{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/openbookqa","name":"OpenBookQA","full_name":"OBQA","description_markdown":"**OpenBookQA** is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject. It consists of 5,957 multiple-choice elementary-level science questions (4,957 train, 500 dev, 500 test), which probe the understanding of a small “book” of 1,326 core science facts and the application of these facts to novel situations. For training, the dataset includes a mapping from each question to the core science fact it was designed to probe. Answering OpenBookQA questions requires additional broad common knowledge, not contained in the book. The questions, by design, are answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm.\r\nAdditionally, the dataset includes a collection of 5,167 crowd-sourced common knowledge facts, and an expanded version of the train/dev/test questions where each question is associated with its originating core fact, a human accuracy score, a clarity score, and an anonymized crowd-worker ID.\r\n\r\nSource: [https://allenai.org/data/open-book-qa](https://allenai.org/data/open-book-qa)\r\nImage Source: [https://arxiv.org/pdf/1809.02789.pdf](https://arxiv.org/pdf/1809.02789.pdf)","description_withheld":null,"homepage":"https://allenai.org/data/open-book-qa","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/can-a-suit-of-armor-conduct-electricity-a-new","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","first_author":"Todor Mihaylov","url":null},"license":{"name":"Custom","url":"https://github.com/allenai/OpenBookQA"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OpenBookQA","OBQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/allenai/openbookqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/openbookqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bobox/OpenbookQA-4ST","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/attacker-exploiting-everyone/test-dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bobox/openbookqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Kaggle/kaggle-api","url":"https://www.kaggle.com/datasets/konradb/chatbot-dataset-openbookqa","frameworks":[]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/openbookqa","frameworks":["tf","jax"]}],"num_papers_in_archive":635,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-openbookqa","task":"Question Answering","dataset_variant":"OpenBookQA","rows":45,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 + knowledge base","paper":null,"metrics":{"Accuracy":"95.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-obqa","task":"Question Answering","dataset_variant":"OBQA","rows":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FLAN 137B (zero-shot)","paper":"/paper/finetuned-language-models-are-zero-shot","metrics":{"Accuracy":"78.4"},"code_links":[{"title":"hiyouga/llama-efficient-tuning","url":"https://github.com/hiyouga/llama-efficient-tuning"},{"title":"bigcode-project/starcoder","url":"https://github.com/bigcode-project/starcoder"},{"title":"bigscience-workshop/promptsource","url":"https://github.com/bigscience-workshop/promptsource"},{"title":"google-research/flan","url":"https://github.com/google-research/flan"},{"title":"ukplab/arxiv2025-inherent-limits-plms","url":"https://github.com/ukplab/arxiv2025-inherent-limits-plms"},{"title":"openbiolink/promptsource","url":"https://github.com/openbiolink/promptsource"},{"title":"MS-P3/code6","url":"https://github.com/MS-P3/code6/tree/main/finetune"},{"title":"hojjat-mokhtarabadi/promptsource","url":"https://github.com/hojjat-mokhtarabadi/promptsource"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-openbookqa","task":"Text Generation","dataset_variant":"OpenBookQA","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":18,"of":18,"counts":{"papers_with_a_benchmark_row":18,"with_a_code_link":14,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":18,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}}}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/grapeqa-graph-augmentation-and-pruning-to","slug":"grapeqa-graph-augmentation-and-pruning-to","title":"GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering","date":"2023-03-22","arxiv_id":"2303.12320","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/clues-before-answers-generation-enhanced","slug":"clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","arxiv_id":"2205.00274","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["nju-websoft/genmc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clues-before-answers-generation-enhanced#ran","syntology_url":"https://syntology.ai/paper/2205.00274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00274"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/gnn-is-a-counter-revisiting-gnn-for-question","slug":"gnn-is-a-counter-revisiting-gnn-for-question","title":"GNN is a Counter? Revisiting GNN for Question Answering","date":"2021-10-07","arxiv_id":"2110.03192","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":17,"pointer_only_for_licence":5,"official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qa-gnn-reasoning-with-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2104.