{"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/fever","name":"FEVER","full_name":"Fact Extraction and VERification","description_markdown":"FEVER is a publicly available dataset for fact extraction and verification against textual sources.\r\n\r\nIt consists of 185,445 claims manually verified against the introductory sections of Wikipedia pages and classified as SUPPORTED, REFUTED or NOTENOUGHINFO. For the first two classes, systems and annotators need to also return the combination of sentences forming the necessary evidence supporting or refuting the claim.\r\n\r\nThe claims were generated by human annotators extracting claims from Wikipedia and mutating them in a variety of ways, some of which were meaning-altering. The verification of each claim was conducted in a separate annotation process by annotators who were aware of the page but not the sentence from which original claim was\r\nextracted and thus in 31.75% of the claims more than one sentence was considered appropriate evidence. Claims require composition of evidence from multiple sentences in 16.82% of cases. Furthermore, in 12.15% of the claims, this evidence was taken from multiple pages.\r\n\r\nSource: [FEVER: a large-scale dataset for Fact Extraction and VERification](https://arxiv.org/pdf/1803.05355v3.pdf)","description_withheld":null,"homepage":"https://fever.ai/resources.html","introduced_date":"2018-03-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/fever-a-large-scale-dataset-for-fact","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","first_author":"James Thorne","url":null},"license":{"name":"Custom","url":"https://s3-eu-west-1.amazonaws.com/fever.public/license.html"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Zero-shot Text Search","url":"/task/zero-shot-text-search","datasets_with_task":"/datasets/task/zero-shot-text-search"},{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Fact Verification","url":"/task/fact-verification","datasets_with_task":"/datasets/task/fact-verification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["FEVER"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/copenlu/fever_gold_evidence","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-fever-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-evidence-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-claim-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/climate-claim-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mwong/fever-evidence-related","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/EleutherAI/fever","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/fever/fever","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":498,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-fever","task":"Question Answering","dataset_variant":"FEVER","rows":8,"metrics":["EM"],"first_row_in_archive_order":{"model":"CoA","paper":"/paper/chain-of-action-faithful-and-multimodal","metrics":{"EM":"68.9"},"code_links":[{"title":"MAGICS-LAB/Chain-of-Actions","url":"https://github.com/MAGICS-LAB/Chain-of-Actions"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/fact-verification-on-fever","task":"Fact Verification","dataset_variant":"FEVER","rows":7,"metrics":["Accuracy","FEVER"],"first_row_in_archive_order":{"model":"ProoFVer-SB","paper":"/paper/proofver-natural-logic-theorem-proving-for","metrics":{"Accuracy":"79.47","FEVER":"76.82"},"code_links":[{"title":"krishnamrith12/proofver","url":"https://github.com/krishnamrith12/proofver"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-retrieval-on-fever","task":"Text Retrieval","dataset_variant":"FEVER","rows":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","metrics":{"nDCG@10":"63.8"},"code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}]},"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":11,"of":11,"counts":{"papers_with_a_benchmark_row":11,"with_a_code_link":10,"where_syntology_ran_a_sample":5,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":5,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":5,"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/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/paper/chain-of-action-faithful-and-multimodal","slug":"chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","arxiv_id":"2403.17359","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["MAGICS-LAB/Chain-of-Actions"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chain-of-action-faithful-and-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.17359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17359"}}}},{"paper":"/paper/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["stanfordnlp/dspy"],"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/dspy-compiling-declarative-language-model#ran","syntology_url":"https://syntology.ai/paper/2310.