataset", + "source_url": "https://huggingface.co/datasets/lmms-lab/DocVQA", + "source_revision": "539088ef8a8ada01ac8e2e6d4e372586748a265e", + "source_config": "DocVQA", + "source_split": "validation", + "source_split_name": "docvqa_validation_10pct", + "split_method": "10% subset sampled from the DocVQA validation split", + "counts": { + "train": 107, + "val": 53, + "test": 374 + }, + "item_fields": [ + "id", + "questionId", + "docId", + "image_path", + "ucsf_document_id", + "ucsf_document_page_no", + "topic", + "source_dataset", + "source_config", + "source_split", + "sample_seed" + ], + "notes": [ + "This is a split manifest, not the full DocVQA payload.", + "Materialize full CSV rows and image files before evaluation.", + "This manifest corresponds to docvqa_validation_10pct.", + "All released train/val/test items originate from a 10% subset of the official DocVQA validation split." + ] +} diff --git a/data/docvqa_id_split/test/items.json b/data/docvqa_id_split/test/items.json new file mode 100644 index 0000000..7c103a9 --- /dev/null +++ b/data/docvqa_id_split/test/items.json @@ -0,0 +1,4864 @@ +[ + { + "id": "63180", + "questionId": "63180", + "docId": "9099", + "image_path": "data/docvqa_images/q63180_d9099.png", + "ucsf_document_id": "jlmf0227", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53705", + "questionId": "53705", + "docId": "3630", + "image_path": "data/docvqa_images/q53705_d3630.png", + "ucsf_document_id": "rhhx0023", + "ucsf_document_page_no": "1", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54376", + "questionId": "54376", + "docId": "3626", + "image_path": "data/docvqa_images/q54376_d3626.png", + "ucsf_document_id": "glxm0052", + "ucsf_document_page_no": "3", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63763", + "questionId": "63763", + "docId": "9581", + "image_path": "data/docvqa_images/q63763_d9581.png", + "ucsf_document_id": "mxmg0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47931", + "questionId": "47931", + "docId": "13884", + "image_path": "data/docvqa_images/q47931_d13884.png", + "ucsf_document_id": "qnfm0227", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47535", + "questionId": "47535", + "docId": "13650", + "image_path": "data/docvqa_images/q47535_d13650.png", + "ucsf_document_id": "pmdv0228", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37329", + "questionId": "37329", + "docId": "10759", + "image_path": "data/docvqa_images/q37329_d10759.png", + "ucsf_document_id": "tjpg0227", + "ucsf_document_page_no": "9", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "26657", + "questionId": "26657", + "docId": "7470", + "image_path": "data/docvqa_images/q26657_d7470.png", + "ucsf_document_id": "lhmg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44939", + "questionId": "44939", + "docId": "12948", + "image_path": "data/docvqa_images/q44939_d12948.png", + "ucsf_document_id": "pmyl0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58754", + "questionId": "58754", + "docId": "5696", + "image_path": "data/docvqa_images/q58754_d5696.png", + "ucsf_document_id": "ggmk0079", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54624", + "questionId": "54624", + "docId": "1992", + "image_path": "data/docvqa_images/q54624_d1992.png", + "ucsf_document_id": "kkny0225", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1900", + "questionId": "1900", + "docId": "845", + "image_path": "data/docvqa_images/q1900_d845.png", + "ucsf_document_id": "thcn0226", + "ucsf_document_page_no": "3", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1978", + "questionId": "1978", + "docId": "909", + "image_path": "data/docvqa_images/q1978_d909.png", + "ucsf_document_id": "jqbn0226", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "21068", + "questionId": "21068", + "docId": "6207", + "image_path": "data/docvqa_images/q21068_d6207.png", + "ucsf_document_id": "txcx0227", + "ucsf_document_page_no": "13", + "topic": "form|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63787", + "questionId": "63787", + "docId": "9619", + "image_path": "data/docvqa_images/q63787_d9619.png", + "ucsf_document_id": "ngvh0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55256", + "questionId": "55256", + "docId": "14298", + "image_path": "data/docvqa_images/q55256_d14298.png", + "ucsf_document_id": "lynb0228", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56275", + "questionId": "56275", + "docId": "5060", + "image_path": "data/docvqa_images/q56275_d5060.png", + "ucsf_document_id": "gpnn0081", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50802", + "questionId": "50802", + "docId": "14747", + "image_path": "data/docvqa_images/q50802_d14747.png", + "ucsf_document_id": "nzfv0228", + "ucsf_document_page_no": "2", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5558", + "questionId": "5558", + "docId": "1885", + "image_path": "data/docvqa_images/q5558_d1885.png", + "ucsf_document_id": "frjh0225", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45724", + "questionId": "45724", + "docId": "13549", + "image_path": "data/docvqa_images/q45724_d13549.png", + "ucsf_document_id": "yscw0217", + "ucsf_document_page_no": "12", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54909", + "questionId": "54909", + "docId": "4183", + "image_path": "data/docvqa_images/q54909_d4183.png", + "ucsf_document_id": "mhcg0072", + "ucsf_document_page_no": "43", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43773", + "questionId": "43773", + "docId": "12709", + "image_path": "data/docvqa_images/q43773_d12709.png", + "ucsf_document_id": "jkhn0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56451", + "questionId": "56451", + "docId": "14795", + "image_path": "data/docvqa_images/q56451_d14795.png", + "ucsf_document_id": "gnnp0227", + "ucsf_document_page_no": "6", + "topic": "Yes/No|handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61985", + "questionId": "61985", + "docId": "8179", + "image_path": "data/docvqa_images/q61985_d8179.png", + "ucsf_document_id": "zpyp0227", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7012", + "questionId": "7012", + "docId": "2392", + "image_path": "data/docvqa_images/q7012_d2392.png", + "ucsf_document_id": "gggw0004", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50508", + "questionId": "50508", + "docId": "245", + "image_path": "data/docvqa_images/q50508_d245.png", + "ucsf_document_id": "nrcj0037", + "ucsf_document_page_no": "8", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47517", + "questionId": "47517", + "docId": "13640", + "image_path": "data/docvqa_images/q47517_d13640.png", + "ucsf_document_id": "pydv0228", + "ucsf_document_page_no": "9", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65341", + "questionId": "65341", + "docId": "10882", + "image_path": "data/docvqa_images/q65341_d10882.png", + "ucsf_document_id": "kfhd0227", + "ucsf_document_page_no": "22", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6822", + "questionId": "6822", + "docId": "2361", + "image_path": "data/docvqa_images/q6822_d2361.png", + "ucsf_document_id": "rmpn0000", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55026", + "questionId": "55026", + "docId": "4162", + "image_path": "data/docvqa_images/q55026_d4162.png", + "ucsf_document_id": "yldg0072", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53438", + "questionId": "53438", + "docId": "2715", + "image_path": "data/docvqa_images/q53438_d2715.png", + "ucsf_document_id": "yhxn0020", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63868", + "questionId": "63868", + "docId": "9631", + "image_path": "data/docvqa_images/q63868_d9631.png", + "ucsf_document_id": "nlcf0227", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16837", + "questionId": "16837", + "docId": "5324", + "image_path": "data/docvqa_images/q16837_d5324.png", + "ucsf_document_id": "rgcw0217", + "ucsf_document_page_no": "7", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57531", + "questionId": "57531", + "docId": "4843", + "image_path": "data/docvqa_images/q57531_d4843.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "7", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50770", + "questionId": "50770", + "docId": "377", + "image_path": "data/docvqa_images/q50770_d377.png", + "ucsf_document_id": "mtyj0226", + "ucsf_document_page_no": "8", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60597", + "questionId": "60597", + "docId": "7232", + "image_path": "data/docvqa_images/q60597_d7232.png", + "ucsf_document_id": "symf0227", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60403", + "questionId": "60403", + "docId": "7135", + "image_path": "data/docvqa_images/q60403_d7135.png", + "ucsf_document_id": "gkpk0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "24116", + "questionId": "24116", + "docId": "6922", + "image_path": "data/docvqa_images/q24116_d6922.png", + "ucsf_document_id": "xjhk0226", + "ucsf_document_page_no": "1", + "topic": "form|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65404", + "questionId": "65404", + "docId": "10983", + "image_path": "data/docvqa_images/q65404_d10983.png", + "ucsf_document_id": "msmg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "359", + "questionId": "359", + "docId": "287", + "image_path": "data/docvqa_images/q359_d287.png", + "ucsf_document_id": "rzbj0037", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58419", + "questionId": "58419", + "docId": "5926", + "image_path": "data/docvqa_images/q58419_d5926.png", + "ucsf_document_id": "lybx0227", + "ucsf_document_page_no": "23", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64587", + "questionId": "64587", + "docId": "10364", + "image_path": "data/docvqa_images/q64587_d10364.png", + "ucsf_document_id": "lpdl0226", + "ucsf_document_page_no": "13", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64328", + "questionId": "64328", + "docId": "10196", + "image_path": "data/docvqa_images/q64328_d10196.png", + "ucsf_document_id": "jjmd0217", + "ucsf_document_page_no": "2", + "topic": "Yes/No|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64219", + "questionId": "64219", + "docId": "10014", + "image_path": "data/docvqa_images/q64219_d10014.png", + "ucsf_document_id": "qjcf0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "2143", + "questionId": "2143", + "docId": "1039", + "image_path": "data/docvqa_images/q2143_d1039.png", + "ucsf_document_id": "khnk0226", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47550", + "questionId": "47550", + "docId": "13691", + "image_path": "data/docvqa_images/q47550_d13691.png", + "ucsf_document_id": "frdv0228", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "8073", + "questionId": "8073", + "docId": "2823", + "image_path": "data/docvqa_images/q8073_d2823.png", + "ucsf_document_id": "pfcn0020", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5607", + "questionId": "5607", + "docId": "1888", + "image_path": "data/docvqa_images/q5607_d1888.png", + "ucsf_document_id": "fqwx0225", + "ucsf_document_page_no": "10", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3072", + "questionId": "3072", + "docId": "1210", + "image_path": "data/docvqa_images/q3072_d1210.png", + "ucsf_document_id": "gxph0227", + "ucsf_document_page_no": "8", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51369", + "questionId": "51369", + "docId": "794", + "image_path": "data/docvqa_images/q51369_d794.png", + "ucsf_document_id": "nlcn0226", + "ucsf_document_page_no": "4", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59443", + "questionId": "59443", + "docId": "5992", + "image_path": "data/docvqa_images/q59443_d5992.png", + "ucsf_document_id": "ffhx0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64188", + "questionId": "64188", + "docId": "9872", + "image_path": "data/docvqa_images/q64188_d9872.png", + "ucsf_document_id": "ptkg0227", + "ucsf_document_page_no": "32", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50924", + "questionId": "50924", + "docId": "473", + "image_path": "data/docvqa_images/q50924_d473.png", + "ucsf_document_id": "ptjf0226", + "ucsf_document_page_no": "3", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "788", + "questionId": "788", + "docId": "408", + "image_path": "data/docvqa_images/q788_d408.png", + "ucsf_document_id": "kfpj0226", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45005", + "questionId": "45005", + "docId": "12959", + "image_path": "data/docvqa_images/q45005_d12959.png", + "ucsf_document_id": "qtgl0226", + "ucsf_document_page_no": "2", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57323", + "questionId": "57323", + "docId": "4722", + "image_path": "data/docvqa_images/q57323_d4722.png", + "ucsf_document_id": "xybx0223", + "ucsf_document_page_no": "32", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32154", + "questionId": "32154", + "docId": "9013", + "image_path": "data/docvqa_images/q32154_d9013.png", + "ucsf_document_id": "qxmp0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56363", + "questionId": "56363", + "docId": "14780", + "image_path": "data/docvqa_images/q56363_d14780.png", + "ucsf_document_id": "lyvd0228", + "ucsf_document_page_no": "6", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5392", + "questionId": "5392", + "docId": "1817", + "image_path": "data/docvqa_images/q5392_d1817.png", + "ucsf_document_id": "xhfl0228", + "ucsf_document_page_no": "7", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5313", + "questionId": "5313", + "docId": "1791", + "image_path": "data/docvqa_images/q5313_d1791.png", + "ucsf_document_id": "myph0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45837", + "questionId": "45837", + "docId": "13402", + "image_path": "data/docvqa_images/q45837_d13402.png", + "ucsf_document_id": "zqdw0217", + "ucsf_document_page_no": "14", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56457", + "questionId": "56457", + "docId": "14795", + "image_path": "data/docvqa_images/q56457_d14795.png", + "ucsf_document_id": "gnnp0227", + "ucsf_document_page_no": "6", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "34135", + "questionId": "34135", + "docId": "9725", + "image_path": "data/docvqa_images/q34135_d9725.png", + "ucsf_document_id": "mswg0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15008", + "questionId": "15008", + "docId": "5026", + "image_path": "data/docvqa_images/q15008_d5026.png", + "ucsf_document_id": "mnvw0217", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51601", + "questionId": "51601", + "docId": "1130", + "image_path": "data/docvqa_images/q51601_d1130.png", + "ucsf_document_id": "gnjk0226", + "ucsf_document_page_no": "1", + "topic": "handwritten|form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64491", + "questionId": "64491", + "docId": "10307", + "image_path": "data/docvqa_images/q64491_d10307.png", + "ucsf_document_id": "lpdl0226", + "ucsf_document_page_no": "15", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56887", + "questionId": "56887", + "docId": "5208", + "image_path": "data/docvqa_images/q56887_d5208.png", + "ucsf_document_id": "jxyn0081", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63246", + "questionId": "63246", + "docId": "9218", + "image_path": "data/docvqa_images/q63246_d9218.png", + "ucsf_document_id": "pqxf0227", + "ucsf_document_page_no": "1", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58558", + "questionId": "58558", + "docId": "4748", + "image_path": "data/docvqa_images/q58558_d4748.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "205", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43110", + "questionId": "43110", + "docId": "12398", + "image_path": "data/docvqa_images/q43110_d12398.png", + "ucsf_document_id": "fggn0226", + "ucsf_document_page_no": "48", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47554", + "questionId": "47554", + "docId": "13691", + "image_path": "data/docvqa_images/q47554_d13691.png", + "ucsf_document_id": "frdv0228", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51224", + "questionId": "51224", + "docId": "768", + "image_path": "data/docvqa_images/q51224_d768.png", + "ucsf_document_id": "ngcn0226", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51484", + "questionId": "51484", + "docId": "1735", + "image_path": "data/docvqa_images/q51484_d1735.png", + "ucsf_document_id": "fpxh0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64634", + "questionId": "64634", + "docId": "10908", + "image_path": "data/docvqa_images/q64634_d10908.png", + "ucsf_document_id": "yrpf0227", + "ucsf_document_page_no": "3", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59802", + "questionId": "59802", + "docId": "6708", + "image_path": "data/docvqa_images/q59802_d6708.png", + "ucsf_document_id": "xkxb0228", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5821", + "questionId": "5821", + "docId": "1996", + "image_path": "data/docvqa_images/q5821_d1996.png", + "ucsf_document_id": "zylj0226", + "ucsf_document_page_no": "7", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45425", + "questionId": "45425", + "docId": "13589", + "image_path": "data/docvqa_images/q45425_d13589.png", + "ucsf_document_id": "zrdw0217", + "ucsf_document_page_no": "1", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56580", + "questionId": "56580", + "docId": "14789", + "image_path": "data/docvqa_images/q56580_d14789.png", + "ucsf_document_id": "kpkp0227", + "ucsf_document_page_no": "14", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52637", + "questionId": "52637", + "docId": "2295", + "image_path": "data/docvqa_images/q52637_d2295.png", + "ucsf_document_id": "fglc0003", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3071", + "questionId": "3071", + "docId": "1210", + "image_path": "data/docvqa_images/q3071_d1210.png", + "ucsf_document_id": "gxph0227", + "ucsf_document_page_no": "8", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58835", + "questionId": "58835", + "docId": "5846", + "image_path": "data/docvqa_images/q58835_d5846.png", + "ucsf_document_id": "knlm0227", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56812", + "questionId": "56812", + "docId": "14919", + "image_path": "data/docvqa_images/q56812_d14919.png", + "ucsf_document_id": "qlkp0227", + "ucsf_document_page_no": "4", + "topic": "handwritten|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62508", + "questionId": "62508", + "docId": "7596", + "image_path": "data/docvqa_images/q62508_d7596.png", + "ucsf_document_id": "fybg0227", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50303", + "questionId": "50303", + "docId": "14571", + "image_path": "data/docvqa_images/q50303_d14571.png", + "ucsf_document_id": "rrdd0228", + "ucsf_document_page_no": "14", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58426", + "questionId": "58426", + "docId": "5313", + "image_path": "data/docvqa_images/q58426_d5313.png", + "ucsf_document_id": "jmcw0217", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64255", + "questionId": "64255", + "docId": "10121", + "image_path": "data/docvqa_images/q64255_d10121.png", + "ucsf_document_id": "lpjm0223", + "ucsf_document_page_no": "58", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1014", + "questionId": "1014", + "docId": "491", + "image_path": "data/docvqa_images/q1014_d491.png", + "ucsf_document_id": "gyjf0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58878", + "questionId": "58878", + "docId": "6096", + "image_path": "data/docvqa_images/q58878_d6096.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "101", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56371", + "questionId": "56371", + "docId": "14778", + "image_path": "data/docvqa_images/q56371_d14778.png", + "ucsf_document_id": "skgb0228", + "ucsf_document_page_no": "43", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58675", + "questionId": "58675", + "docId": "5550", + "image_path": "data/docvqa_images/q58675_d5550.png", + "ucsf_document_id": "fxcv0079", + "ucsf_document_page_no": "4", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7028", + "questionId": "7028", + "docId": "2396", + "image_path": "data/docvqa_images/q7028_d2396.png", + "ucsf_document_id": "myjf0004", + "ucsf_document_page_no": "2", + "topic": "handwritten|free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59022", + "questionId": "59022", + "docId": "6223", + "image_path": "data/docvqa_images/q59022_d6223.png", + "ucsf_document_id": "kmhx0227", + "ucsf_document_page_no": "4", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47003", + "questionId": "47003", + "docId": "13613", + "image_path": "data/docvqa_images/q47003_d13613.png", + "ucsf_document_id": "pyyc0227", + "ucsf_document_page_no": "52", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "17140", + "questionId": "17140", + "docId": "5400", + "image_path": "data/docvqa_images/q17140_d5400.png", + "ucsf_document_id": "zkww0217", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64166", + "questionId": "64166", + "docId": "9866", + "image_path": "data/docvqa_images/q64166_d9866.png", + "ucsf_document_id": "yllg0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5858", + "questionId": "5858", + "docId": "2006", + "image_path": "data/docvqa_images/q5858_d2006.png", + "ucsf_document_id": "lzkh0228", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "2175", + "questionId": "2175", + "docId": "1039", + "image_path": "data/docvqa_images/q2175_d1039.png", + "ucsf_document_id": "khnk0226", + "ucsf_document_page_no": "4", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57313", + "questionId": "57313", + "docId": "4712", + "image_path": "data/docvqa_images/q57313_d4712.png", + "ucsf_document_id": "mtgj0223", + "ucsf_document_page_no": "17", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43626", + "questionId": "43626", + "docId": "12512", + "image_path": "data/docvqa_images/q43626_d12512.png", + "ucsf_document_id": "lngn0226", + "ucsf_document_page_no": "5", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55032", + "questionId": "55032", + "docId": "4163", + "image_path": "data/docvqa_images/q55032_d4163.png", + "ucsf_document_id": "tqcg0072", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57213", + "questionId": "57213", + "docId": "4812", + "image_path": "data/docvqa_images/q57213_d4812.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3079", + "questionId": "3079", + "docId": "1210", + "image_path": "data/docvqa_images/q3079_d1210.png", + "ucsf_document_id": "gxph0227", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55926", + "questionId": "55926", + "docId": "4244", + "image_path": "data/docvqa_images/q55926_d4244.png", + "ucsf_document_id": "jybx0223", + "ucsf_document_page_no": "11", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32157", + "questionId": "32157", + "docId": "9013", + "image_path": "data/docvqa_images/q32157_d9013.png", + "ucsf_document_id": "qxmp0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "28064", + "questionId": "28064", + "docId": "7867", + "image_path": "data/docvqa_images/q28064_d7867.png", + "ucsf_document_id": "zznp0227", + "ucsf_document_page_no": "107", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15041", + "questionId": "15041", + "docId": "5023", + "image_path": "data/docvqa_images/q15041_d5023.png", + "ucsf_document_id": "yxvw0217", + "ucsf_document_page_no": "7", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50515", + "questionId": "50515", + "docId": "219", + "image_path": "data/docvqa_images/q50515_d219.png", + "ucsf_document_id": "ppwl0228", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47073", + "questionId": "47073", + "docId": "13939", + "image_path": "data/docvqa_images/q47073_d13939.png", + "ucsf_document_id": "pnfm0227", + "ucsf_document_page_no": "7", + "topic": "handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58454", + "questionId": "58454", + "docId": "5315", + "image_path": "data/docvqa_images/q58454_d5315.png", + "ucsf_document_id": "mlbw0217", + "ucsf_document_page_no": "6", + "topic": "table/list|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45740", + "questionId": "45740", + "docId": "13581", + "image_path": "data/docvqa_images/q45740_d13581.png", + "ucsf_document_id": "yrvw0217", + "ucsf_document_page_no": "55", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62129", + "questionId": "62129", + "docId": "8322", + "image_path": "data/docvqa_images/q62129_d8322.png", + "ucsf_document_id": "ljgf0227", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47537", + "questionId": "47537", + "docId": "13650", + "image_path": "data/docvqa_images/q47537_d13650.png", + "ucsf_document_id": "pmdv0228", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5552", + "questionId": "5552", + "docId": "1875", + "image_path": "data/docvqa_images/q5552_d1875.png", + "ucsf_document_id": "mnfl0228", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63876", + "questionId": "63876", + "docId": "9654", + "image_path": "data/docvqa_images/q63876_d9654.png", + "ucsf_document_id": "mswg0227", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46435", + "questionId": "46435", + "docId": "13048", + "image_path": "data/docvqa_images/q46435_d13048.png", + "ucsf_document_id": "tzjl0226", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50968", + "questionId": "50968", + "docId": "549", + "image_path": "data/docvqa_images/q50968_d549.png", + "ucsf_document_id": "qtjf0226", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32878", + "questionId": "32878", + "docId": "9253", + "image_path": "data/docvqa_images/q32878_d9253.png", + "ucsf_document_id": "hnhd0227", + "ucsf_document_page_no": "8", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7025", + "questionId": "7025", + "docId": "2396", + "image_path": "data/docvqa_images/q7025_d2396.png", + "ucsf_document_id": "myjf0004", + "ucsf_document_page_no": "2", + "topic": "handwritten|free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47452", + "questionId": "47452", + "docId": "13639", + "image_path": "data/docvqa_images/q47452_d13639.png", + "ucsf_document_id": "skdv0228", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63158", + "questionId": "63158", + "docId": "9088", + "image_path": "data/docvqa_images/q63158_d9088.png", + "ucsf_document_id": "lnyc0227", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "38039", + "questionId": "38039", + "docId": "10946", + "image_path": "data/docvqa_images/q38039_d10946.png", + "ucsf_document_id": "kzng0227", + "ucsf_document_page_no": "48", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46421", + "questionId": "46421", + "docId": "13048", + "image_path": "data/docvqa_images/q46421_d13048.png", + "ucsf_document_id": "tzjl0226", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62392", + "questionId": "62392", + "docId": "7462", + "image_path": "data/docvqa_images/q62392_d7462.png", + "ucsf_document_id": "jfgg0227", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49121", + "questionId": "49121", + "docId": "14218", + "image_path": "data/docvqa_images/q49121_d14218.png", + "ucsf_document_id": "qtyp0227", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63560", + "questionId": "63560", + "docId": "9304", + "image_path": "data/docvqa_images/q63560_d9304.png", + "ucsf_document_id": "jjvg0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32896", + "questionId": "32896", + "docId": "9419", + "image_path": "data/docvqa_images/q32896_d9419.png", + "ucsf_document_id": "sxvg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "39079", + "questionId": "39079", + "docId": "11190", + "image_path": "data/docvqa_images/q39079_d11190.png", + "ucsf_document_id": "qqvf0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "4438", + "questionId": "4438", + "docId": "1971", + "image_path": "data/docvqa_images/q4438_d1971.png", + "ucsf_document_id": "rxxk0225", + "ucsf_document_page_no": "9", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15094", + "questionId": "15094", + "docId": "4768", + "image_path": "data/docvqa_images/q15094_d4768.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "211", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "38032", + "questionId": "38032", + "docId": "10946", + "image_path": "data/docvqa_images/q38032_d10946.png", + "ucsf_document_id": "kzng0227", + "ucsf_document_page_no": "48", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62828", + "questionId": "62828", + "docId": "8866", + "image_path": "data/docvqa_images/q62828_d8866.png", + "ucsf_document_id": "qxhc0228", + "ucsf_document_page_no": "6", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46295", + "questionId": "46295", + "docId": "13358", + "image_path": "data/docvqa_images/q46295_d13358.png", + "ucsf_document_id": "yscw0217", + "ucsf_document_page_no": "61", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56435", + "questionId": "56435", + "docId": "14800", + "image_path": "data/docvqa_images/q56435_d14800.png", + "ucsf_document_id": "jrcy0227", + "ucsf_document_page_no": "15", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53576", + "questionId": "53576", + "docId": "2766", + "image_path": "data/docvqa_images/q53576_d2766.png", + "ucsf_document_id": "hsfn0020", + "ucsf_document_page_no": "2", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37654", + "questionId": "37654", + "docId": "10833", + "image_path": "data/docvqa_images/q37654_d10833.png", + "ucsf_document_id": "yjvg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46506", + "questionId": "46506", + "docId": "12445", + "image_path": "data/docvqa_images/q46506_d12445.png", + "ucsf_document_id": "gggn0226", + "ucsf_document_page_no": "50", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "25502", + "questionId": "25502", + "docId": "7245", + "image_path": "data/docvqa_images/q25502_d7245.png", + "ucsf_document_id": "pzbd0227", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49055", + "questionId": "49055", + "docId": "14189", + "image_path": "data/docvqa_images/q49055_d14189.png", + "ucsf_document_id": "qtyp0227", + "ucsf_document_page_no": "9", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62284", + "questionId": "62284", + "docId": "8429", + "image_path": "data/docvqa_images/q62284_d8429.png", + "ucsf_document_id": "nhkw0227", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54490", + "questionId": "54490", + "docId": "3645", + "image_path": "data/docvqa_images/q54490_d3645.png", + "ucsf_document_id": "tqgk0023", + "ucsf_document_page_no": "13", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63636", + "questionId": "63636", + "docId": "9346", + "image_path": "data/docvqa_images/q63636_d9346.png", + "ucsf_document_id": "fncf0227", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57242", + "questionId": "57242", + "docId": "4719", + "image_path": "data/docvqa_images/q57242_d4719.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "221", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49326", + "questionId": "49326", + "docId": "14304", + "image_path": "data/docvqa_images/q49326_d14304.png", + "ucsf_document_id": "qqvv0228", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65215", + "questionId": "65215", + "docId": "10856", + "image_path": "data/docvqa_images/q65215_d10856.png", + "ucsf_document_id": "kjgf0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64742", + "questionId": "64742", + "docId": "10501", + "image_path": "data/docvqa_images/q64742_d10501.png", + "ucsf_document_id": "zybd0227", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37663", + "questionId": "37663", + "docId": "10835", + "image_path": "data/docvqa_images/q37663_d10835.png", + "ucsf_document_id": "jqxf0227", + "ucsf_document_page_no": "28", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64706", + "questionId": "64706", + "docId": "10475", + "image_path": "data/docvqa_images/q64706_d10475.png", + "ucsf_document_id": "njnf0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "237", + "questionId": "237", + "docId": "230", + "image_path": "data/docvqa_images/q237_d230.png", + "ucsf_document_id": "ljxj0037", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6399", + "questionId": "6399", + "docId": "2242", + "image_path": "data/docvqa_images/q6399_d2242.png", + "ucsf_document_id": "jkcn0000", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64935", + "questionId": "64935", + "docId": "10811", + "image_path": "data/docvqa_images/q64935_d10811.png", + "ucsf_document_id": "ylwg0227", + "ucsf_document_page_no": "15", + "topic": "figure/diagram|free_text|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43224", + "questionId": "43224", + "docId": "12426", + "image_path": "data/docvqa_images/q43224_d12426.png", + "ucsf_document_id": "hmxn0226", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "31079", + "questionId": "31079", + "docId": "8697", + "image_path": "data/docvqa_images/q31079_d8697.png", + "ucsf_document_id": "yhxd0227", + "ucsf_document_page_no": "3", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57543", + "questionId": "57543", + "docId": "4850", + "image_path": "data/docvqa_images/q57543_d4850.