{"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":"/task/science-question-answering","name":"Science Question Answering","slug":"science-question-answering","description_markdown":"Image credit: [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://paperswithcode.com/paper/learn-to-explain-multimodal-reasoning-via)","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":23,"papers_with_code":15,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/science-question-answering-on-scienceqa","slug":"science-question-answering-on-scienceqa","dataset":"ScienceQA","dataset_url":"/dataset/scienceqa","rows_in_archive":10,"metrics":["Avg. Accuracy","Natural Science","Social Science","Language Science","Text Context","Image Context","No Context","Grades 1-6","Grades 7-12"],"first_row_in_archive_order":{"model":"MC-CoT F-Large","paper_title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","paper_url":"/paper/boosting-the-power-of-small-multimodal","paper_date":"2023-11-23","arxiv_id":"2311.14109","code_links":[{"title":"chengtan9907/mc-cot","url":"https://github.com/chengtan9907/mc-cot"}],"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-the-power-of-small-multimodal#ran","syntology_url":"https://syntology.ai/paper/2311.14109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14109"}},"official":{"repos":["chengtan9907/mc-cot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/scienceqa","name":"ScienceQA","full_name":"Science Question Answering","num_papers_in_archive":339},{"url":"/dataset/frenchmedmcqa","name":"FrenchMedMCQA","full_name":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","num_papers_in_archive":6},{"url":"/dataset/semopenalex","name":"SemOpenAlex","full_name":"","num_papers_in_archive":6},{"url":"/dataset/biofuelqr","name":"BioFuelQR","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":23,"of":23,"of_with_code":15,"tagged_in_all":23,"counts":{"archive_papers_tagged":23,"with_a_code_link":15,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":23,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":3,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/chat-univi-unified-visual-representation","slug":"chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","date":"2023-11-14","arxiv_id":"2311.08046","repositories_listed":4,"syntology":null},{"url":"/paper/multimodal-chain-of-thought-reasoning-in","slug":"multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","arxiv_id":"2302.00923","repositories_listed":3,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multimodal-chain-of-thought-reasoning-in#ran","syntology_url":"https://syntology.ai/paper/2302.00923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00923"}},"official":{"repos":["amazon-science/mm-cot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-causalgpt-a-multi-agent-approach-for","slug":"towards-causalgpt-a-multi-agent-approach-for","title":"Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs","date":"2023-08-23","arxiv_id":"2308.11914","repositories_listed":2,"syntology":null},{"url":"/paper/sciqag-a-framework-for-auto-generated","slug":"sciqag-a-framework-for-auto-generated","title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation","date":"2024-05-16","arxiv_id":"2405.09939","repositories_listed":1,"syntology":null},{"url":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}},"official":null}},{"url":"/paper/honeybee-locality-enhanced-projector-for","slug":"honeybee-locality-enhanced-projector-for","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","date":"2023-12-11","arxiv_id":"2312.06742","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/honeybee-locality-enhanced-projector-for#ran","syntology_url":"https://syntology.ai/paper/2312.06742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06742"}},"official":{"repos":["kakaobrain/honeybee"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosting-the-power-of-small-multimodal","slug":"boosting-the-power-of-small-multimodal","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","date":"2023-11-23","arxiv_id":"2311.14109","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/boosting-the-power-of-small-multimodal#ran","syntology_url":"https://syntology.ai/paper/2311.14109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14109"}},"official":{"repos":["chengtan9907/mc-cot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-interpretable-cross-modal","slug":"a-survey-on-interpretable-cross-modal","title":"A Survey on Interpretable Cross-modal Reasoning","date":"2023-09-05","arxiv_id":"2309.01955","repositories_listed":1,"syntology":null},{"url":"/paper/cheap-and-quick-efficient-vision-language","slug":"cheap-and-quick-efficient-vision-language","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","date":"2023-05-24","arxiv_id":"2305.15023","repositories_listed":1,"syntology":null},{"url":"/paper/t-sciq-teaching-multimodal-chain-of-thought","slug":"t-sciq-teaching-multimodal-chain-of-thought","title":"T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering","date":"2023-05-05","arxiv_id":"2305.03453","repositories_listed":1,"syntology":null},{"url":"/paper/two-is-better-than-many-binary-classification","slug":"two-is-better-than-many-binary-classification","title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","date":"2022-10-29","arxiv_id":"2210.16495","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}},"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/learn-to-explain-multimodal-reasoning-via","slug":"learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","arxiv_id":"2209.09513","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learn-to-explain-multimodal-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2209.09513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09513"}},"official":{"repos":["lupantech/ScienceQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/exploiting-reasoning-chains-for-multi-hop","slug":"exploiting-reasoning-chains-for-multi-hop","title":"Exploiting Reasoning Chains for Multi-hop Science Question Answering","date":"2021-09-07","arxiv_id":"2109.02905","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-semantic-graph-construction-and","slug":"dynamic-semantic-graph-construction-and","title":"Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering","date":"2021-05-25","arxiv_id":"2105.11776","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/dynamic-semantic-graph-construction-and#ran","syntology_url":"https://syntology.ai/paper/2105.11776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.11776"}},"official":{"repos":["wwxu21/AMR-SG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unification-based-reconstruction-of","slug":"unification-based-reconstruction-of","title":"Unification-based Reconstruction of Multi-hop Explanations for Science Questions","date":"2020-03-31","arxiv_id":"2004.00061","repositories_listed":1,"syntology":null},{"url":null,"slug":"2408-01107","title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning","date":"2024-08-02","arxiv_id":"2408.01107","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-answer-validation-using-text","title":"Automated Answer Validation using Text Similarity","date":"2024-01-13","arxiv_id":"2401.08688","repositories_listed":0,"syntology":null},{"url":null,"slug":"atlantic-structure-aware-retrieval-augmented","title":"ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science","date":"2023-11-21","arxiv_id":"2311.12289","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-facts-for-explaining-answers-to","title":"Ranking Facts for Explaining Answers to Elementary Science Questions","date":"2021-10-18","arxiv_id":"2110.09036","repositories_listed":0,"syntology":null},{"url":null,"slug":"encoding-explanatory-knowledge-for-zero-shot","title":"Encoding Explanatory Knowledge for Zero-shot Science Question Answering","date":"2021-05-12","arxiv_id":"2105.05737","repositories_listed":0,"syntology":null},{"url":null,"slug":"explanationlp-abductive-reasoning-for","title":"ExplanationLP: Abductive Reasoning for Explainable Science Question Answering","date":"2020-10-25","arxiv_id":"2010.13128","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-hop-inference-for-sentence-level","title":"Multi-hop Inference for Sentence-level TextGraphs: How Challenging is Meaningfully Combining Information for Science Question Answering?","date":"2018-05-29","arxiv_id":"1805.11267","repositories_listed":0,"syntology":null},{"url":null,"slug":"science-question-answering-using","title":"Science Question Answering using Instructional Materials","date":"2016-02-13","arxiv_id":"1602.04375","repositories_listed":0,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":18,"papers_placed":0,"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/science-question-answering-on-scienceqa","since_archive":"/sota/science-question-answering-on-scienceqa#since-judged","papers_judged":18,"placed":0}]},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/task/science-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/science-question-answering/papers/ran/1","json":"/task/science-question-answering/papers/ran/1.json","rows":7}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"31cb20aed71d86b30a344a617d06d0449a158d4f814067db928ce8c96c0742ba","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}