{"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/evidence-selection","name":"Evidence Selection","slug":"evidence-selection","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":22,"papers_with_code":11,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/qasper","name":"QASPER","full_name":"","num_papers_in_archive":102}],"subtasks":[],"parent_tasks":[],"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":22,"of":22,"of_with_code":11,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":11,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/chain-of-discussion-a-multi-model-framework","slug":"chain-of-discussion-a-multi-model-framework","title":"Chain-of-Discussion: A Multi-Model Framework for Complex Evidence-Based Question Answering","date":"2024-02-26","arxiv_id":"2402.16313","repositories_listed":2,"syntology":null},{"url":"/paper/evidence-based-verification-for-real-world","slug":"evidence-based-verification-for-real-world","title":"AmbiFC: Fact-Checking Ambiguous Claims with Evidence","date":"2021-04-01","arxiv_id":"2104.00640","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evidence-based-verification-for-real-world#ran","syntology_url":"https://syntology.ai/paper/2104.00640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00640"}},"official":{"repos":["CambridgeNLIP/verification-real-world-info-needs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/benchmarking-retrieval-augmented-multimomal","slug":"benchmarking-retrieval-augmented-multimomal","title":"Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering","date":"2025-05-22","arxiv_id":"2505.16470","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/benchmarking-retrieval-augmented-multimomal#ran","syntology_url":"https://syntology.ai/paper/2505.16470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16470"}},"official":{"repos":["mmdocrag/mmdocrag"],"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/halu-j-critique-based-hallucination-judge","slug":"halu-j-critique-based-hallucination-judge","title":"Halu-J: Critique-Based Hallucination Judge","date":"2024-07-17","arxiv_id":"2407.12943","repositories_listed":1,"syntology":null},{"url":"/paper/are-large-language-models-really-good-logical","slug":"are-large-language-models-really-good-logical","title":"Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond","date":"2023-06-16","arxiv_id":"2306.09841","repositories_listed":1,"syntology":null},{"url":"/paper/slidevqa-a-dataset-for-document-visual","slug":"slidevqa-a-dataset-for-document-visual","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","date":"2023-01-12","arxiv_id":"2301.04883","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-global-structural-information-in","slug":"capturing-global-structural-information-in","title":"Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network","date":"2022-10-11","arxiv_id":"2210.05499","repositories_listed":1,"syntology":null},{"url":"/paper/evidence-selection-as-a-token-level","slug":"evidence-selection-as-a-token-level","title":"Evidence Selection as a Token-Level Prediction Task","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-of-information-seeking-questions","slug":"a-dataset-of-information-seeking-questions","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","date":"2021-05-07","arxiv_id":"2105.03011","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":0,"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/a-dataset-of-information-seeking-questions#ran","syntology_url":"https://syntology.ai/paper/2105.03011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03011"}},"official":{"repos":["allenai/qasper-led-baseline"],"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/unsupervised-alignment-based-iterative","slug":"unsupervised-alignment-based-iterative","title":"Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering","date":"2020-05-04","arxiv_id":"2005.01218","repositories_listed":1,"syntology":null},{"url":"/paper/melu-meta-learned-user-preference-estimator","slug":"melu-meta-learned-user-preference-estimator","title":"MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation","date":"2019-07-31","arxiv_id":"1908.00413","repositories_listed":1,"syntology":null},{"url":null,"slug":"sara-selective-and-adaptive-retrieval","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","date":"2025-07-08","arxiv_id":"2507.05633","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aware-iterative-retrieval-for-multi","title":"Knowledge-Aware Iterative Retrieval for Multi-Agent Systems","date":"2025-03-17","arxiv_id":"2503.13275","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-large-language-models-with-domain","title":"Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology","date":"2024-09-20","arxiv_id":"2409.13902","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-knowledge-sources-for-open-domain","title":"Comparing Knowledge Sources for Open-Domain Scientific Claim Verification","date":"2024-02-05","arxiv_id":"2402.02844","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-we-need-language-specific-fact-checking","title":"Do We Need Language-Specific Fact-Checking Models? The Case of Chinese","date":"2024-01-27","arxiv_id":"2401.15498","repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2023-task-7-multi-evidence-natural","title":"SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data","date":"2023-05-04","arxiv_id":"2305.02993","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-the-wild-video-question-answering","title":"In-the-Wild Video Question Answering","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/wildqa-in-the-wild-video-question-answering","slug":"wildqa-in-the-wild-video-question-answering","title":"WildQA: In-the-Wild Video Question Answering","date":"2022-09-14","arxiv_id":"2209.06650","repositories_listed":0,"syntology":null},{"url":null,"slug":"product-answer-generation-from-heterogeneous-1","title":"Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"product-answer-generation-from-heterogeneous","title":"Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"complementary-evidence-identification-in-open","title":"Complementary Evidence Identification in Open-Domain Question Answering","date":"2021-03-22","arxiv_id":"2103.11643","repositories_listed":0,"syntology":null}],"syntology_records":3,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/task/evidence-selection/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/evidence-selection/papers/ran/1","json":"/task/evidence-selection/papers/ran/1.json","rows":3}],"description_links":{"kept":0,"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":"b8f9bceffbb88efd443f777b953d236f6dc1dc47d5cec602cf384d90e580b295","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}