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "10", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5413", + "questionId": "5413", + "docId": "1840", + "image_path": "data/docvqa_images/q5413_d1840.png", + "ucsf_document_id": "flfl0228", + "ucsf_document_page_no": "1", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6357", + "questionId": "6357", + "docId": "2225", + "image_path": "data/docvqa_images/q6357_d2225.png", + "ucsf_document_id": "gmhp0000", + "ucsf_document_page_no": "2", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53813", + "questionId": "53813", + "docId": "3200", + "image_path": "data/docvqa_images/q53813_d3200.png", + "ucsf_document_id": "kmfh0023", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51664", + "questionId": "51664", + "docId": "1203", + "image_path": "data/docvqa_images/q51664_d1203.png", + "ucsf_document_id": "hnjh0227", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50295", + "questionId": "50295", + "docId": "14571", + "image_path": "data/docvqa_images/q50295_d14571.png", + "ucsf_document_id": "rrdd0228", + "ucsf_document_page_no": "14", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16473", + "questionId": "16473", + "docId": "5189", + "image_path": "data/docvqa_images/q16473_d5189.png", + "ucsf_document_id": "hsyn0081", + "ucsf_document_page_no": "16", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43719", + "questionId": "43719", + "docId": "12536", + "image_path": "data/docvqa_images/q43719_d12536.png", + "ucsf_document_id": "qjgn0226", + "ucsf_document_page_no": "74", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58694", + "questionId": "58694", + "docId": "5545", + "image_path": "data/docvqa_images/q58694_d5545.png", + "ucsf_document_id": "hhwh0078", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59655", + "questionId": "59655", + "docId": "6579", + "image_path": "data/docvqa_images/q59655_d6579.png", + "ucsf_document_id": "mzbx0227", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58310", + "questionId": "58310", + "docId": "4981", + "image_path": "data/docvqa_images/q58310_d4981.png", + "ucsf_document_id": "fqvw0217", + "ucsf_document_page_no": "39", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5650", + "questionId": "5650", + "docId": "1909", + "image_path": "data/docvqa_images/q5650_d1909.png", + "ucsf_document_id": "ltlj0226", + "ucsf_document_page_no": "7", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47993", + "questionId": "47993", + "docId": "14096", + "image_path": "data/docvqa_images/q47993_d14096.png", + "ucsf_document_id": "lkcv0228", + "ucsf_document_page_no": "17", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64636", + "questionId": "64636", + "docId": "10908", + "image_path": "data/docvqa_images/q64636_d10908.png", + "ucsf_document_id": "yrpf0227", + "ucsf_document_page_no": "3", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44854", + "questionId": "44854", + "docId": "12889", + "image_path": "data/docvqa_images/q44854_d12889.png", + "ucsf_document_id": "rmwn0226", + "ucsf_document_page_no": "95", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55464", + "questionId": "55464", + "docId": "4331", + "image_path": "data/docvqa_images/q55464_d4331.png", + "ucsf_document_id": "gsgj0223", + "ucsf_document_page_no": "68", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58289", + "questionId": "58289", + "docId": "4973", + "image_path": "data/docvqa_images/q58289_d4973.png", + "ucsf_document_id": "npvw0217", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49126", + "questionId": "49126", + "docId": "14218", + "image_path": "data/docvqa_images/q49126_d14218.png", + "ucsf_document_id": "qtyp0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1163", + "questionId": "1163", + "docId": "532", + "image_path": "data/docvqa_images/q1163_d532.png", + "ucsf_document_id": "hmjf0226", + "ucsf_document_page_no": "9", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51615", + "questionId": "51615", + "docId": "1168", + "image_path": "data/docvqa_images/q51615_d1168.png", + "ucsf_document_id": "fzyh0227", + "ucsf_document_page_no": "7", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64903", + "questionId": "64903", + "docId": "10574", + "image_path": "data/docvqa_images/q64903_d10574.png", + "ucsf_document_id": "lmmg0227", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62524", + "questionId": "62524", + "docId": "8587", + "image_path": "data/docvqa_images/q62524_d8587.png", + "ucsf_document_id": "xhwg0227", + "ucsf_document_page_no": "9", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "22511", + "questionId": "22511", + "docId": "6531", + "image_path": "data/docvqa_images/q22511_d6531.png", + "ucsf_document_id": "xfbc0228", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46283", + "questionId": "46283", + "docId": "13358", + "image_path": "data/docvqa_images/q46283_d13358.png", + "ucsf_document_id": "yscw0217", + "ucsf_document_page_no": "61", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56576", + "questionId": "56576", + "docId": "14792", + "image_path": "data/docvqa_images/q56576_d14792.png", + "ucsf_document_id": "jjfb0228", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47525", + "questionId": "47525", + "docId": "13650", + "image_path": "data/docvqa_images/q47525_d13650.png", + "ucsf_document_id": "pmdv0228", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52374", + "questionId": "52374", + "docId": "2251", + "image_path": "data/docvqa_images/q52374_d2251.png", + "ucsf_document_id": "fqny0000", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57786", + "questionId": "57786", + "docId": "4837", + "image_path": "data/docvqa_images/q57786_d4837.png", + "ucsf_document_id": "tnbx0223", + "ucsf_document_page_no": "12", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3838", + "questionId": "3838", + "docId": "1432", + "image_path": "data/docvqa_images/q3838_d1432.png", + "ucsf_document_id": "fshk0226", + "ucsf_document_page_no": "7", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63709", + "questionId": "63709", + "docId": "9387", + "image_path": "data/docvqa_images/q63709_d9387.png", + "ucsf_document_id": "gpcg0227", + "ucsf_document_page_no": "3", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49129", + "questionId": "49129", + "docId": "14218", + "image_path": "data/docvqa_images/q49129_d14218.png", + "ucsf_document_id": "qtyp0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55197", + "questionId": "55197", + "docId": "4259", + "image_path": "data/docvqa_images/q55197_d4259.png", + "ucsf_document_id": "klvj0223", + "ucsf_document_page_no": "15", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56345", + "questionId": "56345", + "docId": "5137", + "image_path": "data/docvqa_images/q56345_d5137.png", + "ucsf_document_id": "hsyn0081", + "ucsf_document_page_no": "54", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6776", + "questionId": "6776", + "docId": "2359", + "image_path": "data/docvqa_images/q6776_d2359.png", + "ucsf_document_id": "hnhp0000", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7019", + "questionId": "7019", + "docId": "2395", + "image_path": "data/docvqa_images/q7019_d2395.png", + "ucsf_document_id": "prbw0004", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "4953", + "questionId": "4953", + "docId": "1969", + "image_path": "data/docvqa_images/q4953_d1969.png", + "ucsf_document_id": "qymj0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "42037", + "questionId": "42037", + "docId": "11940", + "image_path": "data/docvqa_images/q42037_d11940.png", + "ucsf_document_id": "tfgn0226", + "ucsf_document_page_no": "63", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47915", + "questionId": "47915", + "docId": "13885", + "image_path": "data/docvqa_images/q47915_d13885.png", + "ucsf_document_id": "qznm0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47860", + "questionId": "47860", + "docId": "13856", + "image_path": "data/docvqa_images/q47860_d13856.png", + "ucsf_document_id": "nznm0227", + "ucsf_document_page_no": "96", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64612", + "questionId": "64612", + "docId": "10376", + "image_path": "data/docvqa_images/q64612_d10376.png", + "ucsf_document_id": "hslf0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6806", + "questionId": "6806", + "docId": "2366", + "image_path": "data/docvqa_images/q6806_d2366.png", + "ucsf_document_id": "xlvf0001", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47821", + "questionId": "47821", + "docId": "14057", + "image_path": "data/docvqa_images/q47821_d14057.png", + "ucsf_document_id": "sphv0228", + "ucsf_document_page_no": "21", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53466", + "questionId": "53466", + "docId": "2749", + "image_path": "data/docvqa_images/q53466_d2749.png", + "ucsf_document_id": "fpjn0020", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49406", + "questionId": "49406", + "docId": "14325", + "image_path": "data/docvqa_images/q49406_d14325.png", + "ucsf_document_id": "txpp0227", + "ucsf_document_page_no": "9", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "41799", + "questionId": "41799", + "docId": "11850", + "image_path": "data/docvqa_images/q41799_d11850.png", + "ucsf_document_id": "qjgn0226", + "ucsf_document_page_no": "194", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63730", + "questionId": "63730", + "docId": "9561", + "image_path": "data/docvqa_images/q63730_d9561.png", + "ucsf_document_id": "nlcf0227", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64381", + "questionId": "64381", + "docId": "10159", + "image_path": "data/docvqa_images/q64381_d10159.png", + "ucsf_document_id": "gxyd0217", + "ucsf_document_page_no": "10", + "topic": "Yes/No|form|handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "4968", + "questionId": "4968", + "docId": "1977", + "image_path": "data/docvqa_images/q4968_d1977.png", + "ucsf_document_id": "rlmj0226", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "457", + "questionId": "457", + "docId": "306", + "image_path": "data/docvqa_images/q457_d306.png", + "ucsf_document_id": "mxxj0037", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52459", + "questionId": "52459", + "docId": "2050", + "image_path": "data/docvqa_images/q52459_d2050.png", + "ucsf_document_id": "rxxk0225", + "ucsf_document_page_no": "12", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18611", + "questionId": "18611", + "docId": "5691", + "image_path": "data/docvqa_images/q18611_d5691.png", + "ucsf_document_id": "fgbd0079", + "ucsf_document_page_no": "4", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "12550", + "questionId": "12550", + "docId": "4024", + "image_path": "data/docvqa_images/q12550_d4024.png", + "ucsf_document_id": "zxlf0065", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49366", + "questionId": "49366", + "docId": "14314", + "image_path": "data/docvqa_images/q49366_d14314.png", + "ucsf_document_id": "hqgb0228", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61509", + "questionId": "61509", + "docId": "7751", + "image_path": "data/docvqa_images/q61509_d7751.png", + "ucsf_document_id": "krcy0227", + "ucsf_document_page_no": "27", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "2191", + "questionId": "2191", + "docId": "1400", + "image_path": "data/docvqa_images/q2191_d1400.png", + "ucsf_document_id": "ggjh0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55340", + "questionId": "55340", + "docId": "14414", + "image_path": "data/docvqa_images/q55340_d14414.png", + "ucsf_document_id": "gnhm0227", + "ucsf_document_page_no": "7", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18961", + "questionId": "18961", + "docId": "5773", + "image_path": "data/docvqa_images/q18961_d5773.png", + "ucsf_document_id": "npbb0079", + "ucsf_document_page_no": "10", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51548", + "questionId": "51548", + "docId": "1311", + "image_path": "data/docvqa_images/q51548_d1311.png", + "ucsf_document_id": "jtlh0227", + "ucsf_document_page_no": "10", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51248", + "questionId": "51248", + "docId": "836", + "image_path": "data/docvqa_images/q51248_d836.png", + "ucsf_document_id": "pybn0226", + "ucsf_document_page_no": "1", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5591", + "questionId": "5591", + "docId": "1897", + "image_path": "data/docvqa_images/q5591_d1897.png", + "ucsf_document_id": "gpfl0225", + "ucsf_document_page_no": "7", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61125", + "questionId": "61125", + "docId": "7604", + "image_path": "data/docvqa_images/q61125_d7604.png", + "ucsf_document_id": "ngmw0227", + "ucsf_document_page_no": "1", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58464", + "questionId": "58464", + "docId": "5315", + "image_path": "data/docvqa_images/q58464_d5315.png", + "ucsf_document_id": "mlbw0217", + "ucsf_document_page_no": "6", + "topic": "table/list|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65203", + "questionId": "65203", + "docId": "10847", + "image_path": "data/docvqa_images/q65203_d10847.png", + "ucsf_document_id": "npvg0227", + "ucsf_document_page_no": "5", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63554", + "questionId": "63554", + "docId": "9304", + "image_path": "data/docvqa_images/q63554_d9304.png", + "ucsf_document_id": "jjvg0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59850", + "questionId": "59850", + "docId": "6743", + "image_path": "data/docvqa_images/q59850_d6743.png", + "ucsf_document_id": "xngv0228", + "ucsf_document_page_no": "3", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63026", + "questionId": "63026", + "docId": "13532", + "image_path": "data/docvqa_images/q63026_d13532.png", + "ucsf_document_id": "mybw0217", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50815", + "questionId": "50815", + "docId": "14743", + "image_path": "data/docvqa_images/q50815_d14743.png", + "ucsf_document_id": "mskw0228", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45151", + "questionId": "45151", + "docId": "13041", + "image_path": "data/docvqa_images/q45151_d13041.png", + "ucsf_document_id": "yjjl0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63250", + "questionId": "63250", + "docId": "9218", + "image_path": "data/docvqa_images/q63250_d9218.png", + "ucsf_document_id": "pqxf0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63771", + "questionId": "63771", + "docId": "9597", + "image_path": "data/docvqa_images/q63771_d9597.png", + "ucsf_document_id": "nldg0227", + "ucsf_document_page_no": "14", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5439", + "questionId": "5439", + "docId": "1838", + "image_path": "data/docvqa_images/q5439_d1838.png", + "ucsf_document_id": "gmgl0228", + "ucsf_document_page_no": "5", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "38912", + "questionId": "38912", + "docId": "11156", + "image_path": "data/docvqa_images/q38912_d11156.png", + "ucsf_document_id": "qsnc0227", + "ucsf_document_page_no": "72", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52155", + "questionId": "52155", + "docId": "1796", + "image_path": "data/docvqa_images/q52155_d1796.png", + "ucsf_document_id": "pgfl0228", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61164", + "questionId": "61164", + "docId": "7408", + "image_path": "data/docvqa_images/q61164_d7408.png", + "ucsf_document_id": "jldg0227", + "ucsf_document_page_no": "7", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1748", + "questionId": "1748", + "docId": "704", + "image_path": "data/docvqa_images/q1748_d704.png", + "ucsf_document_id": "jzbn0226", + "ucsf_document_page_no": "14", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45111", + "questionId": "45111", + "docId": "13037", + "image_path": "data/docvqa_images/q45111_d13037.png", + "ucsf_document_id": "yyml0226", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60447", + "questionId": "60447", + "docId": "7167", + "image_path": "data/docvqa_images/q60447_d7167.png", + "ucsf_document_id": "mfyk0226", + "ucsf_document_page_no": "8", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "21707", + "questionId": "21707", + "docId": "6870", + "image_path": "data/docvqa_images/q21707_d6870.png", + "ucsf_document_id": "ffjw0228", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63710", + "questionId": "63710", + "docId": "9387", + "image_path": "data/docvqa_images/q63710_d9387.png", + "ucsf_document_id": "gpcg0227", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45801", + "questionId": "45801", + "docId": "13560", + "image_path": "data/docvqa_images/q45801_d13560.png", + "ucsf_document_id": "ryvw0217", + "ucsf_document_page_no": "1", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58697", + "questionId": "58697", + "docId": "5694", + "image_path": "data/docvqa_images/q58697_d5694.png", + "ucsf_document_id": "fgbd0079", + "ucsf_document_page_no": "7", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56857", + "questionId": "56857", + "docId": "14906", + "image_path": "data/docvqa_images/q56857_d14906.png", + "ucsf_document_id": "jrcy0227", + "ucsf_document_page_no": "98", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5216", + "questionId": "5216", + "docId": "1768", + "image_path": "data/docvqa_images/q5216_d1768.png", + "ucsf_document_id": "nxkh0227", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59607", + "questionId": "59607", + "docId": "6561", + "image_path": "data/docvqa_images/q59607_d6561.png", + "ucsf_document_id": "tzgv0228", + "ucsf_document_page_no": "7", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54586", + "questionId": "54586", + "docId": "3706", + "image_path": "data/docvqa_images/q54586_d3706.png", + "ucsf_document_id": "lfng0023", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7615", + "questionId": "7615", + "docId": "2668", + "image_path": "data/docvqa_images/q7615_d2668.png", + "ucsf_document_id": "flxn0020", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62917", + "questionId": "62917", + "docId": "8966", + "image_path": "data/docvqa_images/q62917_d8966.png", + "ucsf_document_id": "qycc0228", + "ucsf_document_page_no": "4", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56441", + "questionId": "56441", + "docId": "14798", + "image_path": "data/docvqa_images/q56441_d14798.png", + "ucsf_document_id": "jnmw0228", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "25734", + "questionId": "25734", + "docId": "7326", + "image_path": "data/docvqa_images/q25734_d7326.png", + "ucsf_document_id": "jzhd0227", + "ucsf_document_page_no": "40", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57532", + "questionId": "57532", + "docId": "4843", + "image_path": "data/docvqa_images/q57532_d4843.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "7", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57454", + "questionId": "57454", + "docId": "4826", + "image_path": "data/docvqa_images/q57454_d4826.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "19", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "41690", + "questionId": "41690", + "docId": "11831", + "image_path": "data/docvqa_images/q41690_d11831.png", + "ucsf_document_id": "kmwn0226", + "ucsf_document_page_no": "18", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55027", + "questionId": "55027", + "docId": "4162", + "image_path": "data/docvqa_images/q55027_d4162.png", + "ucsf_document_id": "yldg0072", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16429", + "questionId": "16429", + "docId": "5178", + "image_path": "data/docvqa_images/q16429_d5178.png", + "ucsf_document_id": "xjpn0081", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5827", + "questionId": "5827", + "docId": "1981", + "image_path": "data/docvqa_images/q5827_d1981.png", + "ucsf_document_id": "rlmj0226", + "ucsf_document_page_no": "7", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1963", + "questionId": "1963", + "docId": "901", + "image_path": "data/docvqa_images/q1963_d901.png", + "ucsf_document_id": "slcn0226", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57402", + "questionId": "57402", + "docId": "4780", + "image_path": "data/docvqa_images/q57402_d4780.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "42", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64673", + "questionId": "64673", + "docId": "10446", + "image_path": "data/docvqa_images/q64673_d10446.png", + "ucsf_document_id": "hslf0227", + "ucsf_document_page_no": "9", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "36593", + "questionId": "36593", + "docId": "10553", + "image_path": "data/docvqa_images/q36593_d10553.png", + "ucsf_document_id": "hqvd0227", + "ucsf_document_page_no": "19", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "39089", + "questionId": "39089", + "docId": "11190", + "image_path": "data/docvqa_images/q39089_d11190.png", + "ucsf_document_id": "qqvf0227", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18779", + "questionId": "18779", + "docId": "5732", + "image_path": "data/docvqa_images/q18779_d5732.png", + "ucsf_document_id": "gtph0079", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64387", + "questionId": "64387", + "docId": "10159", + "image_path": "data/docvqa_images/q64387_d10159.png", + "ucsf_document_id": "gxyd0217", + "ucsf_document_page_no": "10", + "topic": "form|handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43154", + "questionId": "43154", + "docId": "12417", + "image_path": "data/docvqa_images/q43154_d12417.png", + "ucsf_document_id": "kmxn0226", + "ucsf_document_page_no": "6", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "39069", + "questionId": "39069", + "docId": "11190", + "image_path": "data/docvqa_images/q39069_d11190.png", + "ucsf_document_id": "qqvf0227", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7013", + "questionId": "7013", + "docId": "2392", + "image_path": "data/docvqa_images/q7013_d2392.png", + "ucsf_document_id": "gggw0004", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "42332", + "questionId": "42332", + "docId": "12065", + "image_path": "data/docvqa_images/q42332_d12065.png", + "ucsf_document_id": "krgn0226", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1903", + "questionId": "1903", + "docId": "859", + "image_path": "data/docvqa_images/q1903_d859.png", + "ucsf_document_id": "jsbn0226", + "ucsf_document_page_no": "6", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59928", + "questionId": "59928", + "docId": "6821", + "image_path": "data/docvqa_images/q59928_d6821.png", + "ucsf_document_id": "gmgv0228", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51791", + "questionId": "51791", + "docId": "1361", + "image_path": "data/docvqa_images/q51791_d1361.png", + "ucsf_document_id": "slkk0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16339", + "questionId": "16339", + "docId": "4878", + "image_path": "data/docvqa_images/q16339_d4878.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "228", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15036", + "questionId": "15036", + "docId": "5024", + "image_path": "data/docvqa_images/q15036_d5024.png", + "ucsf_document_id": "sxvw0217", + "ucsf_document_page_no": "2", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58443", + "questionId": "58443", + "docId": "13850", + "image_path": "data/docvqa_images/q58443_d13850.png", + "ucsf_document_id": "fxwv0228", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62859", + "questionId": "62859", + "docId": "8879", + "image_path": "data/docvqa_images/q62859_d8879.png", + "ucsf_document_id": "zmkp0227", + "ucsf_document_page_no": "7", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16424", + "questionId": "16424", + "docId": "5177", + "image_path": "data/docvqa_images/q16424_d5177.png", + "ucsf_document_id": "hsyn0081", + "ucsf_document_page_no": "31", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60048", + "questionId": "60048", + "docId": "6973", + "image_path": "data/docvqa_images/q60048_d6973.png", + "ucsf_document_id": "phwk0226", + "ucsf_document_page_no": "38", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50865", + "questionId": "50865", + "docId": "14731", + "image_path": "data/docvqa_images/q50865_d14731.png", + "ucsf_document_id": "rfgb0228", + "ucsf_document_page_no": "13", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52213", + "questionId": "52213", + "docId": "1773", + "image_path": "data/docvqa_images/q52213_d1773.png", + "ucsf_document_id": "lphk0226", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1982", + "questionId": "1982", + "docId": "913", + "image_path": "data/docvqa_images/q1982_d913.png", + "ucsf_document_id": "jqbn0226", + "ucsf_document_page_no": "33", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60872", + "questionId": "60872", + "docId": "7330", + "image_path": "data/docvqa_images/q60872_d7330.png", + "ucsf_document_id": "jzhd0227", + "ucsf_document_page_no": "67", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57312", + "questionId": "57312", + "docId": "4712", + "image_path": "data/docvqa_images/q57312_d4712.png", + "ucsf_document_id": "mtgj0223", + "ucsf_document_page_no": "17", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56268", + "questionId": "56268", + "docId": "4448", + "image_path": "data/docvqa_images/q56268_d4448.png", + "ucsf_document_id": "jybx0223", + "ucsf_document_page_no": "84", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55237", + "questionId": "55237", + "docId": "4356", + "image_path": "data/docvqa_images/q55237_d4356.png", + "ucsf_document_id": "hsgj0223", + "ucsf_document_page_no": "96", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50418", + "questionId": "50418", + "docId": "14601", + "image_path": "data/docvqa_images/q50418_d14601.png", + "ucsf_document_id": "qffw0228", + "ucsf_document_page_no": "23", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62997", + "questionId": "62997", + "docId": "8920", + "image_path": "data/docvqa_images/q62997_d8920.png", + "ucsf_document_id": "xkdv0228", + "ucsf_document_page_no": "13", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "25385", + "questionId": "25385", + "docId": "7224", + "image_path": "data/docvqa_images/q25385_d7224.png", + "ucsf_document_id": "rycg0227", + "ucsf_document_page_no": "7", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44978", + "questionId": "44978", + "docId": "12966", + "image_path": "data/docvqa_images/q44978_d12966.png", + "ucsf_document_id": "qhll0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3846", + "questionId": "3846", + "docId": "1424", + "image_path": "data/docvqa_images/q3846_d1424.png", + "ucsf_document_id": "nmmk0226", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50311", + "questionId": "50311", + "docId": "14575", + "image_path": "data/docvqa_images/q50311_d14575.png", + "ucsf_document_id": "knbd0228", + "ucsf_document_page_no": "1", + "topic": "handwritten|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49325", + "questionId": "49325", + "docId": "14304", + "image_path": "data/docvqa_images/q49325_d14304.png", + "ucsf_document_id": "qqvv0228", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47064", + "questionId": "47064", + "docId": "13937", + "image_path": "data/docvqa_images/q47064_d13937.png", + "ucsf_document_id": "nznm0227", + "ucsf_document_page_no": "122", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47559", + "questionId": "47559", + "docId": "13691", + "image_path": "data/docvqa_images/q47559_d13691.png", + "ucsf_document_id": "frdv0228", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "40624", + "questionId": "40624", + "docId": "11562", + "image_path": "data/docvqa_images/q40624_d11562.png", + "ucsf_document_id": "xlpf0227", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5776", + "questionId": "5776", + "docId": "1940", + "image_path": "data/docvqa_images/q5776_d1940.png", + "ucsf_document_id": "pzyw0224", + "ucsf_document_page_no": "10", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "611", + "questionId": "611", + "docId": "361", + "image_path": "data/docvqa_images/q611_d361.png", + "ucsf_document_id": "yhpj0226", + "ucsf_document_page_no": "2", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "9845", + "questionId": "9845", + "docId": "1867", + "image_path": "data/docvqa_images/q9845_d1867.png", + "ucsf_document_id": "ktfl0228", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15323", + "questionId": "15323", + "docId": "4866", + "image_path": "data/docvqa_images/q15323_d4866.