{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DU4WN2XHMNZV6ROKUBJRTBE2RE","short_pith_number":"pith:DU4WN2XH","schema_version":"1.0","canonical_sha256":"1d3966eae763735f45caa05319849a891ada092b9debb811f063084f3b0451b8","source":{"kind":"arxiv","id":"2411.05980","version":3},"attestation_state":"computed","paper":{"title":"FactLens: Benchmarking Fine-Grained Fact Verification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Zhang, Estevam Hruschka, Kushan Mitra, Sajjadur Rahman","submitted_at":"2024-11-08T21:26:57Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents and claims from other sources, traditional verification approaches often rely on holistic models that assign a single factuality label to complex claims, potentially obscuring nuanced errors. In this paper, we advocate for a shift towards fine-grained verification, where complex claims are broken down into smaller sub-claims for individual verification, all"},"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":"2411.05980","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T21:26:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a876fefcfae6ffaf8c4c2e31822b741e413cc60558c0923a69a424c09807d71c","abstract_canon_sha256":"a71ec5c890dd8390f4e3b9988cedb72afb2154564b654d8e0a906a1ee455e700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:15.622174Z","signature_b64":"BCQgI00QZbSgMT8F0GsWAHeeAIXfJcLBGwjEM+39TBIqlMlGqjkjj5BsQP11NA6DiXXEnC5eH2KhxCCpr5WnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d3966eae763735f45caa05319849a891ada092b9debb811f063084f3b0451b8","last_reissued_at":"2026-07-05T11:13:15.621592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:15.621592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FactLens: Benchmarking Fine-Grained Fact Verification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Zhang, Estevam Hruschka, Kushan Mitra, Sajjadur Rahman","submitted_at":"2024-11-08T21:26:57Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation. To verify LLM-generated contents and claims from other sources, traditional verification approaches often rely on holistic models that assign a single factuality label to complex claims, potentially obscuring nuanced errors. In this paper, we advocate for a shift towards fine-grained verification, where complex claims are broken down into smaller sub-claims for individual verification, all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05980","kind":"arxiv","version":3},"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/2411.05980/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":"2411.05980","created_at":"2026-07-05T11:13:15.621660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05980v3","created_at":"2026-07-05T11:13:15.621660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05980","created_at":"2026-07-05T11:13:15.621660+00:00"},{"alias_kind":"pith_short_12","alias_value":"DU4WN2XHMNZV","created_at":"2026-07-05T11:13:15.621660+00:00"},{"alias_kind":"pith_short_16","alias_value":"DU4WN2XHMNZV6ROK","created_at":"2026-07-05T11:13:15.621660+00:00"},{"alias_kind":"pith_short_8","alias_value":"DU4WN2XH","created_at":"2026-07-05T11:13:15.621660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20848","citing_title":"JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE","json":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE.json","graph_json":"https://pith.science/api/pith-number/DU4WN2XHMNZV6ROKUBJRTBE2RE/graph.json","events_json":"https://pith.science/api/pith-number/DU4WN2XHMNZV6ROKUBJRTBE2RE/events.json","paper":"https://pith.science/paper/DU4WN2XH"},"agent_actions":{"view_html":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE","download_json":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE.json","view_paper":"https://pith.science/paper/DU4WN2XH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05980&json=true","fetch_graph":"https://pith.science/api/pith-number/DU4WN2XHMNZV6ROKUBJRTBE2RE/graph.json","fetch_events":"https://pith.science/api/pith-number/DU4WN2XHMNZV6ROKUBJRTBE2RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE/action/storage_attestation","attest_author":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE/action/author_attestation","sign_citation":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE/action/citation_signature","submit_replication":"https://pith.science/pith/DU4WN2XHMNZV6ROKUBJRTBE2RE/action/replication_record"}},"created_at":"2026-07-05T11:13:15.621660+00:00","updated_at":"2026-07-05T11:13:15.621660+00:00"}