{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/fever-a-large-scale-dataset-for-fact","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","arxiv_id":"1803.05355","date":"2018-03-14","proceeding":"NAACL 2018 6","authors":["James Thorne","Andreas Vlachos","Christos Christodoulopoulos","Arpit Mittal"],"abstract":"In this paper we introduce a new publicly available dataset for verification\nagainst textual sources, FEVER: Fact Extraction and VERification. It consists\nof 185,445 claims generated by altering sentences extracted from Wikipedia and\nsubsequently verified without knowledge of the sentence they were derived from.\nThe claims are classified as Supported, Refuted or NotEnoughInfo by annotators\nachieving 0.6841 in Fleiss $\\kappa$. For the first two classes, the annotators\nalso recorded the sentence(s) forming the necessary evidence for their\njudgment. To characterize the challenge of the dataset presented, we develop a\npipeline approach and compare it to suitably designed oracles. The best\naccuracy we achieve on labeling a claim accompanied by the correct evidence is\n31.87%, while if we ignore the evidence we achieve 50.91%. Thus we believe that\nFEVER is a challenging testbed that will help stimulate progress on claim\nverification against textual sources.","url_abs":"http://arxiv.org/abs/1803.05355v3","url_pdf":"http://arxiv.org/pdf/1803.05355v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fever-a-large-scale-dataset-for-fact","repo_url":"https://github.com/awslabs/fever","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fever-a-large-scale-dataset-for-fact","repo_url":"https://github.com/sheffieldnlp/fever-baselines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fever-a-large-scale-dataset-for-fact","repo_url":"https://github.com/bwxu/FNC-SNLI-FEVER-Domain-Adaptation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"fever-a-large-scale-dataset-for-fact","repo_url":"https://github.com/marinsokol5/Fact-checking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fever-a-large-scale-dataset-for-fact","repo_url":"https://github.com/sridharanirudh/tmpFever","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"claim-verification","task_name":"Claim Verification"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"fever","name":"FEVER","full_name":"Fact Extraction and VERification"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.05355","atlas_url":"https://app.syntology.ai/?focus=1803.05355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.05355"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sridharanirudh/tmpFever","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bwxu/FNC-SNLI-FEVER-Domain-Adaptation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marinsokol5/Fact-checking","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awslabs/fever","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sheffieldnlp/fever-baselines","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"14a425772402eaa2","entry":"get_annotations_old","repo":"awslabs/fever","repo_kind":"official","path":"fever-annotations-platform/src/annotation/flask_services/annotation_service.py","file_url":"https://github.com/awslabs/fever/blob/HEAD/fever-annotations-platform/src/annotation/flask_services/annotation_service.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14a425772402eaa2"}},{"code_sha256_prefix":"4bdff8826f3fa4c5","entry":"get_strings_from_dynamodb_row","repo":"awslabs/fever","repo_kind":"official","path":"fever-annotations-platform/src/annotation/flask_services/annotation_service.py","file_url":"https://github.com/awslabs/fever/blob/HEAD/fever-annotations-platform/src/annotation/flask_services/annotation_service.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4bdff8826f3fa4c5"}},{"code_sha256_prefix":"f9ac1bc97b28a8bc","entry":"prepare_item","repo":"awslabs/fever","repo_kind":"official","path":"fever-annotations-platform/src/annotation/flask_services/annotation_service.py","file_url":"https://github.com/awslabs/fever/blob/HEAD/fever-annotations-platform/src/annotation/flask_services/annotation_service.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9ac1bc97b28a8bc"}},{"code_sha256_prefix":"65dbeb9236d5226e","entry":"preprocess","repo":"sheffieldnlp/fever-baselines","repo_kind":"official","path":"src/retrieval/filter_lists.py","file_url":"https://github.com/sheffieldnlp/fever-baselines/blob/HEAD/src/retrieval/filter_lists.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"65dbeb9236d5226e"}},{"code_sha256_prefix":"98f933fc5f35ba11","entry":"preprocess","repo":"sheffieldnlp/fever-baselines","repo_kind":"official","path":"src/retrieval/filter_uninformative.py","file_url":"https://github.com/sheffieldnlp/fever-baselines/blob/HEAD/src/retrieval/filter_uninformative.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98f933fc5f35ba11"}},{"code_sha256_prefix":"1e65673973a229c2","entry":"uninformative","repo":"sheffieldnlp/fever-baselines","repo_kind":"official","path":"src/retrieval/filter_lists.py","file_url":"https://github.com/sheffieldnlp/fever-baselines/blob/HEAD/src/retrieval/filter_lists.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e65673973a229c2"}},{"code_sha256_prefix":"c15ca7cd0e69054f","entry":"uninformative","repo":"sheffieldnlp/fever-baselines","repo_kind":"official","path":"src/retrieval/filter_uninformative.py","file_url":"https://github.com/sheffieldnlp/fever-baselines/blob/HEAD/src/retrieval/filter_uninformative.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c15ca7cd0e69054f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}