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "3", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50840", + "questionId": "50840", + "docId": "14741", + "image_path": "data/docvqa_images/q50840_d14741.png", + "ucsf_document_id": "ysmc0228", + "ucsf_document_page_no": "6", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63569", + "questionId": "63569", + "docId": "9304", + "image_path": "data/docvqa_images/q63569_d9304.png", + "ucsf_document_id": "jjvg0227", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47044", + "questionId": "47044", + "docId": "13647", + "image_path": "data/docvqa_images/q47044_d13647.png", + "ucsf_document_id": "xndv0228", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55160", + "questionId": "55160", + "docId": "4256", + "image_path": "data/docvqa_images/q55160_d4256.png", + "ucsf_document_id": "jkvj0223", + "ucsf_document_page_no": "21", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "40598", + "questionId": "40598", + "docId": "11562", + "image_path": "data/docvqa_images/q40598_d11562.png", + "ucsf_document_id": "xlpf0227", + "ucsf_document_page_no": "1", + "topic": "handwritten|layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "22313", + "questionId": "22313", + "docId": "6486", + "image_path": "data/docvqa_images/q22313_d6486.png", + "ucsf_document_id": "jzbx0227", + "ucsf_document_page_no": "4", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55459", + "questionId": "55459", + "docId": "4331", + "image_path": "data/docvqa_images/q55459_d4331.png", + "ucsf_document_id": "gsgj0223", + "ucsf_document_page_no": "68", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16463", + "questionId": "16463", + "docId": "5181", + "image_path": "data/docvqa_images/q16463_d5181.png", + "ucsf_document_id": "psyn0081", + "ucsf_document_page_no": "30", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1024", + "questionId": "1024", + "docId": "494", + "image_path": "data/docvqa_images/q1024_d494.png", + "ucsf_document_id": "psjf0226", + "ucsf_document_page_no": "3", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45842", + "questionId": "45842", + "docId": "13402", + "image_path": "data/docvqa_images/q45842_d13402.png", + "ucsf_document_id": "zqdw0217", + "ucsf_document_page_no": "14", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37223", + "questionId": "37223", + "docId": "10703", + "image_path": "data/docvqa_images/q37223_d10703.png", + "ucsf_document_id": "rnjg0227", + "ucsf_document_page_no": "1", + "topic": "form|layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59357", + "questionId": "59357", + "docId": "6161", + "image_path": "data/docvqa_images/q59357_d6161.png", + "ucsf_document_id": "qxpn0081", + "ucsf_document_page_no": "9", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "2282", + "questionId": "2282", + "docId": "1009", + "image_path": "data/docvqa_images/q2282_d1009.png", + "ucsf_document_id": "tjpv0228", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61353", + "questionId": "61353", + "docId": "7714", + "image_path": "data/docvqa_images/q61353_d7714.png", + "ucsf_document_id": "krcy0227", + "ucsf_document_page_no": "38", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "39946", + "questionId": "39946", + "docId": "11396", + "image_path": "data/docvqa_images/q39946_d11396.png", + "ucsf_document_id": "mslw0227", + "ucsf_document_page_no": "49", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56556", + "questionId": "56556", + "docId": "5197", + "image_path": "data/docvqa_images/q56556_d5197.png", + "ucsf_document_id": "nynn0081", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46226", + "questionId": "46226", + "docId": "13351", + "image_path": "data/docvqa_images/q46226_d13351.png", + "ucsf_document_id": "rmdw0217", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63892", + "questionId": "63892", + "docId": "9653", + "image_path": "data/docvqa_images/q63892_d9653.png", + "ucsf_document_id": "lgpg0227", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59461", + "questionId": "59461", + "docId": "6263", + "image_path": "data/docvqa_images/q59461_d6263.png", + "ucsf_document_id": "kmcj0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52300", + "questionId": "52300", + "docId": "2432", + "image_path": "data/docvqa_images/q52300_d2432.png", + "ucsf_document_id": "mfnf0004", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "869", + "questionId": "869", + "docId": "427", + "image_path": "data/docvqa_images/q869_d427.png", + "ucsf_document_id": "nhpj0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "4745", + "questionId": "4745", + "docId": "1985", + "image_path": "data/docvqa_images/q4745_d1985.png", + "ucsf_document_id": "spwx0225", + "ucsf_document_page_no": "9", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "21132", + "questionId": "21132", + "docId": "6299", + "image_path": "data/docvqa_images/q21132_d6299.png", + "ucsf_document_id": "hkhx0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63657", + "questionId": "63657", + "docId": "9360", + "image_path": "data/docvqa_images/q63657_d9360.png", + "ucsf_document_id": "gkvh0227", + "ucsf_document_page_no": "1", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64278", + "questionId": "64278", + "docId": "10132", + "image_path": "data/docvqa_images/q64278_d10132.png", + "ucsf_document_id": "lpjm0223", + "ucsf_document_page_no": "56", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57170", + "questionId": "57170", + "docId": "6369", + "image_path": "data/docvqa_images/q57170_d6369.png", + "ucsf_document_id": "zmwm0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1191", + "questionId": "1191", + "docId": "538", + "image_path": "data/docvqa_images/q1191_d538.png", + "ucsf_document_id": "rtjf0226", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61578", + "questionId": "61578", + "docId": "8000", + "image_path": "data/docvqa_images/q61578_d8000.png", + "ucsf_document_id": "fqyf0227", + "ucsf_document_page_no": "15", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64831", + "questionId": "64831", + "docId": "9160", + "image_path": "data/docvqa_images/q64831_d9160.png", + "ucsf_document_id": "qnyg0227", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64940", + "questionId": "64940", + "docId": "10713", + "image_path": "data/docvqa_images/q64940_d10713.png", + "ucsf_document_id": "xhfg0227", + "ucsf_document_page_no": "23", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61605", + "questionId": "61605", + "docId": "7827", + "image_path": "data/docvqa_images/q61605_d7827.png", + "ucsf_document_id": "hlhv0228", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16832", + "questionId": "16832", + "docId": "5324", + "image_path": "data/docvqa_images/q16832_d5324.png", + "ucsf_document_id": "rgcw0217", + "ucsf_document_page_no": "7", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47712", + "questionId": "47712", + "docId": "13832", + "image_path": "data/docvqa_images/q47712_d13832.png", + "ucsf_document_id": "fmnm0227", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56471", + "questionId": "56471", + "docId": "14791", + "image_path": "data/docvqa_images/q56471_d14791.png", + "ucsf_document_id": "knpp0227", + "ucsf_document_page_no": "4", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "265", + "questionId": "265", + "docId": "244", + "image_path": "data/docvqa_images/q265_d244.png", + "ucsf_document_id": "lycj0037", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64319", + "questionId": "64319", + "docId": "10189", + "image_path": "data/docvqa_images/q64319_d10189.png", + "ucsf_document_id": "gxyd0217", + "ucsf_document_page_no": "8", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63779", + "questionId": "63779", + "docId": "9603", + "image_path": "data/docvqa_images/q63779_d9603.png", + "ucsf_document_id": "qnwd0227", + "ucsf_document_page_no": "25", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45103", + "questionId": "45103", + "docId": "12994", + "image_path": "data/docvqa_images/q45103_d12994.png", + "ucsf_document_id": "nsnl0226", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6025", + "questionId": "6025", + "docId": "2149", + "image_path": "data/docvqa_images/q6025_d2149.png", + "ucsf_document_id": "pgxg0224", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64285", + "questionId": "64285", + "docId": "10137", + "image_path": "data/docvqa_images/q64285_d10137.png", + "ucsf_document_id": "lpjm0223", + "ucsf_document_page_no": "59", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50506", + "questionId": "50506", + "docId": "245", + "image_path": "data/docvqa_images/q50506_d245.png", + "ucsf_document_id": "nrcj0037", + "ucsf_document_page_no": "8", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55366", + "questionId": "55366", + "docId": "4297", + "image_path": "data/docvqa_images/q55366_d4297.png", + "ucsf_document_id": "fmvj0223", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "4978", + "questionId": "4978", + "docId": "1982", + "image_path": "data/docvqa_images/q4978_d1982.png", + "ucsf_document_id": "lxcj0224", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59350", + "questionId": "59350", + "docId": "6175", + "image_path": "data/docvqa_images/q59350_d6175.png", + "ucsf_document_id": "srwn0081", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64169", + "questionId": "64169", + "docId": "9866", + "image_path": "data/docvqa_images/q64169_d9866.png", + "ucsf_document_id": "yllg0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44830", + "questionId": "44830", + "docId": "12882", + "image_path": "data/docvqa_images/q44830_d12882.png", + "ucsf_document_id": "rmwn0226", + "ucsf_document_page_no": "81", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63178", + "questionId": "63178", + "docId": "9099", + "image_path": "data/docvqa_images/q63178_d9099.png", + "ucsf_document_id": "jlmf0227", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56075", + "questionId": "56075", + "docId": "5156", + "image_path": "data/docvqa_images/q56075_d5156.png", + "ucsf_document_id": "lnmm0081", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58782", + "questionId": "58782", + "docId": "5785", + "image_path": "data/docvqa_images/q58782_d5785.png", + "ucsf_document_id": "khmk0079", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61228", + "questionId": "61228", + "docId": "7471", + "image_path": "data/docvqa_images/q61228_d7471.png", + "ucsf_document_id": "ggpf0227", + "ucsf_document_page_no": "27", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52274", + "questionId": "52274", + "docId": "1804", + "image_path": "data/docvqa_images/q52274_d1804.png", + "ucsf_document_id": "ypgl0228", + "ucsf_document_page_no": "3", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "26594", + "questionId": "26594", + "docId": "7525", + "image_path": "data/docvqa_images/q26594_d7525.png", + "ucsf_document_id": "nfxd0227", + "ucsf_document_page_no": "3", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "40587", + "questionId": "40587", + "docId": "11562", + "image_path": "data/docvqa_images/q40587_d11562.png", + "ucsf_document_id": "xlpf0227", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64936", + "questionId": "64936", + "docId": "10811", + "image_path": "data/docvqa_images/q64936_d10811.png", + "ucsf_document_id": "ylwg0227", + "ucsf_document_page_no": "15", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50873", + "questionId": "50873", + "docId": "14727", + "image_path": "data/docvqa_images/q50873_d14727.png", + "ucsf_document_id": "lsww0228", + "ucsf_document_page_no": "3", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57564", + "questionId": "57564", + "docId": "4851", + "image_path": "data/docvqa_images/q57564_d4851.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "21", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57798", + "questionId": "57798", + "docId": "4856", + "image_path": "data/docvqa_images/q57798_d4856.png", + "ucsf_document_id": "tnbx0223", + "ucsf_document_page_no": "130", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "54958", + "questionId": "54958", + "docId": "14307", + "image_path": "data/docvqa_images/q54958_d14307.png", + "ucsf_document_id": "sspp0227", + "ucsf_document_page_no": "30", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5675", + "questionId": "5675", + "docId": "1911", + "image_path": "data/docvqa_images/q5675_d1911.png", + "ucsf_document_id": "npwx0225", + "ucsf_document_page_no": "10", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49586", + "questionId": "49586", + "docId": "14386", + "image_path": "data/docvqa_images/q49586_d14386.png", + "ucsf_document_id": "fygb0228", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3116", + "questionId": "3116", + "docId": "1216", + "image_path": "data/docvqa_images/q3116_d1216.png", + "ucsf_document_id": "sxyv0228", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55095", + "questionId": "55095", + "docId": "4225", + "image_path": "data/docvqa_images/q55095_d4225.png", + "ucsf_document_id": "nfdg0072", + "ucsf_document_page_no": "12", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43484", + "questionId": "43484", + "docId": "12473", + "image_path": "data/docvqa_images/q43484_d12473.png", + "ucsf_document_id": "lpgn0226", + "ucsf_document_page_no": "23", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "25714", + "questionId": "25714", + "docId": "7319", + "image_path": "data/docvqa_images/q25714_d7319.png", + "ucsf_document_id": "hsbd0227", + "ucsf_document_page_no": "11", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1261", + "questionId": "1261", + "docId": "555", + "image_path": "data/docvqa_images/q1261_d555.png", + "ucsf_document_id": "jpjf0226", + "ucsf_document_page_no": "1", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16826", + "questionId": "16826", + "docId": "5324", + "image_path": "data/docvqa_images/q16826_d5324.png", + "ucsf_document_id": "rgcw0217", + "ucsf_document_page_no": "7", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64610", + "questionId": "64610", + "docId": "10376", + "image_path": "data/docvqa_images/q64610_d10376.png", + "ucsf_document_id": "hslf0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5824", + "questionId": "5824", + "docId": "1942", + "image_path": "data/docvqa_images/q5824_d1942.png", + "ucsf_document_id": "zqdj0224", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "25788", + "questionId": "25788", + "docId": "7345", + "image_path": "data/docvqa_images/q25788_d7345.png", + "ucsf_document_id": "mldg0227", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58431", + "questionId": "58431", + "docId": "5926", + "image_path": "data/docvqa_images/q58431_d5926.png", + "ucsf_document_id": "lybx0227", + "ucsf_document_page_no": "23", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6775", + "questionId": "6775", + "docId": "2359", + "image_path": "data/docvqa_images/q6775_d2359.png", + "ucsf_document_id": "hnhp0000", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63859", + "questionId": "63859", + "docId": "9647", + "image_path": "data/docvqa_images/q63859_d9647.png", + "ucsf_document_id": "kzng0227", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44130", + "questionId": "44130", + "docId": "12648", + "image_path": "data/docvqa_images/q44130_d12648.png", + "ucsf_document_id": "rmwn0226", + "ucsf_document_page_no": "79", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43265", + "questionId": "43265", + "docId": "12426", + "image_path": "data/docvqa_images/q43265_d12426.png", + "ucsf_document_id": "hmxn0226", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "283", + "questionId": "283", + "docId": "256", + "image_path": "data/docvqa_images/q283_d256.png", + "ucsf_document_id": "nhxj0037", + "ucsf_document_page_no": "3", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "42222", + "questionId": "42222", + "docId": "11955", + "image_path": "data/docvqa_images/q42222_d11955.png", + "ucsf_document_id": "kfgn0226", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65152", + "questionId": "65152", + "docId": "10772", + "image_path": "data/docvqa_images/q65152_d10772.png", + "ucsf_document_id": "pxlg0227", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "16609", + "questionId": "16609", + "docId": "5258", + "image_path": "data/docvqa_images/q16609_d5258.png", + "ucsf_document_id": "rpcw0217", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57300", + "questionId": "57300", + "docId": "6278", + "image_path": "data/docvqa_images/q57300_d6278.png", + "ucsf_document_id": "zmcj0227", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45625", + "questionId": "45625", + "docId": "12717", + "image_path": "data/docvqa_images/q45625_d12717.png", + "ucsf_document_id": "glxn0226", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "2218", + "questionId": "2218", + "docId": "1260", + "image_path": "data/docvqa_images/q2218_d1260.png", + "ucsf_document_id": "mymk0226", + "ucsf_document_page_no": "9", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64617", + "questionId": "64617", + "docId": "10406", + "image_path": "data/docvqa_images/q64617_d10406.png", + "ucsf_document_id": "hslf0227", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47454", + "questionId": "47454", + "docId": "13639", + "image_path": "data/docvqa_images/q47454_d13639.png", + "ucsf_document_id": "skdv0228", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61764", + "questionId": "61764", + "docId": "8056", + "image_path": "data/docvqa_images/q61764_d8056.png", + "ucsf_document_id": "hrfw0227", + "ucsf_document_page_no": "12", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "65115", + "questionId": "65115", + "docId": "10712", + "image_path": "data/docvqa_images/q65115_d10712.png", + "ucsf_document_id": "lmmf0227", + "ucsf_document_page_no": "3", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63537", + "questionId": "63537", + "docId": "9293", + "image_path": "data/docvqa_images/q63537_d9293.png", + "ucsf_document_id": "hgwd0227", + "ucsf_document_page_no": "34", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + } +] diff --git a/data/docvqa_id_split/train/items.json b/data/docvqa_id_split/train/items.json new file mode 100644 index 0000000..b2066e7 --- /dev/null +++ b/data/docvqa_id_split/train/items.json @@ -0,0 +1,1393 @@ +[ + { + "id": "50877", + "questionId": "50877", + "docId": "14724", + "image_path": "data/docvqa_images/q50877_d14724.png", + "ucsf_document_id": "ghlw0228", + "ucsf_document_page_no": "2", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62132", + "questionId": "62132", + "docId": "8327", + "image_path": "data/docvqa_images/q62132_d8327.png", + "ucsf_document_id": "jqbg0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60996", + "questionId": "60996", + "docId": "7599", + "image_path": "data/docvqa_images/q60996_d7599.png", + "ucsf_document_id": "kgbg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46117", + "questionId": "46117", + "docId": "13503", + "image_path": "data/docvqa_images/q46117_d13503.png", + "ucsf_document_id": "xmww0217", + "ucsf_document_page_no": "17", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37456", + "questionId": "37456", + "docId": "10794", + "image_path": "data/docvqa_images/q37456_d10794.png", + "ucsf_document_id": "ypbd0227", + "ucsf_document_page_no": "5", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51768", + "questionId": "51768", + "docId": "14553", + "image_path": "data/docvqa_images/q51768_d14553.png", + "ucsf_document_id": "fhwc0228", + "ucsf_document_page_no": "12", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5646", + "questionId": "5646", + "docId": "1902", + "image_path": "data/docvqa_images/q5646_d1902.png", + "ucsf_document_id": "qzlj0226", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57087", + "questionId": "57087", + "docId": "4624", + "image_path": "data/docvqa_images/q57087_d4624.png", + "ucsf_document_id": "mnbx0223", + "ucsf_document_page_no": "74", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "33923", + "questionId": "33923", + "docId": "9616", + "image_path": "data/docvqa_images/q33923_d9616.png", + "ucsf_document_id": "nldg0227", + "ucsf_document_page_no": "13", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60961", + "questionId": "60961", + "docId": "7572", + "image_path": "data/docvqa_images/q60961_d7572.png", + "ucsf_document_id": "mzlw0227", + "ucsf_document_page_no": "1", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32871", + "questionId": "32871", + "docId": "9252", + "image_path": "data/docvqa_images/q32871_d9252.png", + "ucsf_document_id": "hldg0227", + "ucsf_document_page_no": "7", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6869", + "questionId": "6869", + "docId": "2314", + "image_path": "data/docvqa_images/q6869_d2314.png", + "ucsf_document_id": "rpmy0000", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6010", + "questionId": "6010", + "docId": "2143", + "image_path": "data/docvqa_images/q6010_d2143.png", + "ucsf_document_id": "fllg0224", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37650", + "questionId": "37650", + "docId": "10833", + "image_path": "data/docvqa_images/q37650_d10833.png", + "ucsf_document_id": "yjvg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5474", + "questionId": "5474", + "docId": "1853", + "image_path": "data/docvqa_images/q5474_d1853.png", + "ucsf_document_id": "rkgl0228", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5612", + "questionId": "5612", + "docId": "1898", + "image_path": "data/docvqa_images/q5612_d1898.png", + "ucsf_document_id": "nhgh0228", + "ucsf_document_page_no": "6", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63700", + "questionId": "63700", + "docId": "9552", + "image_path": "data/docvqa_images/q63700_d9552.png", + "ucsf_document_id": "kjhf0227", + "ucsf_document_page_no": "3", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61551", + "questionId": "61551", + "docId": "7805", + "image_path": "data/docvqa_images/q61551_d7805.png", + "ucsf_document_id": "zxkp0227", + "ucsf_document_page_no": "4", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5778", + "questionId": "5778", + "docId": "1940", + "image_path": "data/docvqa_images/q5778_d1940.png", + "ucsf_document_id": "pzyw0224", + "ucsf_document_page_no": "10", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57801", + "questionId": "57801", + "docId": "4856", + "image_path": "data/docvqa_images/q57801_d4856.png", + "ucsf_document_id": "tnbx0223", + "ucsf_document_page_no": "130", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "40714", + "questionId": "40714", + "docId": "11589", + "image_path": "data/docvqa_images/q40714_d11589.png", + "ucsf_document_id": "hthg0227", + "ucsf_document_page_no": "8", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51244", + "questionId": "51244", + "docId": "836", + "image_path": "data/docvqa_images/q51244_d836.png", + "ucsf_document_id": "pybn0226", + "ucsf_document_page_no": "1", + "topic": "form|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47071", + "questionId": "47071", + "docId": "13937", + "image_path": "data/docvqa_images/q47071_d13937.png", + "ucsf_document_id": "nznm0227", + "ucsf_document_page_no": "122", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32546", + "questionId": "32546", + "docId": "9150", + "image_path": "data/docvqa_images/q32546_d9150.png", + "ucsf_document_id": "ztvg0227", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51661", + "questionId": "51661", + "docId": "1203", + "image_path": "data/docvqa_images/q51661_d1203.png", + "ucsf_document_id": "hnjh0227", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "44841", + "questionId": "44841", + "docId": "12889", + "image_path": "data/docvqa_images/q44841_d12889.png", + "ucsf_document_id": "rmwn0226", + "ucsf_document_page_no": "95", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5199", + "questionId": "5199", + "docId": "1768", + "image_path": "data/docvqa_images/q5199_d1768.png", + "ucsf_document_id": "nxkh0227", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6351", + "questionId": "6351", + "docId": "2225", + "image_path": "data/docvqa_images/q6351_d2225.png", + "ucsf_document_id": "gmhp0000", + "ucsf_document_page_no": "2", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61548", + "questionId": "61548", + "docId": "8776", + "image_path": "data/docvqa_images/q61548_d8776.png", + "ucsf_document_id": "yslf0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56301", + "questionId": "56301", + "docId": "5034", + "image_path": "data/docvqa_images/q56301_d5034.png", + "ucsf_document_id": "rrxm0081", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60467", + "questionId": "60467", + "docId": "13534", + "image_path": "data/docvqa_images/q60467_d13534.png", + "ucsf_document_id": "rrcw0217", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6787", + "questionId": "6787", + "docId": "2363", + "image_path": "data/docvqa_images/q6787_d2363.png", + "ucsf_document_id": "jygp0000", + "ucsf_document_page_no": "3", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63638", + "questionId": "63638", + "docId": "9346", + "image_path": "data/docvqa_images/q63638_d9346.png", + "ucsf_document_id": "fncf0227", + "ucsf_document_page_no": "2", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "271", + "questionId": "271", + "docId": "248", + "image_path": "data/docvqa_images/q271_d248.png", + "ucsf_document_id": "kscl0037", + "ucsf_document_page_no": "3", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "19245", + "questionId": "19245", + "docId": "508", + "image_path": "data/docvqa_images/q19245_d508.png", + "ucsf_document_id": "gyjf0226", + "ucsf_document_page_no": "4", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59796", + "questionId": "59796", + "docId": "6701", + "image_path": "data/docvqa_images/q59796_d6701.png", + "ucsf_document_id": "njnp0227", + "ucsf_document_page_no": "15", + "topic": "free_text|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62826", + "questionId": "62826", + "docId": "8866", + "image_path": "data/docvqa_images/q62826_d8866.png", + "ucsf_document_id": "qxhc0228", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61642", + "questionId": "61642", + "docId": "7887", + "image_path": "data/docvqa_images/q61642_d7887.png", + "ucsf_document_id": "gtjc0228", + "ucsf_document_page_no": "4", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57254", + "questionId": "57254", + "docId": "4746", + "image_path": "data/docvqa_images/q57254_d4746.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "36", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60171", + "questionId": "60171", + "docId": "7071", + "image_path": "data/docvqa_images/q60171_d7071.png", + "ucsf_document_id": "lnbl0226", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62478", + "questionId": "62478", + "docId": "8573", + "image_path": "data/docvqa_images/q62478_d8573.png", + "ucsf_document_id": "qfvg0227", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18831", + "questionId": "18831", + "docId": "5749", + "image_path": "data/docvqa_images/q18831_d5749.png", + "ucsf_document_id": "jhfd0079", + "ucsf_document_page_no": "9", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1182", + "questionId": "1182", + "docId": "536", + "image_path": "data/docvqa_images/q1182_d536.png", + "ucsf_document_id": "gmjf0226", + "ucsf_document_page_no": "4", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62646", + "questionId": "62646", + "docId": "8670", + "image_path": "data/docvqa_images/q62646_d8670.png", + "ucsf_document_id": "ztwd0227", + "ucsf_document_page_no": "2", + "topic": "layout|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57391", + "questionId": "57391", + "docId": "4772", + "image_path": "data/docvqa_images/q57391_d4772.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "14", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "17001", + "questionId": "17001", + "docId": "5370", + "image_path": "data/docvqa_images/q17001_d5370.png", + "ucsf_document_id": "tfcw0217", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45726", + "questionId": "45726", + "docId": "13221", + "image_path": "data/docvqa_images/q45726_d13221.png", + "ucsf_document_id": "yscw0217", + "ucsf_document_page_no": "129", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59600", + "questionId": "59600", + "docId": "6561", + "image_path": "data/docvqa_images/q59600_d6561.png", + "ucsf_document_id": "tzgv0228", + "ucsf_document_page_no": "7", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62840", + "questionId": "62840", + "docId": "8870", + "image_path": "data/docvqa_images/q62840_d8870.png", + "ucsf_document_id": "kjlp0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55449", + "questionId": "55449", + "docId": "4331", + "image_path": "data/docvqa_images/q55449_d4331.png", + "ucsf_document_id": "gsgj0223", + "ucsf_document_page_no": "68", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57969", + "questionId": "57969", + "docId": "4920", + "image_path": "data/docvqa_images/q57969_d4920.png", + "ucsf_document_id": "lkvw0217", + "ucsf_document_page_no": "2", + "topic": "free_text|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55949", + "questionId": "55949", + "docId": "5121", + "image_path": "data/docvqa_images/q55949_d5121.png", + "ucsf_document_id": "hsyn0081", + "ucsf_document_page_no": "17", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32892", + "questionId": "32892", + "docId": "9257", + "image_path": "data/docvqa_images/q32892_d9257.png", + "ucsf_document_id": "kqch0227", + "ucsf_document_page_no": "3", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7008", + "questionId": "7008", + "docId": "2392", + "image_path": "data/docvqa_images/q7008_d2392.png", + "ucsf_document_id": "gggw0004", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56464", + "questionId": "56464", + "docId": "14794", + "image_path": "data/docvqa_images/q56464_d14794.png", + "ucsf_document_id": "gnnp0227", + "ucsf_document_page_no": "4", + "topic": "Yes/No|handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "63109", + "questionId": "63109", + "docId": "9048", + "image_path": "data/docvqa_images/q63109_d9048.png", + "ucsf_document_id": "xlwc0228", + "ucsf_document_page_no": "3", + "topic": "handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50307", + "questionId": "50307", + "docId": "14571", + "image_path": "data/docvqa_images/q50307_d14571.png", + "ucsf_document_id": "rrdd0228", + "ucsf_document_page_no": "14", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64599", + "questionId": "64599", + "docId": "10376", + "image_path": "data/docvqa_images/q64599_d10376.png", + "ucsf_document_id": "hslf0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60863", + "questionId": "60863", + "docId": "7328", + "image_path": "data/docvqa_images/q60863_d7328.png", + "ucsf_document_id": "jzhd0227", + "ucsf_document_page_no": "16", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "12577", + "questionId": "12577", + "docId": "4035", + "image_path": "data/docvqa_images/q12577_d4035.png", + "ucsf_document_id": "ykmg0065", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58750", + "questionId": "58750", + "docId": "6153", + "image_path": "data/docvqa_images/q58750_d6153.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "33", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5663", + "questionId": "5663", + "docId": "1902", + "image_path": "data/docvqa_images/q5663_d1902.png", + "ucsf_document_id": "qzlj0226", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51085", + "questionId": "51085", + "docId": "673", + "image_path": "data/docvqa_images/q51085_d673.png", + "ucsf_document_id": "prbn0226", + "ucsf_document_page_no": "16", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60811", + "questionId": "60811", + "docId": "7299", + "image_path": "data/docvqa_images/q60811_d7299.png", + "ucsf_document_id": "phvd0227", + "ucsf_document_page_no": "10", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64494", + "questionId": "64494", + "docId": "10311", + "image_path": "data/docvqa_images/q64494_d10311.png", + "ucsf_document_id": "lpdl0226", + "ucsf_document_page_no": "35", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "297", + "questionId": "297", + "docId": "258", + "image_path": "data/docvqa_images/q297_d258.png", + "ucsf_document_id": "rzbj0037", + "ucsf_document_page_no": "7", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57145", + "questionId": "57145", + "docId": "4692", + "image_path": "data/docvqa_images/q57145_d4692.png", + "ucsf_document_id": "mtgj0223", + "ucsf_document_page_no": "19", + "topic": "table/list|others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "377", + "questionId": "377", + "docId": "272", + "image_path": "data/docvqa_images/q377_d272.png", + "ucsf_document_id": "hjxj0037", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53696", + "questionId": "53696", + "docId": "3630", + "image_path": "data/docvqa_images/q53696_d3630.png", + "ucsf_document_id": "rhhx0023", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18842", + "questionId": "18842", + "docId": "5755", + "image_path": "data/docvqa_images/q18842_d5755.png", + "ucsf_document_id": "npbb0079", + "ucsf_document_page_no": "11", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5181", + "questionId": "5181", + "docId": "1763", + "image_path": "data/docvqa_images/q5181_d1763.png", + "ucsf_document_id": "grlh0227", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "52153", + "questionId": "52153", + "docId": "1341", + "image_path": "data/docvqa_images/q52153_d1341.png", + "ucsf_document_id": "jxmk0226", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57526", + "questionId": "57526", + "docId": "4847", + "image_path": "data/docvqa_images/q57526_d4847.png", + "ucsf_document_id": "snbx0223", + "ucsf_document_page_no": "15", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "45117", + "questionId": "45117", + "docId": "13037", + "image_path": "data/docvqa_images/q45117_d13037.png", + "ucsf_document_id": "yyml0226", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59304", + "questionId": "59304", + "docId": "6128", + "image_path": "data/docvqa_images/q59304_d6128.