{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MYCDIMJ36UFKWFAD3BJIOOWMS2","short_pith_number":"pith:MYCDIMJ3","schema_version":"1.0","canonical_sha256":"660434313bf50aab1403d852873acc96b315a3a0e9f814534d6db352533cc9fb","source":{"kind":"arxiv","id":"2502.10855","version":2},"attestation_state":"computed","paper":{"title":"Towards Effective Extraction and Evaluation of Factual Claims","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dasha Metropolitansky, Jonathan Larson","submitted_at":"2025-02-15T16:58:05Z","abstract_excerpt":"A common strategy for fact-checking long-form content generated by Large Language Models (LLMs) is extracting simple claims that can be verified independently. Since inaccurate or incomplete claims compromise fact-checking results, ensuring claim quality is critical. However, the lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. To address this gap, we propose a framework for evaluating claim extraction in the context of fact-checking along with automated, scalable, and replicable methods for applying this framework, including novel appr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.10855","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T16:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"90aafe48815ebe81baa375c3ecbe4d27869fdc7c2082faaf752f13483ecbb2de","abstract_canon_sha256":"5d7b91faf9368758ca94f23d80ab00c15132d6f8fbec79d0fa21d91415d58cf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:23.582186Z","signature_b64":"d7ZRDDXqpLH0gqxbDV2PbkmymopykyE2OUBOTsQ2Rn81Lna/B/yJIZJ9H7JLSppjPmTp3ITQ0gQqffK54Mn9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660434313bf50aab1403d852873acc96b315a3a0e9f814534d6db352533cc9fb","last_reissued_at":"2026-07-05T11:17:23.581373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:23.581373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Effective Extraction and Evaluation of Factual Claims","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dasha Metropolitansky, Jonathan Larson","submitted_at":"2025-02-15T16:58:05Z","abstract_excerpt":"A common strategy for fact-checking long-form content generated by Large Language Models (LLMs) is extracting simple claims that can be verified independently. Since inaccurate or incomplete claims compromise fact-checking results, ensuring claim quality is critical. However, the lack of a standardized evaluation framework impedes assessment and comparison of claim extraction methods. To address this gap, we propose a framework for evaluating claim extraction in the context of fact-checking along with automated, scalable, and replicable methods for applying this framework, including novel appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10855","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.10855/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.10855","created_at":"2026-07-05T11:17:23.581481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10855v2","created_at":"2026-07-05T11:17:23.581481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10855","created_at":"2026-07-05T11:17:23.581481+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYCDIMJ36UFK","created_at":"2026-07-05T11:17:23.581481+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYCDIMJ36UFKWFAD","created_at":"2026-07-05T11:17:23.581481+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYCDIMJ3","created_at":"2026-07-05T11:17:23.581481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20050","citing_title":"Language Mutations Sustain the Persistences of Conspiracy Theories on Social Media","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01495","citing_title":"FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08082","citing_title":"From Binary Groundedness to Support Relations: Towards a Reader-Centred Taxonomy for Comprehension of AI Output","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2","json":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2.json","graph_json":"https://pith.science/api/pith-number/MYCDIMJ36UFKWFAD3BJIOOWMS2/graph.json","events_json":"https://pith.science/api/pith-number/MYCDIMJ36UFKWFAD3BJIOOWMS2/events.json","paper":"https://pith.science/paper/MYCDIMJ3"},"agent_actions":{"view_html":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2","download_json":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2.json","view_paper":"https://pith.science/paper/MYCDIMJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10855&json=true","fetch_graph":"https://pith.science/api/pith-number/MYCDIMJ36UFKWFAD3BJIOOWMS2/graph.json","fetch_events":"https://pith.science/api/pith-number/MYCDIMJ36UFKWFAD3BJIOOWMS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2/action/storage_attestation","attest_author":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2/action/author_attestation","sign_citation":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2/action/citation_signature","submit_replication":"https://pith.science/pith/MYCDIMJ36UFKWFAD3BJIOOWMS2/action/replication_record"}},"created_at":"2026-07-05T11:17:23.581481+00:00","updated_at":"2026-07-05T11:17:23.581481+00:00"}