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06378"}}}},{"paper":"/paper/fusing-context-into-knowledge-graph-for","slug":"fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}}}},{"paper":"/paper/careful-selection-of-knowledge-to-solve-open","slug":"careful-selection-of-knowledge-to-solve-open","title":"Careful Selection of Knowledge to solve Open Book Question Answering","date":"2019-07-24","arxiv_id":"1907.10738","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/can-a-suit-of-armor-conduct-electricity-a-new","slug":"can-a-suit-of-armor-conduct-electricity-a-new","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","date":"2018-09-08","arxiv_id":"1809.02789","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["allenai/arc-solvers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-a-suit-of-armor-conduct-electricity-a-new#ran","syntology_url":"https://syntology.ai/paper/1809.02789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02789"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":6,"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}}}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","slug":"lamini-lm-a-diverse-herd-of-distilled-models","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","date":"2023-04-27","arxiv_id":"2304.14402","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/grapeqa-graph-augmentation-and-pruning-to","slug":"grapeqa-graph-augmentation-and-pruning-to","title":"GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering","date":"2023-03-22","arxiv_id":"2303.12320","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/large-language-models-can-self-improve","slug":"large-language-models-can-self-improve","title":"Large Language Models Can Self-Improve","date":"2022-10-20","arxiv_id":"2210.11610","rows_on_this_dataset":6,"code_links":0,"syntology":null},{"paper":"/paper/clues-before-answers-generation-enhanced","slug":"clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","arxiv_id":"2205.00274","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["nju-websoft/genmc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clues-before-answers-generation-enhanced#ran","syntology_url":"https://syntology.ai/paper/2205.00274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00274"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/gnn-is-a-counter-revisiting-gnn-for-question","slug":"gnn-is-a-counter-revisiting-gnn-for-question","title":"GNN is a Counter? Revisiting GNN for Question Answering","date":"2021-10-07","arxiv_id":"2110.03192","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/qa-gnn-reasoning-with-language-models-and","slug":"qa-gnn-reasoning-with-language-models-and","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","date":"2021-04-13","arxiv_id":"2104.06378","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":25,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":0,"samples_unverified":17,"pointer_only_for_licence":5,"official":{"repos":["michiyasunaga/qagnn","worksheets.codalab.org/worksheets/0xf215deb05edf44a2ac353c711f52a25f"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":13,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qa-gnn-reasoning-with-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2104.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06378"}}}},{"paper":"/paper/fusing-context-into-knowledge-graph-for","slug":"fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":2,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","slug":"unifiedqa-crossing-format-boundaries-with-a","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","date":"2020-05-02","arxiv_id":"2005.00700","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":4,"samples_constructed":3,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}}}},{"paper":"/paper/careful-selection-of-knowledge-to-solve-open","slug":"careful-selection-of-knowledge-to-solve-open","title":"Careful Selection of Knowledge to solve Open Book Question Answering","date":"2019-07-24","arxiv_id":"1907.10738","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/can-a-suit-of-armor-conduct-electricity-a-new","slug":"can-a-suit-of-armor-conduct-electricity-a-new","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","date":"2018-09-08","arxiv_id":"1809.02789","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["allenai/arc-solvers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/can-a-suit-of-armor-conduct-electricity-a-new#ran","syntology_url":"https://syntology.ai/paper/1809.02789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.02789"}}}}],"papers_where_code_ran":9,"papers_where_code_ran_first_page":"/dataset/openbookqa/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/openbookqa/papers/ran/1","json":"/dataset/openbookqa/papers/ran/1.json","rows":9}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":10,"samples_harvested":224,"samples_ran":144,"samples_constructed":28,"samples_ran_checked":110,"samples_ran_instrument_failed":34,"samples_unverified":80,"pointer_only_for_licence":23,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":9,"papers_with_a_run_with_no_instrument_failure":9,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":31,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/question-answering-on-openbookqa","since_archive":"/sota/question-answering-on-openbookqa#since-judged","papers_judged":22,"placed":1},{"leaderboard":"/sota/question-answering-on-obqa","since_archive":"/sota/question-answering-on-obqa#since-judged","papers_judged":25,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"92e490ee8ca0b9b74c921f729929e060a11e1b9d95f2177b58918ffd0d099b3f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}