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "53", + "topic": "layout|Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5388", + "questionId": "5388", + "docId": "1817", + "image_path": "data/docvqa_images/q5388_d1817.png", + "ucsf_document_id": "xhfl0228", + "ucsf_document_page_no": "7", + "topic": "figure/diagram|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64583", + "questionId": "64583", + "docId": "10364", + "image_path": "data/docvqa_images/q64583_d10364.png", + "ucsf_document_id": "lpdl0226", + "ucsf_document_page_no": "13", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57900", + "questionId": "57900", + "docId": "4898", + "image_path": "data/docvqa_images/q57900_d4898.png", + "ucsf_document_id": "txvw0217", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "596", + "questionId": "596", + "docId": "357", + "image_path": "data/docvqa_images/q596_d357.png", + "ucsf_document_id": "mtyj0226", + "ucsf_document_page_no": "15", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64324", + "questionId": "64324", + "docId": "10189", + "image_path": "data/docvqa_images/q64324_d10189.png", + "ucsf_document_id": "gxyd0217", + "ucsf_document_page_no": "8", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "32881", + "questionId": "32881", + "docId": "9253", + "image_path": "data/docvqa_images/q32881_d9253.png", + "ucsf_document_id": "hnhd0227", + "ucsf_document_page_no": "8", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "9381", + "questionId": "9381", + "docId": "3115", + "image_path": "data/docvqa_images/q9381_d3115.png", + "ucsf_document_id": "plxw0023", + "ucsf_document_page_no": "1", + "topic": "handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59539", + "questionId": "59539", + "docId": "6256", + "image_path": "data/docvqa_images/q59539_d6256.png", + "ucsf_document_id": "xhcc0228", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49279", + "questionId": "49279", + "docId": "14184", + "image_path": "data/docvqa_images/q49279_d14184.png", + "ucsf_document_id": "flpp0227", + "ucsf_document_page_no": "16", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53468", + "questionId": "53468", + "docId": "2749", + "image_path": "data/docvqa_images/q53468_d2749.png", + "ucsf_document_id": "fpjn0020", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57141", + "questionId": "57141", + "docId": "4692", + "image_path": "data/docvqa_images/q57141_d4692.png", + "ucsf_document_id": "mtgj0223", + "ucsf_document_page_no": "19", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51134", + "questionId": "51134", + "docId": "700", + "image_path": "data/docvqa_images/q51134_d700.png", + "ucsf_document_id": "kzbn0226", + "ucsf_document_page_no": "18", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3042", + "questionId": "3042", + "docId": "1204", + "image_path": "data/docvqa_images/q3042_d1204.png", + "ucsf_document_id": "xfjv0228", + "ucsf_document_page_no": "3", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62404", + "questionId": "62404", + "docId": "8554", + "image_path": "data/docvqa_images/q62404_d8554.png", + "ucsf_document_id": "pgjw0227", + "ucsf_document_page_no": "5", + "topic": "others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "8122", + "questionId": "8122", + "docId": "2834", + "image_path": "data/docvqa_images/q8122_d2834.png", + "ucsf_document_id": "zxjw0023", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47974", + "questionId": "47974", + "docId": "14084", + "image_path": "data/docvqa_images/q47974_d14084.png", + "ucsf_document_id": "fphv0228", + "ucsf_document_page_no": "8", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1183", + "questionId": "1183", + "docId": "536", + "image_path": "data/docvqa_images/q1183_d536.png", + "ucsf_document_id": "gmjf0226", + "ucsf_document_page_no": "4", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6003", + "questionId": "6003", + "docId": "2143", + "image_path": "data/docvqa_images/q6003_d2143.png", + "ucsf_document_id": "fllg0224", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "42304", + "questionId": "42304", + "docId": "12048", + "image_path": "data/docvqa_images/q42304_d12048.png", + "ucsf_document_id": "fkxn0226", + "ucsf_document_page_no": "14", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61503", + "questionId": "61503", + "docId": "7751", + "image_path": "data/docvqa_images/q61503_d7751.png", + "ucsf_document_id": "krcy0227", + "ucsf_document_page_no": "27", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "17150", + "questionId": "17150", + "docId": "5403", + "image_path": "data/docvqa_images/q17150_d5403.png", + "ucsf_document_id": "kfdw0217", + "ucsf_document_page_no": "1", + "topic": "others", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62995", + "questionId": "62995", + "docId": "8920", + "image_path": "data/docvqa_images/q62995_d8920.png", + "ucsf_document_id": "xkdv0228", + "ucsf_document_page_no": "13", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46299", + "questionId": "46299", + "docId": "13360", + "image_path": "data/docvqa_images/q46299_d13360.png", + "ucsf_document_id": "ysbw0217", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43600", + "questionId": "43600", + "docId": "12508", + "image_path": "data/docvqa_images/q43600_d12508.png", + "ucsf_document_id": "gmwn0226", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "62001", + "questionId": "62001", + "docId": "8197", + "image_path": "data/docvqa_images/q62001_d8197.png", + "ucsf_document_id": "fgkw0228", + "ucsf_document_page_no": "4", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "9367", + "questionId": "9367", + "docId": "3115", + "image_path": "data/docvqa_images/q9367_d3115.png", + "ucsf_document_id": "plxw0023", + "ucsf_document_page_no": "1", + "topic": "handwritten|form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50817", + "questionId": "50817", + "docId": "14743", + "image_path": "data/docvqa_images/q50817_d14743.png", + "ucsf_document_id": "mskw0228", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3847", + "questionId": "3847", + "docId": "1424", + "image_path": "data/docvqa_images/q3847_d1424.png", + "ucsf_document_id": "nmmk0226", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50362", + "questionId": "50362", + "docId": "14589", + "image_path": "data/docvqa_images/q50362_d14589.png", + "ucsf_document_id": "gscv0228", + "ucsf_document_page_no": "6", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64152", + "questionId": "64152", + "docId": "9857", + "image_path": "data/docvqa_images/q64152_d9857.png", + "ucsf_document_id": "xglg0227", + "ucsf_document_page_no": "10", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59693", + "questionId": "59693", + "docId": "6703", + "image_path": "data/docvqa_images/q59693_d6703.png", + "ucsf_document_id": "qtxb0228", + "ucsf_document_page_no": "1", + "topic": "form|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59502", + "questionId": "59502", + "docId": "6255", + "image_path": "data/docvqa_images/q59502_d6255.png", + "ucsf_document_id": "rpvm0227", + "ucsf_document_page_no": "23", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + } +] diff --git a/data/docvqa_id_split/val/items.json b/data/docvqa_id_split/val/items.json new file mode 100644 index 0000000..89b4acc --- /dev/null +++ b/data/docvqa_id_split/val/items.json @@ -0,0 +1,691 @@ +[ + { + "id": "62409", + "questionId": "62409", + "docId": "8554", + "image_path": "data/docvqa_images/q62409_d8554.png", + "ucsf_document_id": "pgjw0227", + "ucsf_document_page_no": "5", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50961", + "questionId": "50961", + "docId": "549", + "image_path": "data/docvqa_images/q50961_d549.png", + "ucsf_document_id": "qtjf0226", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46461", + "questionId": "46461", + "docId": "13361", + "image_path": "data/docvqa_images/q46461_d13361.png", + "ucsf_document_id": "ysbw0217", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3041", + "questionId": "3041", + "docId": "1204", + "image_path": "data/docvqa_images/q3041_d1204.png", + "ucsf_document_id": "xfjv0228", + "ucsf_document_page_no": "3", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "41716", + "questionId": "41716", + "docId": "11835", + "image_path": "data/docvqa_images/q41716_d11835.png", + "ucsf_document_id": "qjgn0226", + "ucsf_document_page_no": "131", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61123", + "questionId": "61123", + "docId": "7374", + "image_path": "data/docvqa_images/q61123_d7374.png", + "ucsf_document_id": "mldg0227", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "43068", + "questionId": "43068", + "docId": "12393", + "image_path": "data/docvqa_images/q43068_d12393.png", + "ucsf_document_id": "rmwn0226", + "ucsf_document_page_no": "52", + "topic": "figure/diagram", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "51221", + "questionId": "51221", + "docId": "764", + "image_path": "data/docvqa_images/q51221_d764.png", + "ucsf_document_id": "kzbn0226", + "ucsf_document_page_no": "14", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "6397", + "questionId": "6397", + "docId": "2242", + "image_path": "data/docvqa_images/q6397_d2242.png", + "ucsf_document_id": "jkcn0000", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57428", + "questionId": "57428", + "docId": "4779", + "image_path": "data/docvqa_images/q57428_d4779.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "208", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "3135", + "questionId": "3135", + "docId": "1221", + "image_path": "data/docvqa_images/q3135_d1221.png", + "ucsf_document_id": "ngph0227", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "18819", + "questionId": "18819", + "docId": "5749", + "image_path": "data/docvqa_images/q18819_d5749.png", + "ucsf_document_id": "jhfd0079", + "ucsf_document_page_no": "9", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "15382", + "questionId": "15382", + "docId": "4890", + "image_path": "data/docvqa_images/q15382_d4890.png", + "ucsf_document_id": "kjvw0217", + "ucsf_document_page_no": "3", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5772", + "questionId": "5772", + "docId": "1940", + "image_path": "data/docvqa_images/q5772_d1940.png", + "ucsf_document_id": "pzyw0224", + "ucsf_document_page_no": "10", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49077", + "questionId": "49077", + "docId": "14179", + "image_path": "data/docvqa_images/q49077_d14179.png", + "ucsf_document_id": "nrxb0228", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58519", + "questionId": "58519", + "docId": "5347", + "image_path": "data/docvqa_images/q58519_d5347.png", + "ucsf_document_id": "sjbw0217", + "ucsf_document_page_no": "11", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50720", + "questionId": "50720", + "docId": "281", + "image_path": "data/docvqa_images/q50720_d281.png", + "ucsf_document_id": "nrcj0037", + "ucsf_document_page_no": "7", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "56785", + "questionId": "56785", + "docId": "14289", + "image_path": "data/docvqa_images/q56785_d14289.png", + "ucsf_document_id": "xkbv0228", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59653", + "questionId": "59653", + "docId": "6579", + "image_path": "data/docvqa_images/q59653_d6579.png", + "ucsf_document_id": "mzbx0227", + "ucsf_document_page_no": "2", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61791", + "questionId": "61791", + "docId": "8072", + "image_path": "data/docvqa_images/q61791_d8072.png", + "ucsf_document_id": "hfmf0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "37229", + "questionId": "37229", + "docId": "10742", + "image_path": "data/docvqa_images/q37229_d10742.png", + "ucsf_document_id": "nkcd0227", + "ucsf_document_page_no": "2", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60407", + "questionId": "60407", + "docId": "7135", + "image_path": "data/docvqa_images/q60407_d7135.png", + "ucsf_document_id": "gkpk0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64420", + "questionId": "64420", + "docId": "10230", + "image_path": "data/docvqa_images/q64420_d10230.png", + "ucsf_document_id": "jnjm0223", + "ucsf_document_page_no": "107", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47365", + "questionId": "47365", + "docId": "13813", + "image_path": "data/docvqa_images/q47365_d13813.png", + "ucsf_document_id": "nxym0227", + "ucsf_document_page_no": "28", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "47458", + "questionId": "47458", + "docId": "13639", + "image_path": "data/docvqa_images/q47458_d13639.png", + "ucsf_document_id": "skdv0228", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "7621", + "questionId": "7621", + "docId": "2668", + "image_path": "data/docvqa_images/q7621_d2668.png", + "ucsf_document_id": "flxn0020", + "ucsf_document_page_no": "1", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53575", + "questionId": "53575", + "docId": "2766", + "image_path": "data/docvqa_images/q53575_d2766.png", + "ucsf_document_id": "hsfn0020", + "ucsf_document_page_no": "2", + "topic": "free_text|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60913", + "questionId": "60913", + "docId": "7349", + "image_path": "data/docvqa_images/q60913_d7349.png", + "ucsf_document_id": "jzhd0227", + "ucsf_document_page_no": "61", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "60454", + "questionId": "60454", + "docId": "7163", + "image_path": "data/docvqa_images/q60454_d7163.png", + "ucsf_document_id": "jgyk0226", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57978", + "questionId": "57978", + "docId": "4920", + "image_path": "data/docvqa_images/q57978_d4920.png", + "ucsf_document_id": "lkvw0217", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64547", + "questionId": "64547", + "docId": "10361", + "image_path": "data/docvqa_images/q64547_d10361.png", + "ucsf_document_id": "lpdl0226", + "ucsf_document_page_no": "32", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59481", + "questionId": "59481", + "docId": "6243", + "image_path": "data/docvqa_images/q59481_d6243.png", + "ucsf_document_id": "psgv0228", + "ucsf_document_page_no": "5", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "61472", + "questionId": "61472", + "docId": "7757", + "image_path": "data/docvqa_images/q61472_d7757.png", + "ucsf_document_id": "ymkp0227", + "ucsf_document_page_no": "13", + "topic": "handwritten|table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5673", + "questionId": "5673", + "docId": "1908", + "image_path": "data/docvqa_images/q5673_d1908.png", + "ucsf_document_id": "lldj0224", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "49109", + "questionId": "49109", + "docId": "13644", + "image_path": "data/docvqa_images/q49109_d13644.png", + "ucsf_document_id": "mzdv0228", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "46123", + "questionId": "46123", + "docId": "13503", + "image_path": "data/docvqa_images/q46123_d13503.png", + "ucsf_document_id": "xmww0217", + "ucsf_document_page_no": "17", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "48158", + "questionId": "48158", + "docId": "13976", + "image_path": "data/docvqa_images/q48158_d13976.png", + "ucsf_document_id": "zqhm0227", + "ucsf_document_page_no": "1", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "1955", + "questionId": "1955", + "docId": "892", + "image_path": "data/docvqa_images/q1955_d892.png", + "ucsf_document_id": "jsbn0226", + "ucsf_document_page_no": "2", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "8127", + "questionId": "8127", + "docId": "2754", + "image_path": "data/docvqa_images/q8127_d2754.png", + "ucsf_document_id": "xtvn0020", + "ucsf_document_page_no": "2", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57431", + "questionId": "57431", + "docId": "4779", + "image_path": "data/docvqa_images/q57431_d4779.png", + "ucsf_document_id": "rnbx0223", + "ucsf_document_page_no": "208", + "topic": "Image/Photo", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64306", + "questionId": "64306", + "docId": "10149", + "image_path": "data/docvqa_images/q64306_d10149.png", + "ucsf_document_id": "lpjm0223", + "ucsf_document_page_no": "23", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "64887", + "questionId": "64887", + "docId": "9754", + "image_path": "data/docvqa_images/q64887_d9754.png", + "ucsf_document_id": "szpg0227", + "ucsf_document_page_no": "9", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58680", + "questionId": "58680", + "docId": "5545", + "image_path": "data/docvqa_images/q58680_d5545.png", + "ucsf_document_id": "hhwh0078", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "5287", + "questionId": "5287", + "docId": "1785", + "image_path": "data/docvqa_images/q5287_d1785.png", + "ucsf_document_id": "mtnh0227", + "ucsf_document_page_no": "10", + "topic": "form", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "55471", + "questionId": "55471", + "docId": "4340", + "image_path": "data/docvqa_images/q55471_d4340.png", + "ucsf_document_id": "fsgj0223", + "ucsf_document_page_no": "96", + "topic": "free_text", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53095", + "questionId": "53095", + "docId": "296", + "image_path": "data/docvqa_images/q53095_d296.png", + "ucsf_document_id": "qhxj0037", + "ucsf_document_page_no": "3", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "53726", + "questionId": "53726", + "docId": "2008", + "image_path": "data/docvqa_images/q53726_d2008.png", + "ucsf_document_id": "hhnf0094", + "ucsf_document_page_no": "5", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "57321", + "questionId": "57321", + "docId": "4722", + "image_path": "data/docvqa_images/q57321_d4722.png", + "ucsf_document_id": "xybx0223", + "ucsf_document_page_no": "32", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "26659", + "questionId": "26659", + "docId": "7470", + "image_path": "data/docvqa_images/q26659_d7470.png", + "ucsf_document_id": "lhmg0227", + "ucsf_document_page_no": "1", + "topic": "layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "38920", + "questionId": "38920", + "docId": "11157", + "image_path": "data/docvqa_images/q38920_d11157.png", + "ucsf_document_id": "klnf0227", + "ucsf_document_page_no": "1", + "topic": "table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "50837", + "questionId": "50837", + "docId": "14742", + "image_path": "data/docvqa_images/q50837_d14742.png", + "ucsf_document_id": "ysmc0228", + "ucsf_document_page_no": "4", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "59615", + "questionId": "59615", + "docId": "6569", + "image_path": "data/docvqa_images/q59615_d6569.png", + "ucsf_document_id": "hnnp0227", + "ucsf_document_page_no": "45", + "topic": "handwritten|table/list|layout", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + }, + { + "id": "58687", + "questionId": "58687", + "docId": "5545", + "image_path": "data/docvqa_images/q58687_d5545.png", + "ucsf_document_id": "hhwh0078", + "ucsf_document_page_no": "1", + "topic": "table/list", + "source_dataset": "lmms-lab/DocVQA", + "source_config": "DocVQA", + "source_split": "validation", + "sample_seed": "full_validation_5349" + } +] diff --git a/data/livemathematicianbench_id_split/split_manifest.json b/data/livemathematicianbench_id_split/split_manifest.json new file mode 100644 index 0000000..9af68a0 --- /dev/null +++ b/data/livemathematicianbench_id_split/split_manifest.json @@ -0,0 +1,34 @@ +{ + "benchmark": "LiveMathematicianBench", + "manifest_type": "id_split", + "source_repo": "LiveMathematicianBench/LiveMathematicianBench", + "source_repo_type": "dataset", + "source_url": "https://huggingface.co/datasets/LiveMathematicianBench/LiveMathematicianBench", + "source_revision": "b72450f6ce96c26158d64d945a5d31ef7727be41", + "source_files": [ + "data/202511/qa_202511_final.json", + "data/202512/qa_202512_final.json", + "data/202601/qa_202601_final.json", + "data/202602/qa_202602_final.json" + ], + "split_mode": "ratio", + "split_ratio": "2:1:7", + "split_seed": 42, + "counts": { + "train": 35, + "val": 18, + "test": 124 + }, + "item_fields": [ + "id", + "month", + "no", + "paper_link", + "source_file" + ], + "id_format": ":", + "notes": [ + "This is an ID split manifest, not the full LiveMathematicianBench payload.", + "Materialize full split items from the official LiveMathematicianBench raw qa_*_final.json files before evaluation." + ] +} diff --git a/data/livemathematicianbench_id_split/test/items.json b/data/livemathematicianbench_id_split/test/items.json new file mode 100644 index 0000000..83006f3 --- /dev/null +++ b/data/livemathematicianbench_id_split/test/items.json @@ -0,0 +1,870 @@ +[ + { + "id": "202602:12", + "month": "202602", + "no": 12, + "paper_link": "http://arxiv.org/abs/2602.07171v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:3", + "month": "202601", + "no": 3, + "paper_link": "http://arxiv.org/abs/2601.01447v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:4", + "month": "202511", + "no": 4, + "paper_link": "http://arxiv.org/abs/2511.23123v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:20", + "month": "202601", + "no": 20, + "paper_link": "http://arxiv.org/abs/2601.13212v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:42", + "month": "202601", + "no": 42, + "paper_link": "http://arxiv.org/abs/2601.09348v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:38", + "month": "202512", + "no": 38, + "paper_link": "http://arxiv.org/abs/2512.19831v2", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:4", + "month": "202512", + "no": 4, + "paper_link": "http://arxiv.org/abs/2512.03141v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:4", + "month": "202602", + "no": 4, + "paper_link": "http://arxiv.org/abs/2602.14368v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202511:15", + "month": "202511", + "no": 15, + "paper_link": "http://arxiv.org/abs/2511.17325v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:32", + "month": "202602", + "no": 32, + "paper_link": "http://arxiv.org/abs/2602.14817v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:51", + "month": "202512", + "no": 51, + "paper_link": "http://arxiv.org/abs/2512.14581v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:26", + "month": "202512", + "no": 26, + "paper_link": "http://arxiv.org/abs/2512.19586v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:13", + "month": "202601", + "no": 13, + "paper_link": "http://arxiv.org/abs/2601.10017v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:1", + "month": "202602", + "no": 1, + "paper_link": "http://arxiv.org/abs/2602.23137v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202511:18", + "month": "202511", + "no": 18, + "paper_link": "http://arxiv.org/abs/2511.10795v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:5", + "month": "202512", + "no": 5, + "paper_link": "http://arxiv.org/abs/2512.00348v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:19", + "month": "202511", + "no": 19, + "paper_link": "http://arxiv.org/abs/2511.06951v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:40", + "month": "202602", + "no": 40, + "paper_link": "http://arxiv.org/abs/2602.20462v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:29", + "month": "202602", + "no": 29, + "paper_link": "http://arxiv.org/abs/2602.10676v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:35", + "month": "202512", + "no": 35, + "paper_link": "http://arxiv.org/abs/2512.08840v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:48", + "month": "202512", + "no": 48, + "paper_link": "http://arxiv.org/abs/2512.03482v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:52", + "month": "202512", + "no": 52, + "paper_link": "http://arxiv.org/abs/2512.11246v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:44", + "month": "202512", + "no": 44, + "paper_link": "http://arxiv.org/abs/2512.10385v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:28", + "month": "202511", + "no": 28, + "paper_link": "http://arxiv.org/abs/2511.03812v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:43", + "month": "202601", + "no": 43, + "paper_link": "http://arxiv.org/abs/2601.22555v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:9", + "month": "202602", + "no": 9, + "paper_link": "http://arxiv.org/abs/2602.19882v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:23", + "month": "202512", + "no": 23, + "paper_link": "http://arxiv.org/abs/2512.09180v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:21", + "month": "202602", + "no": 21, + "paper_link": "http://arxiv.org/abs/2602.10509v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202511:5", + "month": "202511", + "no": 5, + "paper_link": "http://arxiv.org/abs/2511.20164v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:35", + "month": "202601", + "no": 35, + "paper_link": "http://arxiv.org/abs/2601.15606v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:50", + "month": "202602", + "no": 50, + "paper_link": "http://arxiv.org/abs/2602.05652v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:13", + "month": "202512", + "no": 13, + "paper_link": "http://arxiv.org/abs/2512.22861v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:49", + "month": "202602", + "no": 49, + "paper_link": "http://arxiv.org/abs/2602.07167v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:18", + "month": "202602", + "no": 18, + "paper_link": "http://arxiv.org/abs/2602.20124v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:15", + "month": "202601", + "no": 15, + "paper_link": "http://arxiv.org/abs/2601.05327v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:21", + "month": "202601", + "no": 21, + "paper_link": "http://arxiv.org/abs/2601.04994v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:32", + "month": "202601", + "no": 32, + "paper_link": "http://arxiv.org/abs/2601.09183v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:34", + "month": "202602", + "no": 34, + "paper_link": "http://arxiv.org/abs/2602.21118v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:20", + "month": "202602", + "no": 20, + "paper_link": "http://arxiv.org/abs/2602.16506v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:5", + "month": "202602", + "no": 5, + "paper_link": "http://arxiv.org/abs/2602.09806v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:40", + "month": "202512", + "no": 40, + "paper_link": "http://arxiv.org/abs/2512.16535v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:22", + "month": "202511", + "no": 22, + "paper_link": "http://arxiv.org/abs/2511.07607v2", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:36", + "month": "202601", + "no": 36, + "paper_link": "http://arxiv.org/abs/2601.12457v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:49", + "month": "202512", + "no": 49, + "paper_link": "http://arxiv.org/abs/2512.21565v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:10", + "month": "202511", + "no": 10, + "paper_link": "http://arxiv.org/abs/2511.06484v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:2", + "month": "202601", + "no": 2, + "paper_link": "http://arxiv.org/abs/2601.07068v4", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:19", + "month": "202602", + "no": 19, + "paper_link": "http://arxiv.org/abs/2602.18179v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:9", + "month": "202601", + "no": 9, + "paper_link": "http://arxiv.org/abs/2601.17765v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:6", + "month": "202512", + "no": 6, + "paper_link": "http://arxiv.org/abs/2512.23079v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:5", + "month": "202601", + "no": 5, + "paper_link": "http://arxiv.org/abs/2601.20344v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:14", + "month": "202602", + "no": 14, + "paper_link": "http://arxiv.org/abs/2602.09177v2", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:17", + "month": "202512", + "no": 17, + "paper_link": "http://arxiv.org/abs/2512.11657v2", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:19", + "month": "202512", + "no": 19, + "paper_link": "http://arxiv.org/abs/2512.16655v2", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:33", + "month": "202602", + "no": 33, + "paper_link": "http://arxiv.org/abs/2602.13734v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:18", + "month": "202512", + "no": 18, + "paper_link": "http://arxiv.org/abs/2512.22960v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:26", + "month": "202601", + "no": 26, + "paper_link": "http://arxiv.org/abs/2601.06814v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:1", + "month": "202601", + "no": 1, + "paper_link": "http://arxiv.org/abs/2601.18276v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:30", + "month": "202512", + "no": 30, + "paper_link": "http://arxiv.org/abs/2512.07260v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:44", + "month": "202602", + "no": 44, + "paper_link": "http://arxiv.org/abs/2602.01138v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:20", + "month": "202512", + "no": 20, + "paper_link": "http://arxiv.org/abs/2512.14575v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:13", + "month": "202511", + "no": 13, + "paper_link": "http://arxiv.org/abs/2511.16910v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:30", + "month": "202601", + "no": 30, + "paper_link": "http://arxiv.org/abs/2601.12140v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:40", + "month": "202601", + "no": 40, + "paper_link": "http://arxiv.org/abs/2601.05146v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:29", + "month": "202601", + "no": 29, + "paper_link": "http://arxiv.org/abs/2601.12846v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:11", + "month": "202511", + "no": 11, + "paper_link": "http://arxiv.org/abs/2511.17548v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:9", + "month": "202512", + "no": 9, + "paper_link": "http://arxiv.org/abs/2512.08817v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:18", + "month": "202601", + "no": 18, + "paper_link": "http://arxiv.org/abs/2601.01797v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:1", + "month": "202512", + "no": 1, + "paper_link": "http://arxiv.org/abs/2512.20055v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:4", + "month": "202601", + "no": 4, + "paper_link": "http://arxiv.org/abs/2601.21223v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:6", + "month": "202511", + "no": 6, + "paper_link": "http://arxiv.org/abs/2511.14959v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:38", + "month": "202602", + "no": 38, + "paper_link": "http://arxiv.org/abs/2602.08398v2", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:10", + "month": "202601", + "no": 10, + "paper_link": "http://arxiv.org/abs/2601.15524v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:11", + "month": "202602", + "no": 11, + "paper_link": "http://arxiv.org/abs/2602.11045v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:45", + "month": "202512", + "no": 45, + "paper_link": "http://arxiv.org/abs/2512.08395v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:12", + "month": "202601", + "no": 12, + "paper_link": "http://arxiv.org/abs/2601.11877v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:47", + "month": "202512", + "no": 47, + "paper_link": "http://arxiv.org/abs/2512.09683v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:21", + "month": "202511", + "no": 21, + "paper_link": "http://arxiv.org/abs/2511.21288v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:16", + "month": "202601", + "no": 16, + "paper_link": "http://arxiv.org/abs/2601.05008v2", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:3", + "month": "202512", + "no": 3, + "paper_link": "http://arxiv.org/abs/2512.13450v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:37", + "month": "202601", + "no": 37, + "paper_link": "http://arxiv.org/abs/2601.09443v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:12", + "month": "202511", + "no": 12, + "paper_link": "http://arxiv.org/abs/2511.04978v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:39", + "month": "202512", + "no": 39, + "paper_link": "http://arxiv.org/abs/2512.19003v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:8", + "month": "202601", + "no": 8, + "paper_link": "http://arxiv.org/abs/2601.19754v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:11", + "month": "202601", + "no": 11, + "paper_link": "http://arxiv.org/abs/2601.13552v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:25", + "month": "202511", + "no": 25, + "paper_link": "http://arxiv.org/abs/2511.10548v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:17", + "month": "202601", + "no": 17, + "paper_link": "http://arxiv.org/abs/2601.02655v2", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:36", + "month": "202602", + "no": 36, + "paper_link": "http://arxiv.org/abs/2602.13001v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:43", + "month": "202602", + "no": 43, + "paper_link": "http://arxiv.org/abs/2602.06897v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:6", + "month": "202601", + "no": 6, + "paper_link": "http://arxiv.org/abs/2601.04747v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:35", + "month": "202602", + "no": 35, + "paper_link": "http://arxiv.org/abs/2602.20938v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:11", + "month": "202512", + "no": 11, + "paper_link": "http://arxiv.org/abs/2512.03294v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:23", + "month": "202602", + "no": 23, + "paper_link": "http://arxiv.org/abs/2602.09201v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:7", + "month": "202601", + "no": 7, + "paper_link": "http://arxiv.org/abs/2601.02859v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:39", + "month": "202602", + "no": 39, + "paper_link": "http://arxiv.org/abs/2602.21659v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:12", + "month": "202512", + "no": 12, + "paper_link": "http://arxiv.org/abs/2512.00690v3", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:2", + "month": "202511", + "no": 2, + "paper_link": "http://arxiv.org/abs/2511.19681v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:43", + "month": "202512", + "no": 43, + "paper_link": "http://arxiv.org/abs/2512.10820v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:24", + "month": "202602", + "no": 24, + "paper_link": "http://arxiv.org/abs/2602.08680v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:34", + "month": "202601", + "no": 34, + "paper_link": "http://arxiv.org/abs/2601.07318v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:28", + "month": "202512", + "no": 28, + "paper_link": "http://arxiv.org/abs/2512.11294v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:27", + "month": "202601", + "no": 27, + "paper_link": "http://arxiv.org/abs/2601.05692v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:42", + "month": "202602", + "no": 42, + "paper_link": "http://arxiv.org/abs/2602.09749v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:22", + "month": "202512", + "no": 22, + "paper_link": "http://arxiv.org/abs/2512.11658v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:17", + "month": "202602", + "no": 17, + "paper_link": "http://arxiv.org/abs/2602.22504v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:48", + "month": "202602", + "no": 48, + "paper_link": "http://arxiv.org/abs/2602.08760v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:28", + "month": "202602", + "no": 28, + "paper_link": "http://arxiv.org/abs/2602.11595v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:3", + "month": "202602", + "no": 3, + "paper_link": "http://arxiv.org/abs/2602.17369v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:31", + "month": "202512", + "no": 31, + "paper_link": "http://arxiv.org/abs/2512.23668v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:27", + "month": "202512", + "no": 27, + "paper_link": "http://arxiv.org/abs/2512.16505v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:24", + "month": "202511", + "no": 24, + "paper_link": "http://arxiv.org/abs/2511.12549v2", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202511:8", + "month": "202511", + "no": 8, + "paper_link": "http://arxiv.org/abs/2511.12657v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202511:9", + "month": "202511", + "no": 