{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DZCA3JFK4WEHMDGFYVGIQF4RS","short_pith_number":"pith:5DZCA3JF","schema_version":"1.0","canonical_sha256":"e8f2206d25572c43b0662e2a6440bc8cab33768cc58b04c9bfbbec21e8327d3e","source":{"kind":"arxiv","id":"2410.22257","version":2},"attestation_state":"computed","paper":{"title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Farima Fatahi Bayat, Lechen Zhang, Lu Wang, Sheza Munir","submitted_at":"2024-10-29T17:19:56Z","abstract_excerpt":"The rapid adoption of language models (LMs) across diverse applications has raised concerns about their factuality, i.e., their consistency with real-world facts. We first present VERIFY (Verification and Evidence RetrIeval for FactualitY evaluation), a pipeline to evaluate LMs' factuality in real-world user interactions. VERIFY considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable based on Web-retrieved evidence. Importantly, factuality judgment by VERIFY correlates better with human evaluations than existing methods. Using"},"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":"2410.22257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:19:56Z","cross_cats_sorted":[],"title_canon_sha256":"777e29fb988cab77026514a5836b05ee036b7416f28677dd1b8167386b6474aa","abstract_canon_sha256":"d2705265c3cc8ce4c7a4093aca2ee77b47719a0ad33a1819504b2b611c2d8293"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:25.693269Z","signature_b64":"pfQHUqO+K1TSNyp292vzsESOLve4mJ3S5GHmB2y8G8WhIF0Ev/T7eEI42RHKPS6m0B85ZZV7LVRgSQ3zdTiYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f2206d25572c43b0662e2a6440bc8cab33768cc58b04c9bfbbec21e8327d3e","last_reissued_at":"2026-07-05T09:58:25.692784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:25.692784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Farima Fatahi Bayat, Lechen Zhang, Lu Wang, Sheza Munir","submitted_at":"2024-10-29T17:19:56Z","abstract_excerpt":"The rapid adoption of language models (LMs) across diverse applications has raised concerns about their factuality, i.e., their consistency with real-world facts. We first present VERIFY (Verification and Evidence RetrIeval for FactualitY evaluation), a pipeline to evaluate LMs' factuality in real-world user interactions. VERIFY considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable based on Web-retrieved evidence. Importantly, factuality judgment by VERIFY correlates better with human evaluations than existing methods. Using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22257","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/2410.22257/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":"2410.22257","created_at":"2026-07-05T09:58:25.692870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22257v2","created_at":"2026-07-05T09:58:25.692870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22257","created_at":"2026-07-05T09:58:25.692870+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DZCA3JFK4WE","created_at":"2026-07-05T09:58:25.692870+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DZCA3JFK4WEHMDG","created_at":"2026-07-05T09:58:25.692870+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DZCA3JF","created_at":"2026-07-05T09:58:25.692870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS","json":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS.json","graph_json":"https://pith.science/api/pith-number/5DZCA3JFK4WEHMDGFYVGIQF4RS/graph.json","events_json":"https://pith.science/api/pith-number/5DZCA3JFK4WEHMDGFYVGIQF4RS/events.json","paper":"https://pith.science/paper/5DZCA3JF"},"agent_actions":{"view_html":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS","download_json":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS.json","view_paper":"https://pith.science/paper/5DZCA3JF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22257&json=true","fetch_graph":"https://pith.science/api/pith-number/5DZCA3JFK4WEHMDGFYVGIQF4RS/graph.json","fetch_events":"https://pith.science/api/pith-number/5DZCA3JFK4WEHMDGFYVGIQF4RS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS/action/storage_attestation","attest_author":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS/action/author_attestation","sign_citation":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS/action/citation_signature","submit_replication":"https://pith.science/pith/5DZCA3JFK4WEHMDGFYVGIQF4RS/action/replication_record"}},"created_at":"2026-07-05T09:58:25.692870+00:00","updated_at":"2026-07-05T09:58:25.692870+00:00"}