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03714"}}}},{"paper":"/paper/measuring-and-narrowing-the-compositionality","slug":"measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","arxiv_id":"2210.03350","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/proofver-natural-logic-theorem-proving-for","slug":"proofver-natural-logic-theorem-proving-for","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","date":"2021-08-25","arxiv_id":"2108.11357","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}}}},{"paper":"/paper/kernel-graph-attention-network-for-fact","slug":"kernel-graph-attention-network-for-fact","title":"Fine-grained Fact Verification with Kernel Graph Attention Network","date":"2019-10-22","arxiv_id":"1910.09796","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["thunlp/KernelGAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/kernel-graph-attention-network-for-fact#ran","syntology_url":"https://syntology.ai/paper/1910.09796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09796"}}}},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","slug":"reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","arxiv_id":"1909.03745","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gear-graph-based-evidence-aggregating-and-1","slug":"gear-graph-based-evidence-aggregating-and-1","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","date":"2019-07-22","arxiv_id":"1908.01843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":22,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":12,"samples_ran_instrument_failed":3,"samples_unverified":7,"pointer_only_for_licence":0,"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}}}},{"paper":"/paper/chain-of-action-faithful-and-multimodal","slug":"chain-of-action-faithful-and-multimodal","title":"Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models","date":"2024-03-26","arxiv_id":"2403.17359","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["MAGICS-LAB/Chain-of-Actions"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chain-of-action-faithful-and-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.17359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17359"}}}},{"paper":"/paper/dspy-compiling-declarative-language-model","slug":"dspy-compiling-declarative-language-model","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","date":"2023-10-05","arxiv_id":"2310.03714","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":0,"official":{"repos":["stanfordnlp/dspy"],"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/dspy-compiling-declarative-language-model#ran","syntology_url":"https://syntology.ai/paper/2310.03714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03714"}}}},{"paper":"/paper/measuring-and-narrowing-the-compositionality","slug":"measuring-and-narrowing-the-compositionality","title":"Measuring and Narrowing the Compositionality Gap in Language Models","date":"2022-10-07","arxiv_id":"2210.03350","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/paragraph-based-transformer-pre-training-for","slug":"paragraph-based-transformer-pre-training-for","title":"Paragraph-based Transformer Pre-training for Multi-Sentence Inference","date":"2022-05-02","arxiv_id":"2205.01228","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/proofver-natural-logic-theorem-proving-for","slug":"proofver-natural-logic-theorem-proving-for","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","date":"2021-08-25","arxiv_id":"2108.11357","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}}}},{"paper":"/paper/kernel-graph-attention-network-for-fact","slug":"kernel-graph-attention-network-for-fact","title":"Fine-grained Fact Verification with Kernel Graph Attention Network","date":"2019-10-22","arxiv_id":"1910.09796","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["thunlp/KernelGAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/kernel-graph-attention-network-for-fact#ran","syntology_url":"https://syntology.ai/paper/1910.09796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09796"}}}},{"paper":"/paper/reasoning-over-semantic-level-graph-for-fact","slug":"reasoning-over-semantic-level-graph-for-fact","title":"Reasoning Over Semantic-Level Graph for Fact Checking","date":"2019-09-09","arxiv_id":"1909.03745","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gear-graph-based-evidence-aggregating-and-1","slug":"gear-graph-based-evidence-aggregating-and-1","title":"GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification","date":"2019-07-22","arxiv_id":"1908.01843","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/language-models-are-unsupervised-multitask","slug":"language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"rows_on_this_dataset":1,"code_links":21,"syntology":null}],"papers_where_code_ran":5,"papers_where_code_ran_first_page":"/dataset/fever/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/fever/papers/ran/1","json":"/dataset/fever/papers/ran/1.json","rows":5}],"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":5,"samples_harvested":50,"samples_ran":36,"samples_constructed":3,"samples_ran_checked":29,"samples_ran_instrument_failed":7,"samples_unverified":14,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":5,"papers_with_a_run_with_no_instrument_failure":5,"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":4,"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/fact-verification-on-fever","since_archive":"/sota/fact-verification-on-fever#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/text-retrieval-on-fever","since_archive":"/sota/text-retrieval-on-fever#since-judged","papers_judged":1,"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":"423df0be63f71948eb27e46b9dabf5fba836a1f7a972b2736486facacd3258d7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}