9, + "paper_link": "http://arxiv.org/abs/2511.09015v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:28", + "month": "202601", + "no": 28, + "paper_link": "http://arxiv.org/abs/2601.14825v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:25", + "month": "202602", + "no": 25, + "paper_link": "http://arxiv.org/abs/2602.16048v3", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202511:23", + "month": "202511", + "no": 23, + "paper_link": "http://arxiv.org/abs/2511.06595v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:13", + "month": "202602", + "no": 13, + "paper_link": "http://arxiv.org/abs/2602.12261v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202511:27", + "month": "202511", + "no": 27, + "paper_link": "http://arxiv.org/abs/2511.04407v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:7", + "month": "202512", + "no": 7, + "paper_link": "http://arxiv.org/abs/2512.09490v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:29", + "month": "202512", + "no": 29, + "paper_link": "http://arxiv.org/abs/2512.08562v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:34", + "month": "202512", + "no": 34, + "paper_link": "http://arxiv.org/abs/2512.09598v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:42", + "month": "202512", + "no": 42, + "paper_link": "http://arxiv.org/abs/2512.10845v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:7", + "month": "202511", + "no": 7, + "paper_link": "http://arxiv.org/abs/2511.13976v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202511:29", + "month": "202511", + "no": 29, + "paper_link": "http://arxiv.org/abs/2511.03722v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:37", + "month": "202602", + "no": 37, + "paper_link": "http://arxiv.org/abs/2602.08644v1", + "source_file": "data/202602/qa_202602_final.json" + } +] diff --git a/data/livemathematicianbench_id_split/train/items.json b/data/livemathematicianbench_id_split/train/items.json new file mode 100644 index 0000000..d0f65ba --- /dev/null +++ b/data/livemathematicianbench_id_split/train/items.json @@ -0,0 +1,247 @@ +[ + { + "id": "202602:22", + "month": "202602", + "no": 22, + "paper_link": "http://arxiv.org/abs/2602.10700v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:8", + "month": "202512", + "no": 8, + "paper_link": "http://arxiv.org/abs/2512.08863v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:16", + "month": "202511", + "no": 16, + "paper_link": "http://arxiv.org/abs/2511.15668v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:44", + "month": "202601", + "no": 44, + "paper_link": "http://arxiv.org/abs/2601.21267v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:14", + "month": "202511", + "no": 14, + "paper_link": "http://arxiv.org/abs/2511.13447v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202602:30", + "month": "202602", + "no": 30, + "paper_link": "http://arxiv.org/abs/2602.16692v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:2", + "month": "202602", + "no": 2, + "paper_link": "http://arxiv.org/abs/2602.22933v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202601:41", + "month": "202601", + "no": 41, + "paper_link": "http://arxiv.org/abs/2601.01164v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:23", + "month": "202601", + "no": 23, + "paper_link": "http://arxiv.org/abs/2601.02528v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:20", + "month": "202511", + "no": 20, + "paper_link": "http://arxiv.org/abs/2511.02963v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:22", + "month": "202601", + "no": 22, + "paper_link": "http://arxiv.org/abs/2601.03984v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:14", + "month": "202512", + "no": 14, + "paper_link": "http://arxiv.org/abs/2512.22459v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:26", + "month": "202511", + "no": 26, + "paper_link": "http://arxiv.org/abs/2511.07817v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202511:3", + "month": "202511", + "no": 3, + "paper_link": "http://arxiv.org/abs/2511.11409v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:33", + "month": "202601", + "no": 33, + "paper_link": "http://arxiv.org/abs/2601.07747v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202602:7", + "month": "202602", + "no": 7, + "paper_link": "http://arxiv.org/abs/2602.22912v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:27", + "month": "202602", + "no": 27, + "paper_link": "http://arxiv.org/abs/2602.13968v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:31", + "month": "202602", + "no": 31, + "paper_link": "http://arxiv.org/abs/2602.15528v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:41", + "month": "202602", + "no": 41, + "paper_link": "http://arxiv.org/abs/2602.10707v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:25", + "month": "202512", + "no": 25, + "paper_link": "http://arxiv.org/abs/2512.04531v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:10", + "month": "202602", + "no": 10, + "paper_link": "http://arxiv.org/abs/2602.17863v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:16", + "month": "202602", + "no": 16, + "paper_link": "http://arxiv.org/abs/2602.02723v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:16", + "month": "202512", + "no": 16, + "paper_link": "http://arxiv.org/abs/2512.11601v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:2", + "month": "202512", + "no": 2, + "paper_link": "http://arxiv.org/abs/2512.16120v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:24", + "month": "202512", + "no": 24, + "paper_link": "http://arxiv.org/abs/2512.08391v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:32", + "month": "202512", + "no": 32, + "paper_link": "http://arxiv.org/abs/2512.23224v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:47", + "month": "202602", + "no": 47, + "paper_link": "http://arxiv.org/abs/2602.10391v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:46", + "month": "202602", + "no": 46, + "paper_link": "http://arxiv.org/abs/2602.13727v2", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:21", + "month": "202512", + "no": 21, + "paper_link": "http://arxiv.org/abs/2512.12835v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:33", + "month": "202512", + "no": 33, + "paper_link": "http://arxiv.org/abs/2512.19500v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:45", + "month": "202602", + "no": 45, + "paper_link": "http://arxiv.org/abs/2602.23912v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:26", + "month": "202602", + "no": 26, + "paper_link": "http://arxiv.org/abs/2602.14658v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:41", + "month": "202512", + "no": 41, + "paper_link": "http://arxiv.org/abs/2512.15177v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:38", + "month": "202601", + "no": 38, + "paper_link": "http://arxiv.org/abs/2601.07817v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:14", + "month": "202601", + "no": 14, + "paper_link": "http://arxiv.org/abs/2601.08704v1", + "source_file": "data/202601/qa_202601_final.json" + } +] diff --git a/data/livemathematicianbench_id_split/val/items.json b/data/livemathematicianbench_id_split/val/items.json new file mode 100644 index 0000000..4298592 --- /dev/null +++ b/data/livemathematicianbench_id_split/val/items.json @@ -0,0 +1,128 @@ +[ + { + "id": "202602:8", + "month": "202602", + "no": 8, + "paper_link": "http://arxiv.org/abs/2602.19529v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:50", + "month": "202512", + "no": 50, + "paper_link": "http://arxiv.org/abs/2512.15277v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202512:36", + "month": "202512", + "no": 36, + "paper_link": "http://arxiv.org/abs/2512.06696v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202511:1", + "month": "202511", + "no": 1, + "paper_link": "http://arxiv.org/abs/2511.04651v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202601:31", + "month": "202601", + "no": 31, + "paper_link": "http://arxiv.org/abs/2601.10298v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202511:17", + "month": "202511", + "no": 17, + "paper_link": "http://arxiv.org/abs/2511.13215v1", + "source_file": "data/202511/qa_202511_final.json" + }, + { + "id": "202512:37", + "month": "202512", + "no": 37, + "paper_link": "http://arxiv.org/abs/2512.20498v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:39", + "month": "202601", + "no": 39, + "paper_link": "http://arxiv.org/abs/2601.06601v2", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:25", + "month": "202601", + "no": 25, + "paper_link": "http://arxiv.org/abs/2601.10996v3", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:24", + "month": "202601", + "no": 24, + "paper_link": "http://arxiv.org/abs/2601.12250v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:45", + "month": "202601", + "no": 45, + "paper_link": "http://arxiv.org/abs/2601.12113v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202601:19", + "month": "202601", + "no": 19, + "paper_link": "http://arxiv.org/abs/2601.00779v1", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:10", + "month": "202512", + "no": 10, + "paper_link": "http://arxiv.org/abs/2512.07073v2", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202601:46", + "month": "202601", + "no": 46, + "paper_link": "http://arxiv.org/abs/2601.07793v2", + "source_file": "data/202601/qa_202601_final.json" + }, + { + "id": "202512:15", + "month": "202512", + "no": 15, + "paper_link": "http://arxiv.org/abs/2512.16165v1", + "source_file": "data/202512/qa_202512_final.json" + }, + { + "id": "202602:15", + "month": "202602", + "no": 15, + "paper_link": "http://arxiv.org/abs/2602.05303v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202602:6", + "month": "202602", + "no": 6, + "paper_link": "http://arxiv.org/abs/2602.01571v1", + "source_file": "data/202602/qa_202602_final.json" + }, + { + "id": "202512:46", + "month": "202512", + "no": 46, + "paper_link": "http://arxiv.org/abs/2512.05945v1", + "source_file": "data/202512/qa_202512_final.json" + } +] diff --git a/data/officeqa_id_split/split_manifest.json b/data/officeqa_id_split/split_manifest.json new file mode 100644 index 0000000..1054c19 --- /dev/null +++ b/data/officeqa_id_split/split_manifest.json @@ -0,0 +1,27 @@ +{ + "benchmark": "OfficeQA", + "manifest_type": "id_split", + "source_repo": "databricks/officeqa", + "source_repo_type": "dataset", + "source_url": "https://huggingface.co/datasets/databricks/officeqa", + "source_revision": "8ecbf18d3833daf4750a903d14963e4c4c1d4cd8", + "source_file": "officeqa_full.csv", + "source_split_name": "officeqa_split", + "counts": { + "train": 50, + "val": 24, + "test": 172 + }, + "item_fields": [ + "id", + "uid", + "category", + "source_files", + "source_docs", + "source_split" + ], + "notes": [ + "This is a split manifest, not the full OfficeQA payload.", + "The official OfficeQA CSV is gated on Hugging Face; materialization requires authorized access." + ] +} diff --git a/data/officeqa_id_split/test/items.json b/data/officeqa_id_split/test/items.json new file mode 100644 index 0000000..b40bb15 --- /dev/null +++ b/data/officeqa_id_split/test/items.json @@ -0,0 +1,1378 @@ +[ + { + "id": "UID0003", + "uid": "UID0003", + "category": "hard", + "source_files": "treasury_bulletin_1954_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1954-6685?page=14", + "source_split": "test" + }, + { + "id": "UID0004", + "uid": "UID0004", + "category": "hard", + "source_files": "treasury_bulletin_1941_01.txt\r\ntreasury_bulletin_1954_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1941-6529?page=15\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1954-6685?page=14", + "source_split": "test" + }, + { + "id": "UID0005", + "uid": "UID0005", + "category": "hard", + "source_files": "treasury_bulletin_1941_01.txt\r\ntreasury_bulletin_1954_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1941-6529?page=15\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1954-6685?page=14", + "source_split": "test" + }, + { + "id": "UID0006", + "uid": "UID0006", + "category": "easy", + "source_files": "treasury_bulletin_1998_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1998-7096?page=73&deep=true", + "source_split": "test" + }, + { + "id": "UID0008", + "uid": "UID0008", + "category": "easy", + "source_files": "treasury_bulletin_2012_06.txt\r\ntreasury_bulletin_2022_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2012-7151?page=18\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2022-616226?page=20", + "source_split": "test" + }, + { + "id": "UID0009", + "uid": "UID0009", + "category": "hard", + "source_files": "treasury_bulletin_2011_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2011-7148?page=50", + "source_split": "test" + }, + { + "id": "UID0010", + "uid": "UID0010", + "category": "hard", + "source_files": "treasury_bulletin_2025_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2025-687694?page=76", + "source_split": "test" + }, + { + "id": "UID0011", + "uid": "UID0011", + "category": "easy", + "source_files": "treasury_bulletin_1946_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1946-6594?page=72&deep=true", + "source_split": "test" + }, + { + "id": "UID0012", + "uid": "UID0012", + "category": "hard", + "source_files": "treasury_bulletin_1958_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1958-6741?page=16", + "source_split": "test" + }, + { + "id": "UID0013", + "uid": "UID0013", + "category": "hard", + "source_files": "treasury_bulletin_1942_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1942-6547?page=76", + "source_split": "test" + }, + { + "id": "UID0015", + "uid": "UID0015", + "category": "hard", + "source_files": "treasury_bulletin_1981_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1981-7019?page=24", + "source_split": "test" + }, + { + "id": "UID0016", + "uid": "UID0016", + "category": "easy", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=24", + "source_split": "test" + }, + { + "id": "UID0020", + "uid": "UID0020", + "category": "easy", + "source_files": "treasury_bulletin_1944_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1944-6570?page=14", + "source_split": "test" + }, + { + "id": "UID0021", + "uid": "UID0021", + "category": "easy", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=21&deep=true", + "source_split": "test" + }, + { + "id": "UID0022", + "uid": "UID0022", + "category": "hard", + "source_files": "treasury_bulletin_1999_03.txt\r\ntreasury_bulletin_1994_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1999-7097?page=18\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1994-7076?page=34", + "source_split": "test" + }, + { + "id": "UID0023", + "uid": "UID0023", + "category": "easy", + "source_files": "treasury_bulletin_1939_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1939-6510?page=15", + "source_split": "test" + }, + { + "id": "UID0024", + "uid": "UID0024", + "category": "easy", + "source_files": "treasury_bulletin_1990_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1990-7063?page=43", + "source_split": "test" + }, + { + "id": "UID0025", + "uid": "UID0025", + "category": "hard", + "source_files": "treasury_bulletin_1942_10.txt\r\ntreasury_bulletin_1947_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1942-6550?page=18&deep=true\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1947-6607?page=24&deep=true", + "source_split": "test" + }, + { + "id": "UID0029", + "uid": "UID0029", + "category": "hard", + "source_files": "treasury_bulletin_1970_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1970-6882?page=89&deep=true", + "source_split": "test" + }, + { + "id": "UID0032", + "uid": "UID0032", + "category": "hard", + "source_files": "treasury_bulletin_1941_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1941-6531?page=48", + "source_split": "test" + }, + { + "id": "UID0035", + "uid": "UID0035", + "category": "hard", + "source_files": "treasury_bulletin_1980_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1980-7001?page=41", + "source_split": "test" + }, + { + "id": "UID0036", + "uid": "UID0036", + "category": "hard", + "source_files": "treasury_bulletin_2011_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2011-7148?page=53", + "source_split": "test" + }, + { + "id": "UID0037", + "uid": "UID0037", + "category": "hard", + "source_files": "treasury_bulletin_2007_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2007-7132?page=12&deep=true", + "source_split": "test" + }, + { + "id": "UID0038", + "uid": "UID0038", + "category": "easy", + "source_files": "treasury_bulletin_2004_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2004-7117?page=66", + "source_split": "test" + }, + { + "id": "UID0040", + "uid": "UID0040", + "category": "easy", + "source_files": "treasury_bulletin_1981_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1981-7012?page=130", + "source_split": "test" + }, + { + "id": "UID0042", + "uid": "UID0042", + "category": "hard", + "source_files": "treasury_bulletin_2020_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=29\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=30", + "source_split": "test" + }, + { + "id": "UID0043", + "uid": "UID0043", + "category": "easy", + "source_files": "treasury_bulletin_2005_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2005-7121?page=123", + "source_split": "test" + }, + { + "id": "UID0045", + "uid": "UID0045", + "category": "easy", + "source_files": "treasury_bulletin_2003_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2003-7114?page=83", + "source_split": "test" + }, + { + "id": "UID0047", + "uid": "UID0047", + "category": "easy", + "source_files": "treasury_bulletin_1982_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1982-7029?page=86", + "source_split": "test" + }, + { + "id": "UID0048", + "uid": "UID0048", + "category": "easy", + "source_files": "treasury_bulletin_1939_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1939-6505?page=111", + "source_split": "test" + }, + { + "id": "UID0050", + "uid": "UID0050", + "category": "hard", + "source_files": "treasury_bulletin_1941_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1941-6533?page=32", + "source_split": "test" + }, + { + "id": "UID0051", + "uid": "UID0051", + "category": "easy", + "source_files": "treasury_bulletin_1969_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1969-6871?page=77", + "source_split": "test" + }, + { + "id": "UID0053", + "uid": "UID0053", + "category": "hard", + "source_files": "treasury_bulletin_2000_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2000-7103?page=24", + "source_split": "test" + }, + { + "id": "UID0054", + "uid": "UID0054", + "category": "easy", + "source_files": "treasury_bulletin_2020_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2020-596188?page=74", + "source_split": "test" + }, + { + "id": "UID0055", + "uid": "UID0055", + "category": "hard", + "source_files": "treasury_bulletin_1960_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1960-6763?page=68", + "source_split": "test" + }, + { + "id": "UID0057", + "uid": "UID0057", + "category": "hard", + "source_files": "treasury_bulletin_1969_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1969-6874?page=32, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1970-6877?page=32, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1971-6889?page=24, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1972-6901?page=32, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1973-6913?page=38, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1974-6924?page=37, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1975-6937?page=28, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1976-6949?page=27, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1977-6961?page=27, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1978-6973?page=31, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1979-6985?page=29, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1980-6997?page=30, https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1981-7009?page=39", + "source_split": "test" + }, + { + "id": "UID0058", + "uid": "UID0058", + "category": "hard", + "source_files": "treasury_bulletin_2003_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2003-7115?page=106&deep=true", + "source_split": "test" + }, + { + "id": "UID0059", + "uid": "UID0059", + "category": "hard", + "source_files": "treasury_bulletin_1953_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1953-6673?page=25", + "source_split": "test" + }, + { + "id": "UID0060", + "uid": "UID0060", + "category": "easy", + "source_files": "treasury_bulletin_1953_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1953-6673?page=25", + "source_split": "test" + }, + { + "id": "UID0061", + "uid": "UID0061", + "category": "easy", + "source_files": "treasury_bulletin_1949_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1949-6624?page=37", + "source_split": "test" + }, + { + "id": "UID0062", + "uid": "UID0062", + "category": "hard", + "source_files": "treasury_bulletin_1948_04.txt\r\ntreasury_bulletin_1952_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1948-6615?page=13\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1952-6671?page=15", + "source_split": "test" + }, + { + "id": "UID0064", + "uid": "UID0064", + "category": "easy", + "source_files": "treasury_bulletin_1941_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1941-6531?page=58&deep=true\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1941-6531?page=59&deep=true", + "source_split": "test" + }, + { + "id": "UID0066", + "uid": "UID0066", + "category": "easy", + "source_files": "treasury_bulletin_2020_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=29\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=30&deep=true", + "source_split": "test" + }, + { + "id": "UID0067", + "uid": "UID0067", + "category": "easy", + "source_files": "treasury_bulletin_1940_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1940-6524?page=71", + "source_split": "test" + }, + { + "id": "UID0068", + "uid": "UID0068", + "category": "hard", + "source_files": "treasury_bulletin_2016_12.txt\r\ntreasury_bulletin_2017_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2016-535293?page=22&deep=true\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2017-552379?page=22", + "source_split": "test" + }, + { + "id": "UID0069", + "uid": "UID0069", + "category": "hard", + "source_files": "treasury_bulletin_2000_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=55\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=56\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=57", + "source_split": "test" + }, + { + "id": "UID0071", + "uid": "UID0071", + "category": "hard", + "source_files": "treasury_bulletin_2007_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2007-7133?page=53", + "source_split": "test" + }, + { + "id": "UID0074", + "uid": "UID0074", + "category": "easy", + "source_files": "treasury_bulletin_1969_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1969-6865?page=30", + "source_split": "test" + }, + { + "id": "UID0075", + "uid": "UID0075", + "category": "easy", + "source_files": "treasury_bulletin_1975_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1975-6939?page=11&deep=true", + "source_split": "test" + }, + { + "id": "UID0076", + "uid": "UID0076", + "category": "easy", + "source_files": "treasury_bulletin_1990_03.txt\r\ntreasury_bulletin_1991_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1990-7060?page=27\r\n\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1991-7064?page=29", + "source_split": "test" + }, + { + "id": "UID0077", + "uid": "UID0077", + "category": "hard", + "source_files": "treasury_bulletin_2011_03.txt\r\ntreasury_bulletin_2012_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2011-7147?page=20\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2011-7147?page=21\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2012-7150?page=21\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2012-7150?page=22", + "source_split": "test" + }, + { + "id": "UID0078", + "uid": "UID0078", + "category": "easy", + "source_files": "treasury_bulletin_2010_12.txt\r\ntreasury_bulletin_2015_12.txt\r\ntreasury_bulletin_2024_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2010-7146?page=26\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2015-519209?page=24\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2024-679984?page=28", + "source_split": "test" + }, + { + "id": "UID0080", + "uid": "UID0080", + "category": "easy", + "source_files": "treasury_bulletin_1955_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1955-6696?page=51", + "source_split": "test" + }, + { + "id": "UID0081", + "uid": "UID0081", + "category": "easy", + "source_files": "treasury_bulletin_2023_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2023-628984?page=31", + "source_split": "test" + }, + { + "id": "UID0082", + "uid": "UID0082", + "category": "easy", + "source_files": "treasury_bulletin_2011_12.txt\r\ntreasury_bulletin_2016_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2011-7149?page=57&deep=true\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2016-535293?page=56&deep=true", + "source_split": "test" + }, + { + "id": "UID0084", + "uid": "UID0084", + "category": "hard", + "source_files": "treasury_bulletin_1969_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1969-6865?page=30", + "source_split": "test" + }, + { + "id": "UID0088", + "uid": "UID0088", + "category": "easy", + "source_files": "treasury_bulletin_2012_12.txt\r\ntreasury_bulletin_2017_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2012-7142?page=24\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2017-575188?page=22", + "source_split": "test" + }, + { + "id": "UID0089", + "uid": "UID0089", + "category": "easy", + "source_files": "treasury_bulletin_2016_12.txt\r\ntreasury_bulletin_2017_12.txt\r\ntreasury_bulletin_2020_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2016-535293?page=21\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2017-575188?page=21\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=24", + "source_split": "test" + }, + { + "id": "UID0090", + "uid": "UID0090", + "category": "easy", + "source_files": "treasury_bulletin_1985_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1985-7043?page=24", + "source_split": "test" + }, + { + "id": "UID0093", + "uid": "UID0093", + "category": "hard", + "source_files": "treasury_bulletin_1988_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1988-7055?page=95", + "source_split": "test" + }, + { + "id": "UID0094", + "uid": "UID0094", + "category": "hard", + "source_files": "treasury_bulletin_1939_12.txt\r\ntreasury_bulletin_1941_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1939-6513?page=31\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1941-6529?page=26", + "source_split": "test" + }, + { + "id": "UID0095", + "uid": "UID0095", + "category": "easy", + "source_files": "treasury_bulletin_1939_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1939-6513?page=51", + "source_split": "test" + }, + { + "id": "UID0096", + "uid": "UID0096", + "category": "hard", + "source_files": "treasury_bulletin_1940_12.txt\r\ntreasury_bulletin_1941_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1940-6528?page=21\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1941-6540?page=64", + "source_split": "test" + }, + { + "id": "UID0097", + "uid": "UID0097", + "category": "hard", + "source_files": "treasury_bulletin_1989_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1989-7059?page=117&deep=true", + "source_split": "test" + }, + { + "id": "UID0099", + "uid": "UID0099", + "category": "easy", + "source_files": "treasury_bulletin_2020_12.txt\r\ntreasury_bulletin_2024_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=24\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2024-679984?page=25", + "source_split": "test" + }, + { + "id": "UID0100", + "uid": "UID0100", + "category": "hard", + "source_files": "treasury_bulletin_2011_12.txt\r\ntreasury_bulletin_2014_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2011-7149?page=23 \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2014-487465?page=22", + "source_split": "test" + }, + { + "id": "UID0102", + "uid": "UID0102", + "category": "hard", + "source_files": "treasury_bulletin_2021_03.txt\r\ntreasury_bulletin_2021_06.txt\r\ntreasury_bulletin_2021_09.txt\r\ntreasury_bulletin_2021_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2021-601654?page=16\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2021-603946?page=20\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2021-605026?page=20\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2021-610144?page=22", + "source_split": "test" + }, + { + "id": "UID0103", + "uid": "UID0103", + "category": "hard", + "source_files": "treasury_bulletin_1960_12.txt\r\ntreasury_bulletin_1967_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1960-6768?page=71\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1967-6852?page=83", + "source_split": "test" + }, + { + "id": "UID0104", + "uid": "UID0104", + "category": "easy", + "source_files": "treasury_bulletin_1970_12.txt\r\ntreasury_bulletin_1978_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1970-6888?page=94\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1978-6984?page=91", + "source_split": "test" + }, + { + "id": "UID0105", + "uid": "UID0105", + "category": "easy", + "source_files": "treasury_bulletin_1948_12.txt\r\ntreasury_bulletin_1950_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1948-6623?page=54\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1950-6647?page=56", + "source_split": "test" + }, + { + "id": "UID0106", + "uid": "UID0106", + "category": "easy", + "source_files": "treasury_bulletin_1960_12.txt\r\ntreasury_bulletin_1954_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1960-6768?page=13\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1954-6695?page=13", + "source_split": "test" + }, + { + "id": "UID0107", + "uid": "UID0107", + "category": "easy", + "source_files": "treasury_bulletin_1962_12.txt\r\ntreasury_bulletin_1955_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1962-6792?page=91\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1955-6707?page=57", + "source_split": "test" + }, + { + "id": "UID0108", + "uid": "UID0108", + "category": "hard", + "source_files": "treasury_bulletin_2018_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2018-581283?page=18", + "source_split": "test" + }, + { + "id": "UID0111", + "uid": "UID0111", + "category": "hard", + "source_files": "treasury_bulletin_2015_09.txt\r\ntreasury_bulletin_2020_09.txt\r\ntreasury_bulletin_2024_09.txt\r\ntreasury_bulletin_2025_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2015-519208?page=18\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2020-596188?page=21\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2024-677156?page=21\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2025-701334?page=22", + "source_split": "test" + }, + { + "id": "UID0112", + "uid": "UID0112", + "category": "hard", + "source_files": "treasury_bulletin_1996_09.txt\r\ntreasury_bulletin_2001_09.txt\r\ntreasury_bulletin_2006_09.txt\r\ntreasury_bulletin_2011_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1996-7087?page=12\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2001-7107?page=16&deep=true\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2006-7127?page=19\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2011-7148?page=20", + "source_split": "test" + }, + { + "id": "UID0113", + "uid": "UID0113", + "category": "hard", + "source_files": "treasury_bulletin_1982_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1982-7031?page=66", + "source_split": "test" + }, + { + "id": "UID0114", + "uid": "UID0114", + "category": "hard", + "source_files": "treasury_bulletin_2003_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2003-7109?page=58", + "source_split": "test" + }, + { + "id": "UID0116", + "uid": "UID0116", + "category": "easy", + "source_files": "treasury_bulletin_1969_12.txt\r\ntreasury_bulletin_1974_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1969-6876?page=182\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1974-6936?page=126", + "source_split": "test" + }, + { + "id": "UID0117", + "uid": "UID0117", + "category": "hard", + "source_files": "treasury_bulletin_1972_03.txt\r\ntreasury_bulletin_1973_03.txt\r\ntreasury_bulletin_1974_03.txt\r\ntreasury_bulletin_1975_03.txt\r\ntreasury_bulletin_1976_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1972-6903?page=45\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1973-6915?page=49\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1974-6926?page=38\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1975-6939?page=36\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1976-6951?page=38", + "source_split": "test" + }, + { + "id": "UID0118", + "uid": "UID0118", + "category": "hard", + "source_files": "treasury_bulletin_1968_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1968-6859?page=83", + "source_split": "test" + }, + { + "id": "UID0119", + "uid": "UID0119", + "category": "easy", + "source_files": "treasury_bulletin_1960_08.txt\r\ntreasury_bulletin_1961_08.txt\r\ntreasury_bulletin_1962_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1960-6764?page=77\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1961-6776?page=84\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1962-6788?page=98", + "source_split": "test" + }, + { + "id": "UID0120", + "uid": "UID0120", + "category": "hard", + "source_files": "treasury_bulletin_1970_05.txt\r\ntreasury_bulletin_1970_06.txt\r\ntreasury_bulletin_1970_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1970-6758?page=79\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1970-6882?page=76\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1970-6883?page=73", + "source_split": "test" + }, + { + "id": "UID0121", + "uid": "UID0121", + "category": "hard", + "source_files": "treasury_bulletin_1980_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1980-6999?page=81", + "source_split": "test" + }, + { + "id": "UID0124", + "uid": "UID0124", + "category": "hard", + "source_files": "treasury_bulletin_2000_06.txt\r\ntreasury_bulletin_2005_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=48\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=49\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2005-7122?page=50\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2005-7122?page=51", + "source_split": "test" + }, + { + "id": "UID0125", + "uid": "UID0125", + "category": "easy", + "source_files": "treasury_bulletin_2011_03.txt\r\ntreasury_bulletin_2012_03.txt\r\ntreasury_bulletin_2013_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2011-7147?page=106\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2012-7150?page=105\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2013-6928?page=107", + "source_split": "test" + }, + { + "id": "UID0126", + "uid": "UID0126", + "category": "easy", + "source_files": "treasury_bulletin_1970_01.txt\r\ntreasury_bulletin_1970_02.txt\r\ntreasury_bulletin_1970_03.txt\r\ntreasury_bulletin_1970_04.txt\r\ntreasury_bulletin_1970_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1970-6877?page=91\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1970-6878?page=98\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1970-6880?page=93\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1970-6881?page=96\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1970-6758?page=90", + "source_split": "test" + }, + { + "id": "UID0127", + "uid": "UID0127", + "category": "easy", + "source_files": "treasury_bulletin_1991_03.txt\r\ntreasury_bulletin_1992_03.txt\r\ntreasury_bulletin_1993_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1991-7064?page=122\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1992-7068?page=145\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1993-7072?page=132", + "source_split": "test" + }, + { + "id": "UID0128", + "uid": "UID0128", + "category": "easy", + "source_files": "treasury_bulletin_1941_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1941-6529?page=17", + "source_split": "test" + }, + { + "id": "UID0129", + "uid": "UID0129", + "category": "easy", + "source_files": "treasury_bulletin_1994_03.txt\r\ntreasury_bulletin_1999_03.txt\r\ntreasury_bulletin_2004_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1994-7076?page=78\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1999-7097?page=55\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2004-7117?page=53", + "source_split": "test" + }, + { + "id": "UID0130", + "uid": "UID0130", + "category": "hard", + "source_files": "treasury_bulletin_1980_04.txt\r\ntreasury_bulletin_1981_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1980-7000?page=85\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1981-7012?page=81", + "source_split": "test" + }, + { + "id": "UID0131", + "uid": "UID0131", + "category": "easy", + "source_files": "treasury_bulletin_2003_12.txt\r\ntreasury_bulletin_2008_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2003-7116?page=32\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2008-7137?page=38", + "source_split": "test" + }, + { + "id": "UID0132", + "uid": "UID0132", + "category": "easy", + "source_files": "treasury_bulletin_1994_03.txt\r\ntreasury_bulletin_1995_03.txt\r\ntreasury_bulletin_1996_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1994-7076?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1995-7081?page=29\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1996-7085?page=11", + "source_split": "test" + }, + { + "id": "UID0134", + "uid": "UID0134", + "category": "hard", + "source_files": "treasury_bulletin_1963_02.txt\r\ntreasury_bulletin_1964_02.txt\r\ntreasury_bulletin_1965_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1963-6794?page=45\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1964-6806?page=38\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1965-6818?page=42", + "source_split": "test" + }, + { + "id": "UID0135", + "uid": "UID0135", + "category": "hard", + "source_files": "treasury_bulletin_1996_06.txt\r\ntreasury_bulletin_1997_06.txt\r\ntreasury_bulletin_1998_06.txt\r\ntreasury_bulletin_2000_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1996-7086?page=70\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1997-7090?page=68\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1998-7094?page=70\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=65", + "source_split": "test" + }, + { + "id": "UID0136", + "uid": "UID0136", + "category": "hard", + "source_files": "treasury_bulletin_1953_10.txt\r\ntreasury_bulletin_1954_10.txt\r\ntreasury_bulletin_1955_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1953-6681?page=8\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1954-6693?page=11\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1955-6705?page=9", + "source_split": "test" + }, + { + "id": "UID0137", + "uid": "UID0137", + "category": "easy", + "source_files": "treasury_bulletin_1939_05.txt\r\ntreasury_bulletin_1944_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1939-6507?page=65\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1944-6569?page=91", + "source_split": "test" + }, + { + "id": "UID0138", + "uid": "UID0138", + "category": "easy", + "source_files": "treasury_bulletin_1943_04.txt\r\ntreasury_bulletin_1944_04.txt\r\ntreasury_bulletin_1945_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1943-6556?page=51\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1944-6568?page=55\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1945-6578?page=63", + "source_split": "test" + }, + { + "id": "UID0139", + "uid": "UID0139", + "category": "easy", + "source_files": "treasury_bulletin_1970_01.txt\r\ntreasury_bulletin_1970_02.txt\r\ntreasury_bulletin_1970_03.txt\r\ntreasury_bulletin_1970_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1970-6877?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1970-6878?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1970-6880?page=30\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1970-6881?page=31", + "source_split": "test" + }, + { + "id": "UID0140", + "uid": "UID0140", + "category": "hard", + "source_files": "treasury_bulletin_1994_06.txt\r\ntreasury_bulletin_1999_06.txt\r\ntreasury_bulletin_2004_06.txt\r\ntreasury_bulletin_2009_06.txt\r\ntreasury_bulletin_2014_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1994-7077?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1999-7098?page=15\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2004-7118?page=18\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2009-7139?page=20\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2014-7157?page=19", + "source_split": "test" + }, + { + "id": "UID0143", + "uid": "UID0143", + "category": "easy", + "source_files": "treasury_bulletin_1943_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1943-6553?page=33", + "source_split": "test" + }, + { + "id": "UID0146", + "uid": "UID0146", + "category": "easy", + "source_files": "treasury_bulletin_1960_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1960-6756?page=60", + "source_split": "test" + }, + { + "id": "UID0147", + "uid": "UID0147", + "category": "hard", + "source_files": "treasury_bulletin_1948_03.txt\r\ntreasury_bulletin_1949_03.txt\r\ntreasury_bulletin_1950_03.txt\r\ntreasury_bulletin_1951_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1948-6614?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1949-6626?page=29\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1950-6638?page=31\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1951-6650?page=32", + "source_split": "test" + }, + { + "id": "UID0148", + "uid": "UID0148", + "category": "hard", + "source_files": "treasury_bulletin_1972_05.txt\r\ntreasury_bulletin_1973_05.txt\r\ntreasury_bulletin_1974_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1972-6906?page=89\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1973-6898?page=95\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1974-6929?page=83", + "source_split": "test" + }, + { + "id": "UID0149", + "uid": "UID0149", + "category": "hard", + "source_files": "treasury_bulletin_1962_03.txt\r\ntreasury_bulletin_1963_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1962-6783?page=74\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1963-6795?page=81", + "source_split": "test" + }, + { + "id": "UID0152", + "uid": "UID0152", + "category": "easy", + "source_files": "treasury_bulletin_1939_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1939-6518?page=15", + "source_split": "test" + }, + { + "id": "UID0153", + "uid": "UID0153", + "category": "easy", + "source_files": "treasury_bulletin_1996_03.txt\r\ntreasury_bulletin_1997_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1996-7085?page=113\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1997-7089?page=106", + "source_split": "test" + }, + { + "id": "UID0155", + "uid": "UID0155", + "category": "hard", + "source_files": "treasury_bulletin_2010_09.txt\r\ntreasury_bulletin_2011_09.txt\r\ntreasury_bulletin_2012_09.txt\r\ntreasury_bulletin_2013_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2010-7145?page=52\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2011-7148?page=52\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2012-7152?page=52\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2013-7154?page=51", + "source_split": "test" + }, + { + "id": "UID0156", + "uid": "UID0156", + "category": "easy", + "source_files": "treasury_bulletin_1947_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1947-6602?page=34", + "source_split": "test" + }, + { + "id": "UID0157", + "uid": "UID0157", + "category": "easy", + "source_files": "treasury_bulletin_1961_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1961-6774?page=75", + "source_split": "test" + }, + { + "id": "UID0158", + "uid": "UID0158", + "category": "easy", + "source_files": "treasury_bulletin_1970_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1970-6888?page=44", + "source_split": "test" + }, + { + "id": "UID0160", + "uid": "UID0160", + "category": "easy", + "source_files": "treasury_bulletin_1980_03.txt\r\ntreasury_bulletin_1980_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1980-6999?page=9\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1980-7000?page=9", + "source_split": "test" + }, + { + "id": "UID0164", + "uid": "UID0164", + "category": "easy", + "source_files": "treasury_bulletin_1948_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1948-6614?page=37", + "source_split": "test" + }, + { + "id": "UID0167", + "uid": "UID0167", + "category": "easy", + "source_files": "treasury_bulletin_1950_05.txt\r\ntreasury_bulletin_1955_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1950-6640?page=30\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1955-6700?page=27", + "source_split": "test" + }, + { + "id": "UID0168", + "uid": "UID0168", + "category": "hard", + "source_files": "treasury_bulletin_1939_08.txt\r\ntreasury_bulletin_1939_09.txt\r\ntreasury_bulletin_1939_10.txt\r\ntreasury_bulletin_1939_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1939-6510?page=79\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1939-6511?page=45\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1939-6520?page=45\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1939-6512?page=49", + "source_split": "test" + }, + { + "id": "UID0171", + "uid": "UID0171", + "category": "easy", + "source_files": "treasury_bulletin_1963_12.txt\r\ntreasury_bulletin_1964_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1963-6804?page=39\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1964-6816?page=34", + "source_split": "test" + }, + { + "id": "UID0172", + "uid": "UID0172", + "category": "hard", + "source_files": "treasury_bulletin_2000_12.txt\r\ntreasury_bulletin_2001_12.txt\r\ntreasury_bulletin_2002_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2000-7104?page=68\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2001-7108?page=73\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2002-7113?page=73", + "source_split": "test" + }, + { + "id": "UID0173", + "uid": "UID0173", + "category": "hard", + "source_files": "treasury_bulletin_1980_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1980-7004?page=95", + "source_split": "test" + }, + { + "id": "UID0174", + "uid": "UID0174", + "category": "hard", + "source_files": "treasury_bulletin_1960_04.txt\r\ntreasury_bulletin_1960_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1960-6760?page=69\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1960-6762?page=71", + "source_split": "test" + }, + { + "id": "UID0175", + "uid": "UID0175", + "category": "hard", + "source_files": "treasury_bulletin_1947_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1947-6601?page=87", + "source_split": "test" + }, + { + "id": "UID0176", + "uid": "UID0176", + "category": "easy", + "source_files": "treasury_bulletin_1992_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1992-7068?page=42", + "source_split": "test" + }, + { + "id": "UID0177", + "uid": "UID0177", + "category": "hard", + "source_files": "treasury_bulletin_1950_04.txt\r\ntreasury_bulletin_1951_04.txt\r\ntreasury_bulletin_1952_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1950-6639?page=30\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1951-6652?page=33\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1952-6663?page=29", + "source_split": "test" + }, + { + "id": "UID0178", + "uid": "UID0178", + "category": "easy", + "source_files": "treasury_bulletin_2014_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2014-487465?page=19", + "source_split": "test" + }, + { + "id": "UID0179", + "uid": "UID0179", + "category": "hard", + "source_files": "treasury_bulletin_1977_03.txt\r\ntreasury_bulletin_1977_04.txt\r\ntreasury_bulletin_1977_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1977-6963?page=135\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1977-6964?page=137\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1977-6965?page=130", + "source_split": "test" + }, + { + "id": "UID0180", + "uid": "UID0180", + "category": "hard", + "source_files": "treasury_bulletin_2010_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2010-7145?page=47", + "source_split": "test" + }, + { + "id": "UID0181", + "uid": "UID0181", + "category": "easy", + "source_files": "treasury_bulletin_1960_02.txt\r\ntreasury_bulletin_1961_02.txt\r\ntreasury_bulletin_1962_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1960-6757?page=37\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1961-6770?page=36\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1962-6782?page=39", + "source_split": "test" + }, + { + "id": "UID0182", + "uid": "UID0182", + "category": "hard", + "source_files": "treasury_bulletin_2011_03.txt\r\ntreasury_bulletin_2012_03.txt\r\ntreasury_bulletin_2013_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2011-7147?page=59\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2012-7150?page=58\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2013-6928?page=60", + "source_split": "test" + }, + { + "id": "UID0183", + "uid": "UID0183", + "category": "hard", + "source_files": "treasury_bulletin_1964_03.txt\r\ntreasury_bulletin_1965_03.txt\r\ntreasury_bulletin_1966_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1964-6807?page=80\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1965-6819?page=79\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1966-6831?page=86", + "source_split": "test" + }, + { + "id": "UID0184", + "uid": "UID0184", + "category": "hard", + "source_files": "treasury_bulletin_1948_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1948-6614?page=45", + "source_split": "test" + }, + { + "id": "UID0185", + "uid": "UID0185", + "category": "easy", + "source_files": "treasury_bulletin_1990_09.txt\r\ntreasury_bulletin_1991_09.txt\r\ntreasury_bulletin_1992_09.txt\r\ntreasury_bulletin_1993_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1990-7062?page=72\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1991-7066?page=76\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1992-7070?page=69\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1993-7074?page=73", + "source_split": "test" + }, + { + "id": "UID0186", + "uid": "UID0186", + "category": "easy", + "source_files": "treasury_bulletin_1974_11.txt\r\ntreasury_bulletin_1975_11.txt\r\ntreasury_bulletin_1976_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1974-6935?page=80\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1975-6947?page=75\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1976-6960?page=83", + "source_split": "test" + }, + { + "id": "UID0187", + "uid": "UID0187", + "category": "hard", + "source_files": "treasury_bulletin_1940_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1940-6516?page=74", + "source_split": "test" + }, + { + "id": "UID0188", + "uid": "UID0188", + "category": "hard", + "source_files": "treasury_bulletin_1939_01.txt\r\ntreasury_bulletin_1949_01.txt\r\ntreasury_bulletin_1959_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1939-6518?page=67\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1949-6624?page=57\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1959-6744?page=71", + "source_split": "test" + }, + { + "id": "UID0191", + "uid": "UID0191", + "category": "easy", + "source_files": "treasury_bulletin_1980_11.txt\r\ntreasury_bulletin_1981_11.txt\r\ntreasury_bulletin_1982_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1980-7007?page=148\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1981-7019?page=140\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1982-7031?page=112", + "source_split": "test" + }, + { + "id": "UID0192", + "uid": "UID0192", + "category": "easy", + "source_files": "treasury_bulletin_1990_06.txt\r\ntreasury_bulletin_1991_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1990-7061?page=42\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1991-7065?page=46", + "source_split": "test" + }, + { + "id": "UID0193", + "uid": "UID0193", + "category": "hard", + "source_files": "treasury_bulletin_1939_03.txt\r\ntreasury_bulletin_1940_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1939-6519?page=115\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1940-6523?page=71", + "source_split": "test" + }, + { + "id": "UID0194", + "uid": "UID0194", + "category": "hard", + "source_files": "treasury_bulletin_2003_09.txt\r\ntreasury_bulletin_2013_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2003-7115?page=69\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2013-7154?page=62", + "source_split": "test" + }, + { + "id": "UID0196", + "uid": "UID0196", + "category": "hard", + "source_files": "treasury_bulletin_1980_05.txt\r\ntreasury_bulletin_1980_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1980-7001?page=41\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1980-7002?page=35", + "source_split": "test" + }, + { + "id": "UID0197", + "uid": "UID0197", + "category": "easy", + "source_files": "treasury_bulletin_1970_11.txt\r\ntreasury_bulletin_1971_11.txt\r\ntreasury_bulletin_1972_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1970-6887?page=74\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1971-6899?page=70\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1972-6911?page=74", + "source_split": "test" + }, + { + "id": "UID0198", + "uid": "UID0198", + "category": "easy", + "source_files": "treasury_bulletin_1978_05.txt\r\ntreasury_bulletin_1979_05.txt\r\ntreasury_bulletin_1980_05.txt\r\ntreasury_bulletin_1981_05.txt\r\ntreasury_bulletin_1982_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1978-6977?page=91\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1979-6989?page=83\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1980-7001?page=99\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1981-7013?page=81\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1982-7025?page=76", + "source_split": "test" + }, + { + "id": "UID0199", + "uid": "UID0199", + "category": "easy", + "source_files": "treasury_bulletin_1939_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1939-6518?page=49", + "source_split": "test" + }, + { + "id": "UID0200", + "uid": "UID0200", + "category": "easy", + "source_files": "treasury_bulletin_1939_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1939-6513?page=54", + "source_split": "test" + }, + { + "id": "UID0201", + "uid": "UID0201", + "category": "hard", + "source_files": "treasury_bulletin_1975_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1975-6947?page=147", + "source_split": "test" + }, + { + "id": "UID0203", + "uid": "UID0203", + "category": "hard", + "source_files": "treasury_bulletin_1960_04.txt\r\ntreasury_bulletin_1961_04.txt\r\ntreasury_bulletin_1962_04.txt\r\ntreasury_bulletin_1963_04.txt\r\ntreasury_bulletin_1964_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1960-6760?page=36\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1961-6772?page=40\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1962-6784?page=41\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1963-6796?page=45\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1964-6808?page=40", + "source_split": "test" + }, + { + "id": "UID0204", + "uid": "UID0204", + "category": "hard", + "source_files": "treasury_bulletin_2010_09.txt\r\ntreasury_bulletin_2011_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2010-7145?page=13\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2011-7148?page=13", + "source_split": "test" + }, + { + "id": "UID0205", + "uid": "UID0205", + "category": "hard", + "source_files": "treasury_bulletin_1960_10.txt\r\ntreasury_bulletin_1965_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1960-6766?page=15\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1965-6826?page=15", + "source_split": "test" + }, + { + "id": "UID0206", + "uid": "UID0206", + "category": "easy", + "source_files": "treasury_bulletin_2010_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2010-7143?page=31", + "source_split": "test" + }, + { + "id": "UID0207", + "uid": "UID0207", + "category": "hard", + "source_files": "treasury_bulletin_1980_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1980-7002?page=16", + "source_split": "test" + }, + { + "id": "UID0208", + "uid": "UID0208", + "category": "easy", + "source_files": "treasury_bulletin_1973_07.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1973-6918?page=88", + "source_split": "test" + }, + { + "id": "UID0209", + "uid": "UID0209", + "category": "easy", + "source_files": "treasury_bulletin_1970_08.txt\r\ntreasury_bulletin_1970_09.txt\r\ntreasury_bulletin_1970_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1970-6884?page=93\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1970-6885?page=86\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1970-6886?page=83", + "source_split": "test" + }, + { + "id": "UID0210", + "uid": "UID0210", + "category": "easy", + "source_files": "treasury_bulletin_1994_06.txt\r\ntreasury_bulletin_1995_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1994-7077?page=69\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1995-7082?page=63", + "source_split": "test" + }, + { + "id": "UID0211", + "uid": "UID0211", + "category": "hard", + "source_files": "treasury_bulletin_1956_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1956-6715?page=43", + "source_split": "test" + }, + { + "id": "UID0214", + "uid": "UID0214", + "category": "hard", + "source_files": "treasury_bulletin_1970_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1970-6877?page=31", + "source_split": "test" + }, + { + "id": "UID0215", + "uid": "UID0215", + "category": "hard", + "source_files": "treasury_bulletin_1988_03.txt\r\ntreasury_bulletin_1989_03.txt\r\ntreasury_bulletin_1990_03.txt\r\ntreasury_bulletin_1991_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1988-7052?page=52\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1988-7052?page=53\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1988-7052?page=54\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1989-7056?page=53\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1989-7056?page=54\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1989-7056?page=55\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1990-7060?page=51\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1990-7060?page=52\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1990-7060?page=53\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1991-7064?page=53\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1991-7064?page=54\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1991-7064?page=55", + "source_split": "test" + }, + { + "id": "UID0216", + "uid": "UID0216", + "category": "hard", + "source_files": "treasury_bulletin_1941_10.txt\r\ntreasury_bulletin_1942_10.txt\r\ntreasury_bulletin_1943_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1941-6538?page=12\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1942-6550?page=12\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1943-6562?page=22", + "source_split": "test" + }, + { + "id": "UID0218", + "uid": "UID0218", + "category": "hard", + "source_files": "treasury_bulletin_1962_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1962-6783?page=67", + "source_split": "test" + }, + { + "id": "UID0219", + "uid": "UID0219", + "category": "hard", + "source_files": "treasury_bulletin_2013_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2013-7153?page=47", + "source_split": "test" + }, + { + "id": "UID0221", + "uid": "UID0221", + "category": "hard", + "source_files": "treasury_bulletin_1950_01.txt\r\ntreasury_bulletin_1950_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1950-6636?page=32\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1950-6637?page=30", + "source_split": "test" + }, + { + "id": "UID0223", + "uid": "UID0223", + "category": "hard", + "source_files": "treasury_bulletin_1991_09.txt\r\ntreasury_bulletin_1996_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1991-7066?page=99\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1996-7087?page=69", + "source_split": "test" + }, + { + "id": "UID0224", + "uid": "UID0224", + "category": "hard", + "source_files": "treasury_bulletin_1943_01.txt\r\ntreasury_bulletin_1944_01.txt\r\ntreasury_bulletin_1945_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1943-6553?page=74\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1944-6565?page=68\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1945-6575?page=83", + "source_split": "test" + }, + { + "id": "UID0225", + "uid": "UID0225", + "category": "hard", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=74", + "source_split": "test" + }, + { + "id": "UID0226", + "uid": "UID0226", + "category": "hard", + "source_files": "treasury_bulletin_1953_03.txt\r\ntreasury_bulletin_1954_03.txt\r\ntreasury_bulletin_1955_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1953-6674?page=31\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1954-6686?page=25\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1955-6698?page=27", + "source_split": "test" + }, + { + "id": "UID0227", + "uid": "UID0227", + "category": "hard", + "source_files": "treasury_bulletin_1982_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1982-7031?page=66", + "source_split": "test" + }, + { + "id": "UID0230", + "uid": "UID0230", + "category": "hard", + "source_files": "treasury_bulletin_1960_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1960-6766?page=14", + "source_split": "test" + }, + { + "id": "UID0231", + "uid": "UID0231", + "category": "easy", + "source_files": "treasury_bulletin_1961_12.txt\r\ntreasury_bulletin_1962_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1961-6780?page=35\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1962-6792?page=44", + "source_split": "test" + }, + { + "id": "UID0232", + "uid": "UID0232", + "category": "easy", + "source_files": "treasury_bulletin_1949_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1949-6626?page=18", + "source_split": "test" + }, + { + "id": "UID0236", + "uid": "UID0236", + "category": "easy", + "source_files": "treasury_bulletin_1982_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1982-7024?page=77", + "source_split": "test" + }, + { + "id": "UID0237", + "uid": "UID0237", + "category": "hard", + "source_files": "treasury_bulletin_2007_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2007-7132?page=47", + "source_split": "test" + }, + { + "id": "UID0242", + "uid": "UID0242", + "category": "easy", + "source_files": "treasury_bulletin_2010_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=57\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=59\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=61\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=62\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=64\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=86\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=87\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2010-7144?page=89", + "source_split": "test" + }, + { + "id": "UID0243", + "uid": "UID0243", + "category": "hard", + "source_files": "treasury_bulletin_1970_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1970-6877?page=32", + "source_split": "test" + }, + { + "id": "UID0244", + "uid": "UID0244", + "category": "hard", + "source_files": "treasury_bulletin_1960_01.txt\r\ntreasury_bulletin_1960_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1960-6756?page=20\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1960-6757?page=22", + "source_split": "test" + }, + { + "id": "UID0245", + "uid": "UID0245", + "category": "hard", + "source_files": "treasury_bulletin_1982_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1982-7028?page=82", + "source_split": "test" + }, + { + "id": "UID0246", + "uid": "UID0246", + "category": "hard", + "source_files": "treasury_bulletin_1970_03.txt\r\ntreasury_bulletin_1975_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1970-6880?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1975-6939?page=71", + "source_split": "test" + } +] diff --git a/data/officeqa_id_split/train/items.json b/data/officeqa_id_split/train/items.json new file mode 100644 index 0000000..ea8265a --- /dev/null +++ b/data/officeqa_id_split/train/items.json @@ -0,0 +1,402 @@ +[ + { + "id": "UID0002", + "uid": "UID0002", + "category": "easy", + "source_files": "treasury_bulletin_1944_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1944-6565?page=18", + "source_split": "train" + }, + { + "id": "UID0007", + "uid": "UID0007", + "category": "hard", + "source_files": "treasury_bulletin_1950_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1950-6637?page=15", + "source_split": "train" + }, + { + "id": "UID0014", + "uid": "UID0014", + "category": "easy", + "source_files": "treasury_bulletin_1942_07.txt\r\ntreasury_bulletin_2001_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1942-6547?page=76\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2001-7108?page=17&deep=true", + "source_split": "train" + }, + { + "id": "UID0017", + "uid": "UID0017", + "category": "hard", + "source_files": "treasury_bulletin_1982_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1982-7028?page=13", + "source_split": "train" + }, + { + "id": "UID0018", + "uid": "UID0018", + "category": "hard", + "source_files": "treasury_bulletin_1985_03.txt\r\ntreasury_bulletin_1986_03.txt\r\ntreasury_bulletin_1987_03.txt\r\ntreasury_bulletin_1988_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1985-7040?page=22\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1986-7045?page=26\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1987-7049?page=24\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1988-7052?page=36", + "source_split": "train" + }, + { + "id": "UID0019", + "uid": "UID0019", + "category": "hard", + "source_files": "treasury_bulletin_2016_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2016-533966?page=54\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2016-533966?page=58", + "source_split": "train" + }, + { + "id": "UID0026", + "uid": "UID0026", + "category": "easy", + "source_files": "treasury_bulletin_1963_01.txt\r\ntreasury_bulletin_1962_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1963-6793?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1962-6781?page=82&deep=true", + "source_split": "train" + }, + { + "id": "UID0028", + "uid": "UID0028", + "category": "hard", + "source_files": "treasury_bulletin_1970_06.txt\r\ntreasury_bulletin_1964_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1970-6882?page=89&deep=true\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1964-6816?page=25&deep=true", + "source_split": "train" + }, + { + "id": "UID0030", + "uid": "UID0030", + "category": "hard", + "source_files": "treasury_bulletin_1990_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1990-7062?page=19&deep=true", + "source_split": "train" + }, + { + "id": "UID0031", + "uid": "UID0031", + "category": "hard", + "source_files": "treasury_bulletin_1992_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1992-7068?page=158&deep=true", + "source_split": "train" + }, + { + "id": "UID0033", + "uid": "UID0033", + "category": "easy", + "source_files": "treasury_bulletin_1977_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1977-6964?page=9", + "source_split": "train" + }, + { + "id": "UID0034", + "uid": "UID0034", + "category": "easy", + "source_files": "treasury_bulletin_1992_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1992-7069?page=32", + "source_split": "train" + }, + { + "id": "UID0044", + "uid": "UID0044", + "category": "hard", + "source_files": "treasury_bulletin_1939_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1939-6506?page=61", + "source_split": "train" + }, + { + "id": "UID0046", + "uid": "UID0046", + "category": "easy", + "source_files": "treasury_bulletin_1988_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1988-7054?page=37", + "source_split": "train" + }, + { + "id": "UID0049", + "uid": "UID0049", + "category": "hard", + "source_files": "treasury_bulletin_1942_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1942-6542?page=19&deep=true", + "source_split": "train" + }, + { + "id": "UID0056", + "uid": "UID0056", + "category": "hard", + "source_files": "treasury_bulletin_1991_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1991-7066?page=30&deep=true", + "source_split": "train" + }, + { + "id": "UID0063", + "uid": "UID0063", + "category": "easy", + "source_files": "treasury_bulletin_1990_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1990-7061?page=127", + "source_split": "train" + }, + { + "id": "UID0065", + "uid": "UID0065", + "category": "hard", + "source_files": "treasury_bulletin_1998_06.txt\r\ntreasury_bulletin_1995_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1998-7094?page=7\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1995-7084?page=16", + "source_split": "train" + }, + { + "id": "UID0073", + "uid": "UID0073", + "category": "hard", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=24", + "source_split": "train" + }, + { + "id": "UID0079", + "uid": "UID0079", + "category": "easy", + "source_files": "treasury_bulletin_2011_12.txt\r\ntreasury_bulletin_2013_12.txt\r\ntreasury_bulletin_2015_12.txt\r\ntreasury_bulletin_2017_12.txt\r\ntreasury_bulletin_2019_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2011-7149?page=25\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2013-7155?page=24\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2015-519209?page=23\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2017-575188?page=23\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2019-584842?page=22", + "source_split": "train" + }, + { + "id": "UID0083", + "uid": "UID0083", + "category": "hard", + "source_files": "treasury_bulletin_1981_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1981-7020?page=24", + "source_split": "train" + }, + { + "id": "UID0085", + "uid": "UID0085", + "category": "hard", + "source_files": "treasury_bulletin_2019_12.txt\r\ntreasury_bulletin_2018_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2019-584842?page=23\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2018-581283?page=22", + "source_split": "train" + }, + { + "id": "UID0087", + "uid": "UID0087", + "category": "easy", + "source_files": "treasury_bulletin_2013_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2013-7155?page=17", + "source_split": "train" + }, + { + "id": "UID0092", + "uid": "UID0092", + "category": "easy", + "source_files": "treasury_bulletin_1987_12.txt\r\ntreasury_bulletin_1992_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1987-7051?page=69\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1992-7071?page=84", + "source_split": "train" + }, + { + "id": "UID0098", + "uid": "UID0098", + "category": "easy", + "source_files": "treasury_bulletin_2020_12.txt\r\ntreasury_bulletin_2024_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=21\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2024-679984?page=22", + "source_split": "train" + }, + { + "id": "UID0101", + "uid": "UID0101", + "category": "hard", + "source_files": "treasury_bulletin_2011_12.txt\r\ntreasury_bulletin_2019_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2011-7149?page=25\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2019-584842?page=22", + "source_split": "train" + }, + { + "id": "UID0110", + "uid": "UID0110", + "category": "hard", + "source_files": "treasury_bulletin_2020_03.txt\r\ntreasury_bulletin_2016_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2020-587316?page=10\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2016-527290?page=9", + "source_split": "train" + }, + { + "id": "UID0115", + "uid": "UID0115", + "category": "easy", + "source_files": "treasury_bulletin_1980_02.txt\r\ntreasury_bulletin_1981_02.txt\r\ntreasury_bulletin_1982_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1980-6998?page=27\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1981-7010?page=38\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1982-7022?page=31", + "source_split": "train" + }, + { + "id": "UID0122", + "uid": "UID0122", + "category": "hard", + "source_files": "treasury_bulletin_2001_03.txt\r\ntreasury_bulletin_2002_03.txt\r\ntreasury_bulletin_2003_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2001-7105?page=112\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2002-7110?page=115\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2003-7109?page=113", + "source_split": "train" + }, + { + "id": "UID0123", + "uid": "UID0123", + "category": "hard", + "source_files": "treasury_bulletin_1941_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1941-6540?page=91", + "source_split": "train" + }, + { + "id": "UID0133", + "uid": "UID0133", + "category": "hard", + "source_files": "treasury_bulletin_2004_09.txt\r\ntreasury_bulletin_2013_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2004-7119?page=63\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2013-7155?page=68", + "source_split": "train" + }, + { + "id": "UID0141", + "uid": "UID0141", + "category": "easy", + "source_files": "treasury_bulletin_1962_04.txt\r\ntreasury_bulletin_1963_04.txt\r\ntreasury_bulletin_1964_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1962-6784?page=75\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1963-6796?page=79\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1964-6808?page=82", + "source_split": "train" + }, + { + "id": "UID0144", + "uid": "UID0144", + "category": "easy", + "source_files": "treasury_bulletin_1980_11.txt\r\ntreasury_bulletin_1981_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1980-7007?page=76\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1981-7019?page=67", + "source_split": "train" + }, + { + "id": "UID0145", + "uid": "UID0145", + "category": "easy", + "source_files": "treasury_bulletin_1943_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1943-6553?page=41", + "source_split": "train" + }, + { + "id": "UID0150", + "uid": "UID0150", + "category": "hard", + "source_files": "treasury_bulletin_1972_04.txt\r\ntreasury_bulletin_1973_04.txt\r\ntreasury_bulletin_1974_04.txt\r\ntreasury_bulletin_1975_04.txt\r\ntreasury_bulletin_1976_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1972-6905?page=89\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1973-6916?page=91\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1974-6927?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1975-6940?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1976-6952?page=104", + "source_split": "train" + }, + { + "id": "UID0151", + "uid": "UID0151", + "category": "easy", + "source_files": "treasury_bulletin_1953_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1953-6674?page=54", + "source_split": "train" + }, + { + "id": "UID0162", + "uid": "UID0162", + "category": "easy", + "source_files": "treasury_bulletin_2011_06.txt\r\ntreasury_bulletin_2012_06.txt\r\ntreasury_bulletin_2013_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2011-7129?page=105\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2012-7151?page=105\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2013-7153?page=104", + "source_split": "train" + }, + { + "id": "UID0163", + "uid": "UID0163", + "category": "easy", + "source_files": "treasury_bulletin_1981_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1981-7020?page=28", + "source_split": "train" + }, + { + "id": "UID0165", + "uid": "UID0165", + "category": "hard", + "source_files": "treasury_bulletin_2010_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2010-7143?page=49", + "source_split": "train" + }, + { + "id": "UID0166", + "uid": "UID0166", + "category": "easy", + "source_files": "treasury_bulletin_1943_03.txt\r\ntreasury_bulletin_1944_03.txt\r\ntreasury_bulletin_1945_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1943-6555?page=68\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1944-6567?page=83\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1945-6577?page=71", + "source_split": "train" + }, + { + "id": "UID0169", + "uid": "UID0169", + "category": "hard", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=73", + "source_split": "train" + }, + { + "id": "UID0189", + "uid": "UID0189", + "category": "easy", + "source_files": "treasury_bulletin_1970_08.txt\r\ntreasury_bulletin_1970_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1970-6884?page=70\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1970-6885?page=70", + "source_split": "train" + }, + { + "id": "UID0195", + "uid": "UID0195", + "category": "hard", + "source_files": "treasury_bulletin_1956_08.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1956-6715?page=59", + "source_split": "train" + }, + { + "id": "UID0202", + "uid": "UID0202", + "category": "easy", + "source_files": "treasury_bulletin_1939_07.txt\r\ntreasury_bulletin_1939_08.txt\r\ntreasury_bulletin_1939_09.txt\r\ntreasury_bulletin_1939_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1939-6509?page=99\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1939-6510?page=107\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1939-6511?page=60\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1939-6520?page=62", + "source_split": "train" + }, + { + "id": "UID0212", + "uid": "UID0212", + "category": "hard", + "source_files": "treasury_bulletin_1964_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1964-6805?page=99", + "source_split": "train" + }, + { + "id": "UID0222", + "uid": "UID0222", + "category": "hard", + "source_files": "treasury_bulletin_2001_06.txt\r\ntreasury_bulletin_2006_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2001-7106?page=50\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2006-7126?page=50", + "source_split": "train" + }, + { + "id": "UID0228", + "uid": "UID0228", + "category": "hard", + "source_files": "treasury_bulletin_1956_03.txt\r\ntreasury_bulletin_1956_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1956-6710?page=22\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1956-6711?page=22", + "source_split": "train" + }, + { + "id": "UID0229", + "uid": "UID0229", + "category": "easy", + "source_files": "treasury_bulletin_2005_03.txt\r\ntreasury_bulletin_2006_03.txt\r\ntreasury_bulletin_2007_03.txt\r\ntreasury_bulletin_2008_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2005-7121?page=109\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2006-7125?page=106\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2007-7130?page=109\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2008-7134?page=107", + "source_split": "train" + }, + { + "id": "UID0238", + "uid": "UID0238", + "category": "hard", + "source_files": "treasury_bulletin_1982_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1982-7023?page=44", + "source_split": "train" + }, + { + "id": "UID0241", + "uid": "UID0241", + "category": "easy", + "source_files": "treasury_bulletin_1963_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1963-6798?page=13", + "source_split": "train" + } +] diff --git a/data/officeqa_id_split/val/items.json b/data/officeqa_id_split/val/items.json new file mode 100644 index 0000000..290a52d --- /dev/null +++ b/data/officeqa_id_split/val/items.json @@ -0,0 +1,194 @@ +[ + { + "id": "UID0001", + "uid": "UID0001", + "category": "hard", + "source_files": "treasury_bulletin_1941_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1941-6529?page=15", + "source_split": "val" + }, + { + "id": "UID0027", + "uid": "UID0027", + "category": "hard", + "source_files": "treasury_bulletin_1970_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1970-6882?page=89&deep=true", + "source_split": "val" + }, + { + "id": "UID0039", + "uid": "UID0039", + "category": "hard", + "source_files": "treasury_bulletin_2004_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2004-7117?page=20\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-2004-7117?page=21&deep=true", + "source_split": "val" + }, + { + "id": "UID0041", + "uid": "UID0041", + "category": "easy", + "source_files": "treasury_bulletin_1970_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1970-6886?page=35", + "source_split": "val" + }, + { + "id": "UID0052", + "uid": "UID0052", + "category": "easy", + "source_files": "treasury_bulletin_2000_06.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/june-2000-7102?page=56", + "source_split": "val" + }, + { + "id": "UID0070", + "uid": "UID0070", + "category": "easy", + "source_files": "treasury_bulletin_1939_01.txt\r\ntreasury_bulletin_1939_02.txt\r\ntreasury_bulletin_1939_03.txt\r\ntreasury_bulletin_1939_04.txt\r\ntreasury_bulletin_1939_05.txt\r\ntreasury_bulletin_1939_06.txt\r\ntreasury_bulletin_1939_07.txt\r\ntreasury_bulletin_1939_08.txt\r\ntreasury_bulletin_1939_09.txt\r\ntreasury_bulletin_1939_10.txt\r\ntreasury_bulletin_1939_11.txt\r\ntreasury_bulletin_1939_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1939-6518?page=81\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1939-6505?page=111\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1939-6519?page=117\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1939-6506?page=95\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1939-6507?page=109\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/june-1939-6508?page=117\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/july-1939-6509?page=109\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/august-1939-6510?page=117\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/september-1939-6511?page=66&deep=true \r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1939-6520?page=68\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1939-6512?page=70\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1939-6513?page=72", + "source_split": "val" + }, + { + "id": "UID0072", + "uid": "UID0072", + "category": "easy", + "source_files": "treasury_bulletin_2011_12.txt\r\ntreasury_bulletin_2016_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2011-7149?page=58\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2016-535293?page=57", + "source_split": "val" + }, + { + "id": "UID0086", + "uid": "UID0086", + "category": "hard", + "source_files": "treasury_bulletin_2022_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2022-627778?page=86", + "source_split": "val" + }, + { + "id": "UID0091", + "uid": "UID0091", + "category": "easy", + "source_files": "treasury_bulletin_1940_12.txt\r\ntreasury_bulletin_1941_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1940-6528?page=21\r\n\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1941-6540?page=64", + "source_split": "val" + }, + { + "id": "UID0109", + "uid": "UID0109", + "category": "hard", + "source_files": "treasury_bulletin_2015_12.txt\r\ntreasury_bulletin_2020_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2015-519209?page=21\r\n \r\n https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-2020-598551?page=24", + "source_split": "val" + }, + { + "id": "UID0142", + "uid": "UID0142", + "category": "easy", + "source_files": "treasury_bulletin_1944_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1944-6567?page=93", + "source_split": "val" + }, + { + "id": "UID0154", + "uid": "UID0154", + "category": "hard", + "source_files": "treasury_bulletin_1977_03.txt\r\ntreasury_bulletin_1978_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1977-6963?page=83\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1978-6975?page=84", + "source_split": "val" + }, + { + "id": "UID0159", + "uid": "UID0159", + "category": "easy", + "source_files": "treasury_bulletin_2000_09.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/september-2000-7103?page=109", + "source_split": "val" + }, + { + "id": "UID0161", + "uid": "UID0161", + "category": "hard", + "source_files": "treasury_bulletin_1980_03.txt\r\ntreasury_bulletin_1985_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1980-6999?page=88\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1985-7040?page=48", + "source_split": "val" + }, + { + "id": "UID0170", + "uid": "UID0170", + "category": "hard", + "source_files": "treasury_bulletin_1960_03.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/march-1960-6759?page=64", + "source_split": "val" + }, + { + "id": "UID0190", + "uid": "UID0190", + "category": "hard", + "source_files": "treasury_bulletin_1939_10.txt\r\ntreasury_bulletin_1939_11.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1939-6520?page=14\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/november-1939-6512?page=14", + "source_split": "val" + }, + { + "id": "UID0213", + "uid": "UID0213", + "category": "hard", + "source_files": "treasury_bulletin_1947_04.txt\r\ntreasury_bulletin_1948_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1947-6603?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1948-6615?page=18", + "source_split": "val" + }, + { + "id": "UID0217", + "uid": "UID0217", + "category": "easy", + "source_files": "treasury_bulletin_1963_10.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/october-1963-6802?page=15", + "source_split": "val" + }, + { + "id": "UID0220", + "uid": "UID0220", + "category": "hard", + "source_files": "treasury_bulletin_1939_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1939-6505?page=25", + "source_split": "val" + }, + { + "id": "UID0233", + "uid": "UID0233", + "category": "hard", + "source_files": "treasury_bulletin_1948_04.txt\r\ntreasury_bulletin_1958_04.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1948-6615?page=42\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1958-6735?page=54", + "source_split": "val" + }, + { + "id": "UID0234", + "uid": "UID0234", + "category": "easy", + "source_files": "treasury_bulletin_1958_01.txt\r\ntreasury_bulletin_1958_02.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1958-6732?page=28\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/february-1958-6733?page=32", + "source_split": "val" + }, + { + "id": "UID0235", + "uid": "UID0235", + "category": "easy", + "source_files": "treasury_bulletin_1948_04.txt\r\ntreasury_bulletin_1948_05.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/april-1948-6615?page=27\r\nhttps://fraser.stlouisfed.org/title/treasury-bulletin-407/may-1948-6616?page=27", + "source_split": "val" + }, + { + "id": "UID0239", + "uid": "UID0239", + "category": "easy", + "source_files": "treasury_bulletin_1953_01.txt\r\ntreasury_bulletin_1954_01.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1953-6672?page=62\r\nhttp://fraser.stlouisfed.org/title/treasury-bulletin-407/january-1954-6684?page=51", + "source_split": "val" + }, + { + "id": "UID0240", + "uid": "UID0240", + "category": "hard", + "source_files": "treasury_bulletin_1957_12.txt", + "source_docs": "https://fraser.stlouisfed.org/title/treasury-bulletin-407/december-1957-6731?page=26", + "source_split": "val" + } +] diff --git a/data/searchqa_id_split/split_manifest.json b/data/searchqa_id_split/split_manifest.json new file mode 100644 index 0000000..9b87645 --- /dev/null +++ b/data/searchqa_id_split/split_manifest.json @@ -0,0 +1,21 @@ +{ + "benchmark": "SearchQA", + "manifest_type": "id_split", + "source_repo": "lucadiliello/searchqa", + "source_repo_type": "dataset", + "source_url": "https://huggingface.co/datasets/lucadiliello/searchqa", + "source_id_field": "key", + "counts": { + "train": 400, + "val": 200, + "test": 1400 + }, + "item_fields": [ + "id" + ], + "notes": [ + "This is a split manifest, not the full SearchQA payload.", + "Materialize full split items from lucadiliello/searchqa before evaluation.", + "The IDs in items.json exactly match the key field in lucadiliello/searchqa." + ] +} diff --git a/data/searchqa_id_split/test/test.json b/data/searchqa_id_split/test/items.json similarity index 100% rename from data/searchqa_id_split/test/test.json rename to data/searchqa_id_split/test/items.json diff --git a/data/searchqa_id_split/train/train.json b/data/searchqa_id_split/train/items.json similarity index 100% rename from data/searchqa_id_split/train/train.json rename to data/searchqa_id_split/train/items.json diff --git a/data/searchqa_id_split/val/sel.json b/data/searchqa_id_split/val/items.json similarity index 100% rename from data/searchqa_id_split/val/sel.json rename to data/searchqa_id_split/val/items.json diff --git a/data/spreadsheetbench_id_split/split_manifest.json b/data/spreadsheetbench_id_split/split_manifest.json new file mode 100644 index 0000000..03a558c --- /dev/null +++ b/data/spreadsheetbench_id_split/split_manifest.json @@ -0,0 +1,24 @@ +{ + "benchmark": "SpreadsheetBench", + "manifest_type": "id_split", + "source_repo": "KAKA22/SpreadsheetBench", + "source_repo_type": "dataset", + "source_url": "https://huggingface.co/datasets/KAKA22/SpreadsheetBench", + "source_revision": "ab0b742b0fc95b946f212d80ac7771b5531272e4", + "source_file": "spreadsheetbench_verified_400.tar.gz", + "source_split_name": "spreadsheetbench_split", + "counts": { + "train": 80, + "val": 40, + "test": 280 + }, + "item_fields": [ + "id", + "spreadsheet_path", + "instruction_type" + ], + "notes": [ + "This is a split manifest, not the full SpreadsheetBench payload.", + "Materialize full task JSON rows plus spreadsheet files from SpreadsheetBench Verified 400 before evaluation." + ] +} diff --git a/data/spreadsheetbench_id_split/test/items.json b/data/spreadsheetbench_id_split/test/items.json new file mode 100644 index 0000000..08c78ee --- /dev/null +++ b/data/spreadsheetbench_id_split/test/items.json @@ -0,0 +1,1402 @@ +[ + { + "id": "52532", + "spreadsheet_path": "spreadsheet/52532", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41-47", + "spreadsheet_path": "spreadsheet/41-47", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "59794", + "spreadsheet_path": "spreadsheet/59794", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42515", + "spreadsheet_path": "spreadsheet/42515", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "493-5", + "spreadsheet_path": "spreadsheet/493-5", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "41969", + "spreadsheet_path": "spreadsheet/41969", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "49237", + "spreadsheet_path": "spreadsheet/49237", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "516-46", + "spreadsheet_path": "spreadsheet/516-46", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "290-27", + "spreadsheet_path": "spreadsheet/290-27", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "32562", + "spreadsheet_path": "spreadsheet/32562", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "545-35", + "spreadsheet_path": "spreadsheet/545-35", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "32293", + "spreadsheet_path": "spreadsheet/32293", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42181", + "spreadsheet_path": "spreadsheet/42181", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "46240", + "spreadsheet_path": "spreadsheet/46240", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55817", + "spreadsheet_path": "spreadsheet/55817", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59358", + "spreadsheet_path": "spreadsheet/59358", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "44389", + "spreadsheet_path": "spreadsheet/44389", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58701", + "spreadsheet_path": "spreadsheet/58701", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50193", + "spreadsheet_path": "spreadsheet/50193", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55976", + "spreadsheet_path": "spreadsheet/55976", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56378", + "spreadsheet_path": "spreadsheet/56378", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "438-18", + "spreadsheet_path": "spreadsheet/438-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "50952", + "spreadsheet_path": "spreadsheet/50952", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "408-5", + "spreadsheet_path": "spreadsheet/408-5", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "56953", + "spreadsheet_path": "spreadsheet/56953", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54925", + "spreadsheet_path": "spreadsheet/54925", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "448-11", + "spreadsheet_path": "spreadsheet/448-11", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "52917", + "spreadsheet_path": "spreadsheet/52917", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "382-29", + "spreadsheet_path": "spreadsheet/382-29", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "45707", + "spreadsheet_path": "spreadsheet/45707", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42526", + "spreadsheet_path": "spreadsheet/42526", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41978", + "spreadsheet_path": "spreadsheet/41978", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "146-49", + "spreadsheet_path": "spreadsheet/146-49", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "440-24", + "spreadsheet_path": "spreadsheet/440-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "46167", + "spreadsheet_path": "spreadsheet/46167", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "230-16", + "spreadsheet_path": "spreadsheet/230-16", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54675", + "spreadsheet_path": "spreadsheet/54675", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41601", + "spreadsheet_path": "spreadsheet/41601", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41410", + "spreadsheet_path": "spreadsheet/41410", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50521", + "spreadsheet_path": "spreadsheet/50521", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "18645", + "spreadsheet_path": "spreadsheet/18645", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52807", + "spreadsheet_path": "spreadsheet/52807", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52964", + "spreadsheet_path": "spreadsheet/52964", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50250", + "spreadsheet_path": "spreadsheet/50250", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "203-15", + "spreadsheet_path": "spreadsheet/203-15", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "37900", + "spreadsheet_path": "spreadsheet/37900", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48975", + "spreadsheet_path": "spreadsheet/48975", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "367-23", + "spreadsheet_path": "spreadsheet/367-23", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "60-7", + "spreadsheet_path": "spreadsheet/60-7", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "55708", + "spreadsheet_path": "spreadsheet/55708", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "49196", + "spreadsheet_path": "spreadsheet/49196", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57693", + "spreadsheet_path": "spreadsheet/57693", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50051", + "spreadsheet_path": "spreadsheet/50051", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "290-1", + "spreadsheet_path": "spreadsheet/290-1", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "57262", + "spreadsheet_path": "spreadsheet/57262", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41589", + "spreadsheet_path": "spreadsheet/41589", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "49300", + "spreadsheet_path": "spreadsheet/49300", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "37554", + "spreadsheet_path": "spreadsheet/37554", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39515", + "spreadsheet_path": "spreadsheet/39515", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "37086", + "spreadsheet_path": "spreadsheet/37086", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "36277", + "spreadsheet_path": "spreadsheet/36277", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "374-18", + "spreadsheet_path": "spreadsheet/374-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "50971", + "spreadsheet_path": "spreadsheet/50971", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "37229", + "spreadsheet_path": "spreadsheet/37229", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57033", + "spreadsheet_path": "spreadsheet/57033", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "477-45", + "spreadsheet_path": "spreadsheet/477-45", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "531-18", + "spreadsheet_path": "spreadsheet/531-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "38074", + "spreadsheet_path": "spreadsheet/38074", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56599", + "spreadsheet_path": "spreadsheet/56599", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "31746", + "spreadsheet_path": "spreadsheet/31746", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51556", + "spreadsheet_path": "spreadsheet/51556", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48924", + "spreadsheet_path": "spreadsheet/48924", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "423-16", + "spreadsheet_path": "spreadsheet/423-16", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "43213", + "spreadsheet_path": "spreadsheet/43213", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "49801", + "spreadsheet_path": "spreadsheet/49801", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54717", + "spreadsheet_path": "spreadsheet/54717", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58147", + "spreadsheet_path": "spreadsheet/58147", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54474", + "spreadsheet_path": "spreadsheet/54474", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56921", + "spreadsheet_path": "spreadsheet/56921", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39190", + "spreadsheet_path": "spreadsheet/39190", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "168-17", + "spreadsheet_path": "spreadsheet/168-17", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "49945", + "spreadsheet_path": "spreadsheet/49945", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "32093", + "spreadsheet_path": "spreadsheet/32093", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "17111", + "spreadsheet_path": "spreadsheet/17111", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "120-24", + "spreadsheet_path": "spreadsheet/120-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "97-36", + "spreadsheet_path": "spreadsheet/97-36", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "59639", + "spreadsheet_path": "spreadsheet/59639", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "567-21", + "spreadsheet_path": "spreadsheet/567-21", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "48643", + "spreadsheet_path": "spreadsheet/48643", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "1925", + "spreadsheet_path": "spreadsheet/1925", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "40959", + "spreadsheet_path": "spreadsheet/40959", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51431", + "spreadsheet_path": "spreadsheet/51431", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "37462", + "spreadsheet_path": "spreadsheet/37462", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53161", + "spreadsheet_path": "spreadsheet/53161", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "283-32", + "spreadsheet_path": "spreadsheet/283-32", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "1563", + "spreadsheet_path": "spreadsheet/1563", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "599-9", + "spreadsheet_path": "spreadsheet/599-9", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "50682", + "spreadsheet_path": "spreadsheet/50682", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "304-35", + "spreadsheet_path": "spreadsheet/304-35", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "297-42", + "spreadsheet_path": "spreadsheet/297-42", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "40478", + "spreadsheet_path": "spreadsheet/40478", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "9391", + "spreadsheet_path": "spreadsheet/9391", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "269-44", + "spreadsheet_path": "spreadsheet/269-44", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "208-20", + "spreadsheet_path": "spreadsheet/208-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "45063", + "spreadsheet_path": "spreadsheet/45063", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54590", + "spreadsheet_path": "spreadsheet/54590", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "3002", + "spreadsheet_path": "spreadsheet/3002", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "9448", + "spreadsheet_path": "spreadsheet/9448", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "388-47", + "spreadsheet_path": "spreadsheet/388-47", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "51354", + "spreadsheet_path": "spreadsheet/51354", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "24-23", + "spreadsheet_path": "spreadsheet/24-23", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "52541", + "spreadsheet_path": "spreadsheet/52541", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "353-29", + "spreadsheet_path": "spreadsheet/353-29", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "45300", + "spreadsheet_path": "spreadsheet/45300", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "13-1", + "spreadsheet_path": "spreadsheet/13-1", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "58942", + "spreadsheet_path": "spreadsheet/58942", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "45944", + "spreadsheet_path": "spreadsheet/45944", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52305", + "spreadsheet_path": "spreadsheet/52305", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52575", + "spreadsheet_path": "spreadsheet/52575", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52220", + "spreadsheet_path": "spreadsheet/52220", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "91-34", + "spreadsheet_path": "spreadsheet/91-34", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "40757", + "spreadsheet_path": "spreadsheet/40757", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "399-14", + "spreadsheet_path": "spreadsheet/399-14", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "82-38", + "spreadsheet_path": "spreadsheet/82-38", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "156-14", + "spreadsheet_path": "spreadsheet/156-14", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "45896", + "spreadsheet_path": "spreadsheet/45896", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "33157", + "spreadsheet_path": "spreadsheet/33157", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48257", + "spreadsheet_path": "spreadsheet/48257", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "4714", + "spreadsheet_path": "spreadsheet/4714", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "302-1", + "spreadsheet_path": "spreadsheet/302-1", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "47842", + "spreadsheet_path": "spreadsheet/47842", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "36764", + "spreadsheet_path": "spreadsheet/36764", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "455-35", + "spreadsheet_path": "spreadsheet/455-35", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "14240", + "spreadsheet_path": "spreadsheet/14240", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "33722", + "spreadsheet_path": "spreadsheet/33722", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "387-16", + "spreadsheet_path": "spreadsheet/387-16", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "35739", + "spreadsheet_path": "spreadsheet/35739", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "44296", + "spreadsheet_path": "spreadsheet/44296", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "17-35", + "spreadsheet_path": "spreadsheet/17-35", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54513", + "spreadsheet_path": "spreadsheet/54513", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "343-20", + "spreadsheet_path": "spreadsheet/343-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "9111", + "spreadsheet_path": "spreadsheet/9111", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56419", + "spreadsheet_path": "spreadsheet/56419", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59884", + "spreadsheet_path": "spreadsheet/59884", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "44017", + "spreadsheet_path": "spreadsheet/44017", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53449", + "spreadsheet_path": "spreadsheet/53449", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "191-40", + "spreadsheet_path": "spreadsheet/191-40", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "28-7", + "spreadsheet_path": "spreadsheet/28-7", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "31202", + "spreadsheet_path": "spreadsheet/31202", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "18935", + "spreadsheet_path": "spreadsheet/18935", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51359", + "spreadsheet_path": "spreadsheet/51359", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51586", + "spreadsheet_path": "spreadsheet/51586", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "547-18", + "spreadsheet_path": "spreadsheet/547-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "44913", + "spreadsheet_path": "spreadsheet/44913", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "45937", + "spreadsheet_path": "spreadsheet/45937", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "334-11", + "spreadsheet_path": "spreadsheet/334-11", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "177-6", + "spreadsheet_path": "spreadsheet/177-6", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "384-4", + "spreadsheet_path": "spreadsheet/384-4", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "130-9", + "spreadsheet_path": "spreadsheet/130-9", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "32789", + "spreadsheet_path": "spreadsheet/32789", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "36191", + "spreadsheet_path": "spreadsheet/36191", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "183-8", + "spreadsheet_path": "spreadsheet/183-8", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "59160", + "spreadsheet_path": "spreadsheet/59160", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56225", + "spreadsheet_path": "spreadsheet/56225", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54196", + "spreadsheet_path": "spreadsheet/54196", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "7665", + "spreadsheet_path": "spreadsheet/7665", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "38537", + "spreadsheet_path": "spreadsheet/38537", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41420", + "spreadsheet_path": "spreadsheet/41420", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56915", + "spreadsheet_path": "spreadsheet/56915", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "15380", + "spreadsheet_path": "spreadsheet/15380", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59224", + "spreadsheet_path": "spreadsheet/59224", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57590", + "spreadsheet_path": "spreadsheet/57590", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "209-30", + "spreadsheet_path": "spreadsheet/209-30", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "15387", + "spreadsheet_path": "spreadsheet/15387", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53167", + "spreadsheet_path": "spreadsheet/53167", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "34210", + "spreadsheet_path": "spreadsheet/34210", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50486", + "spreadsheet_path": "spreadsheet/50486", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50811", + "spreadsheet_path": "spreadsheet/50811", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "45738", + "spreadsheet_path": "spreadsheet/45738", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "488-14", + "spreadsheet_path": "spreadsheet/488-14", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "61-4", + "spreadsheet_path": "spreadsheet/61-4", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "38969", + "spreadsheet_path": "spreadsheet/38969", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54242", + "spreadsheet_path": "spreadsheet/54242", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "47933", + "spreadsheet_path": "spreadsheet/47933", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57989", + "spreadsheet_path": "spreadsheet/57989", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "535-20", + "spreadsheet_path": "spreadsheet/535-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "469-9", + "spreadsheet_path": "spreadsheet/469-9", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "48608", + "spreadsheet_path": "spreadsheet/48608", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55468", + "spreadsheet_path": "spreadsheet/55468", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "44266", + "spreadsheet_path": "spreadsheet/44266", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "38985", + "spreadsheet_path": "spreadsheet/38985", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59902", + "spreadsheet_path": "spreadsheet/59902", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "16511", + "spreadsheet_path": "spreadsheet/16511", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "54274", + "spreadsheet_path": "spreadsheet/54274", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59511", + "spreadsheet_path": "spreadsheet/59511", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41265", + "spreadsheet_path": "spreadsheet/41265", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "374-31", + "spreadsheet_path": "spreadsheet/374-31", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "52233", + "spreadsheet_path": "spreadsheet/52233", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "79-7", + "spreadsheet_path": "spreadsheet/79-7", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "38823", + "spreadsheet_path": "spreadsheet/38823", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "486-17", + "spreadsheet_path": "spreadsheet/486-17", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "49667", + "spreadsheet_path": "spreadsheet/49667", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50796", + "spreadsheet_path": "spreadsheet/50796", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "359-21", + "spreadsheet_path": "spreadsheet/359-21", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "50526", + "spreadsheet_path": "spreadsheet/50526", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "13284", + "spreadsheet_path": "spreadsheet/13284", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55977", + "spreadsheet_path": "spreadsheet/55977", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58723", + "spreadsheet_path": "spreadsheet/58723", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "157-4", + "spreadsheet_path": "spreadsheet/157-4", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "58904", + "spreadsheet_path": "spreadsheet/58904", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56920", + "spreadsheet_path": "spreadsheet/56920", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "41691", + "spreadsheet_path": "spreadsheet/41691", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "534-26", + "spreadsheet_path": "spreadsheet/534-26", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "341-40", + "spreadsheet_path": "spreadsheet/341-40", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "73-45", + "spreadsheet_path": "spreadsheet/73-45", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "409-45", + "spreadsheet_path": "spreadsheet/409-45", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "49857", + "spreadsheet_path": "spreadsheet/49857", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50324", + "spreadsheet_path": "spreadsheet/50324", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53117", + "spreadsheet_path": "spreadsheet/53117", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53994", + "spreadsheet_path": "spreadsheet/53994", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42198", + "spreadsheet_path": "spreadsheet/42198", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42930", + "spreadsheet_path": "spreadsheet/42930", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "84-40", + "spreadsheet_path": "spreadsheet/84-40", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "51262", + "spreadsheet_path": "spreadsheet/51262", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "236-22", + "spreadsheet_path": "spreadsheet/236-22", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "41348", + "spreadsheet_path": "spreadsheet/41348", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "15671", + "spreadsheet_path": "spreadsheet/15671", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "333-29", + "spreadsheet_path": "spreadsheet/333-29", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "38703", + "spreadsheet_path": "spreadsheet/38703", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "52050", + "spreadsheet_path": "spreadsheet/52050", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "49036", + "spreadsheet_path": "spreadsheet/49036", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50088", + "spreadsheet_path": "spreadsheet/50088", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "147-48", + "spreadsheet_path": "spreadsheet/147-48", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "51289", + "spreadsheet_path": "spreadsheet/51289", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57612", + "spreadsheet_path": "spreadsheet/57612", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59129", + "spreadsheet_path": "spreadsheet/59129", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48969", + "spreadsheet_path": "spreadsheet/48969", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "496-15", + "spreadsheet_path": "spreadsheet/496-15", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "341-14", + "spreadsheet_path": "spreadsheet/341-14", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "47827", + "spreadsheet_path": "spreadsheet/47827", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48982", + "spreadsheet_path": "spreadsheet/48982", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58032", + "spreadsheet_path": "spreadsheet/58032", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42902", + "spreadsheet_path": "spreadsheet/42902", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "353-6", + "spreadsheet_path": "spreadsheet/353-6", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "23-24", + "spreadsheet_path": "spreadsheet/23-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "39667", + "spreadsheet_path": "spreadsheet/39667", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50631", + "spreadsheet_path": "spreadsheet/50631", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "11276", + "spreadsheet_path": "spreadsheet/11276", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "510-3", + "spreadsheet_path": "spreadsheet/510-3", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "3911", + "spreadsheet_path": "spreadsheet/3911", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58687", + "spreadsheet_path": "spreadsheet/58687", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "43657", + "spreadsheet_path": "spreadsheet/43657", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55085", + "spreadsheet_path": "spreadsheet/55085", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55260", + "spreadsheet_path": "spreadsheet/55260", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "416-27", + "spreadsheet_path": "spreadsheet/416-27", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "44628", + "spreadsheet_path": "spreadsheet/44628", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "269-43", + "spreadsheet_path": "spreadsheet/269-43", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "51680", + "spreadsheet_path": "spreadsheet/51680", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "35747", + "spreadsheet_path": "spreadsheet/35747", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "547-43", + "spreadsheet_path": "spreadsheet/547-43", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "496-34", + "spreadsheet_path": "spreadsheet/496-34", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "142-19", + "spreadsheet_path": "spreadsheet/142-19", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "279-23", + "spreadsheet_path": "spreadsheet/279-23", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "280-17", + "spreadsheet_path": "spreadsheet/280-17", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "5835", + "spreadsheet_path": "spreadsheet/5835", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50683", + "spreadsheet_path": "spreadsheet/50683", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "109-21", + "spreadsheet_path": "spreadsheet/109-21", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "42216", + "spreadsheet_path": "spreadsheet/42216", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59734", + "spreadsheet_path": "spreadsheet/59734", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57232", + "spreadsheet_path": "spreadsheet/57232", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "160-6", + "spreadsheet_path": "spreadsheet/160-6", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "57117", + "spreadsheet_path": "spreadsheet/57117", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "188-39", + "spreadsheet_path": "spreadsheet/188-39", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "524-31", + "spreadsheet_path": "spreadsheet/524-31", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "12307", + "spreadsheet_path": "spreadsheet/12307", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39432", + "spreadsheet_path": "spreadsheet/39432", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57354", + "spreadsheet_path": "spreadsheet/57354", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "267-21", + "spreadsheet_path": "spreadsheet/267-21", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "178-22", + "spreadsheet_path": "spreadsheet/178-22", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54667", + "spreadsheet_path": "spreadsheet/54667", + "instruction_type": "Cell-Level Manipulation" + } +] diff --git a/data/spreadsheetbench_id_split/train/items.json b/data/spreadsheetbench_id_split/train/items.json new file mode 100644 index 0000000..bcc3376 --- /dev/null +++ b/data/spreadsheetbench_id_split/train/items.json @@ -0,0 +1,402 @@ +[ + { + "id": "32438", + "spreadsheet_path": "spreadsheet/32438", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "398-14", + "spreadsheet_path": "spreadsheet/398-14", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "47766", + "spreadsheet_path": "spreadsheet/47766", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48365", + "spreadsheet_path": "spreadsheet/48365", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "32255", + "spreadsheet_path": "spreadsheet/32255", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "10747", + "spreadsheet_path": "spreadsheet/10747", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50916", + "spreadsheet_path": "spreadsheet/50916", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "577-40", + "spreadsheet_path": "spreadsheet/577-40", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "35742", + "spreadsheet_path": "spreadsheet/35742", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "46121", + "spreadsheet_path": "spreadsheet/46121", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51090", + "spreadsheet_path": "spreadsheet/51090", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51249", + "spreadsheet_path": "spreadsheet/51249", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "82-30", + "spreadsheet_path": "spreadsheet/82-30", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "56274", + "spreadsheet_path": "spreadsheet/56274", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57445", + "spreadsheet_path": "spreadsheet/57445", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "46646", + "spreadsheet_path": "spreadsheet/46646", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "105-24", + "spreadsheet_path": "spreadsheet/105-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "6239", + "spreadsheet_path": "spreadsheet/6239", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "414-20", + "spreadsheet_path": "spreadsheet/414-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "165-23", + "spreadsheet_path": "spreadsheet/165-23", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "40892", + "spreadsheet_path": "spreadsheet/40892", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48745", + "spreadsheet_path": "spreadsheet/48745", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "32612", + "spreadsheet_path": "spreadsheet/32612", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "325-44", + "spreadsheet_path": "spreadsheet/325-44", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "262-17", + "spreadsheet_path": "spreadsheet/262-17", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "141-20", + "spreadsheet_path": "spreadsheet/141-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "52216", + "spreadsheet_path": "spreadsheet/52216", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "22-47", + "spreadsheet_path": "spreadsheet/22-47", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "55421", + "spreadsheet_path": "spreadsheet/55421", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56427", + "spreadsheet_path": "spreadsheet/56427", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "36097", + "spreadsheet_path": "spreadsheet/36097", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "32902", + "spreadsheet_path": "spreadsheet/32902", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "32023", + "spreadsheet_path": "spreadsheet/32023", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "1818", + "spreadsheet_path": "spreadsheet/1818", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "170-13", + "spreadsheet_path": "spreadsheet/170-13", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "66-24", + "spreadsheet_path": "spreadsheet/66-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "58949", + "spreadsheet_path": "spreadsheet/58949", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "42354", + "spreadsheet_path": "spreadsheet/42354", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "194-19", + "spreadsheet_path": "spreadsheet/194-19", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "31915", + "spreadsheet_path": "spreadsheet/31915", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "58499", + "spreadsheet_path": "spreadsheet/58499", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "45372", + "spreadsheet_path": "spreadsheet/45372", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "11842", + "spreadsheet_path": "spreadsheet/11842", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57558", + "spreadsheet_path": "spreadsheet/57558", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "472-15", + "spreadsheet_path": "spreadsheet/472-15", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "55060", + "spreadsheet_path": "spreadsheet/55060", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "31011", + "spreadsheet_path": "spreadsheet/31011", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "408-39", + "spreadsheet_path": "spreadsheet/408-39", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54085", + "spreadsheet_path": "spreadsheet/54085", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39903", + "spreadsheet_path": "spreadsheet/39903", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48983", + "spreadsheet_path": "spreadsheet/48983", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "108-24", + "spreadsheet_path": "spreadsheet/108-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "58484", + "spreadsheet_path": "spreadsheet/58484", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "118-50", + "spreadsheet_path": "spreadsheet/118-50", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "10452", + "spreadsheet_path": "spreadsheet/10452", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39931", + "spreadsheet_path": "spreadsheet/39931", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "3413", + "spreadsheet_path": "spreadsheet/3413", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "247-24", + "spreadsheet_path": "spreadsheet/247-24", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "56786", + "spreadsheet_path": "spreadsheet/56786", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55965", + "spreadsheet_path": "spreadsheet/55965", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "379-36", + "spreadsheet_path": "spreadsheet/379-36", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "58109", + "spreadsheet_path": "spreadsheet/58109", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "433-47", + "spreadsheet_path": "spreadsheet/433-47", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "192-22", + "spreadsheet_path": "spreadsheet/192-22", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "49333", + "spreadsheet_path": "spreadsheet/49333", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "493-18", + "spreadsheet_path": "spreadsheet/493-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54638", + "spreadsheet_path": "spreadsheet/54638", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "34033", + "spreadsheet_path": "spreadsheet/34033", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "30930", + "spreadsheet_path": "spreadsheet/30930", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "585-41", + "spreadsheet_path": "spreadsheet/585-41", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "32337", + "spreadsheet_path": "spreadsheet/32337", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55427", + "spreadsheet_path": "spreadsheet/55427", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "263-1", + "spreadsheet_path": "spreadsheet/263-1", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "254-34", + "spreadsheet_path": "spreadsheet/254-34", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "57113", + "spreadsheet_path": "spreadsheet/57113", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "57743", + "spreadsheet_path": "spreadsheet/57743", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "43589", + "spreadsheet_path": "spreadsheet/43589", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "250-20", + "spreadsheet_path": "spreadsheet/250-20", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "48080", + "spreadsheet_path": "spreadsheet/48080", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "370-43", + "spreadsheet_path": "spreadsheet/370-43", + "instruction_type": "Sheet-Level Manipulation" + } +] diff --git a/data/spreadsheetbench_id_split/val/items.json b/data/spreadsheetbench_id_split/val/items.json new file mode 100644 index 0000000..a918756 --- /dev/null +++ b/data/spreadsheetbench_id_split/val/items.json @@ -0,0 +1,202 @@ +[ + { + "id": "45635", + "spreadsheet_path": "spreadsheet/45635", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "560-12", + "spreadsheet_path": "spreadsheet/560-12", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "55049", + "spreadsheet_path": "spreadsheet/55049", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "9569", + "spreadsheet_path": "spreadsheet/9569", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "7902", + "spreadsheet_path": "spreadsheet/7902", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "227-40", + "spreadsheet_path": "spreadsheet/227-40", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "463-17", + "spreadsheet_path": "spreadsheet/463-17", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "54144", + "spreadsheet_path": "spreadsheet/54144", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "80-42", + "spreadsheet_path": "spreadsheet/80-42", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "2768", + "spreadsheet_path": "spreadsheet/2768", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "37456", + "spreadsheet_path": "spreadsheet/37456", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "12864", + "spreadsheet_path": "spreadsheet/12864", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "55979", + "spreadsheet_path": "spreadsheet/55979", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48620", + "spreadsheet_path": "spreadsheet/48620", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48588", + "spreadsheet_path": "spreadsheet/48588", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "395-36", + "spreadsheet_path": "spreadsheet/395-36", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "382-10", + "spreadsheet_path": "spreadsheet/382-10", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "59595", + "spreadsheet_path": "spreadsheet/59595", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53383", + "spreadsheet_path": "spreadsheet/53383", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48921", + "spreadsheet_path": "spreadsheet/48921", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "416-15", + "spreadsheet_path": "spreadsheet/416-15", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "47798", + "spreadsheet_path": "spreadsheet/47798", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "56563", + "spreadsheet_path": "spreadsheet/56563", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "46897", + "spreadsheet_path": "spreadsheet/46897", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "9726", + "spreadsheet_path": "spreadsheet/9726", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "50768", + "spreadsheet_path": "spreadsheet/50768", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "51-12", + "spreadsheet_path": "spreadsheet/51-12", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "31628", + "spreadsheet_path": "spreadsheet/31628", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "39046", + "spreadsheet_path": "spreadsheet/39046", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "8942", + "spreadsheet_path": "spreadsheet/8942", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "48527", + "spreadsheet_path": "spreadsheet/48527", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "59196", + "spreadsheet_path": "spreadsheet/59196", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "6698", + "spreadsheet_path": "spreadsheet/6698", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "43436", + "spreadsheet_path": "spreadsheet/43436", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "38462", + "spreadsheet_path": "spreadsheet/38462", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "402-43", + "spreadsheet_path": "spreadsheet/402-43", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "267-18", + "spreadsheet_path": "spreadsheet/267-18", + "instruction_type": "Sheet-Level Manipulation" + }, + { + "id": "37378", + "spreadsheet_path": "spreadsheet/37378", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "53647", + "spreadsheet_path": "spreadsheet/53647", + "instruction_type": "Cell-Level Manipulation" + }, + { + "id": "142-12", + "spreadsheet_path": "spreadsheet/142-12", + "instruction_type": "Sheet-Level Manipulation" + } +]