{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5DZCA3JFK4WEHMDGFYVGIQF4RS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d2705265c3cc8ce4c7a4093aca2ee77b47719a0ad33a1819504b2b611c2d8293","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:19:56Z","title_canon_sha256":"777e29fb988cab77026514a5836b05ee036b7416f28677dd1b8167386b6474aa"},"schema_version":"1.0","source":{"id":"2410.22257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22257","created_at":"2026-07-05T09:58:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22257v2","created_at":"2026-07-05T09:58:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22257","created_at":"2026-07-05T09:58:25Z"},{"alias_kind":"pith_short_12","alias_value":"5DZCA3JFK4WE","created_at":"2026-07-05T09:58:25Z"},{"alias_kind":"pith_short_16","alias_value":"5DZCA3JFK4WEHMDG","created_at":"2026-07-05T09:58:25Z"},{"alias_kind":"pith_short_8","alias_value":"5DZCA3JF","created_at":"2026-07-05T09:58:25Z"}],"graph_snapshots":[{"event_id":"sha256:c389aeff72653f2478e9c80ad4b13847047c52ee4f8be98d7339643ef78aeeeb","target":"graph","created_at":"2026-07-05T09:58:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.22257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Farima Fatahi Bayat, Lechen Zhang, Lu Wang, Sheza Munir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:19:56Z","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22257","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e99ba00f1036d4bc38b8a51f904045828c0887c99c7141fb1200b583a0c8b7e5","target":"record","created_at":"2026-07-05T09:58:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d2705265c3cc8ce4c7a4093aca2ee77b47719a0ad33a1819504b2b611c2d8293","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:19:56Z","title_canon_sha256":"777e29fb988cab77026514a5836b05ee036b7416f28677dd1b8167386b6474aa"},"schema_version":"1.0","source":{"id":"2410.22257","kind":"arxiv","version":2}},"canonical_sha256":"e8f2206d25572c43b0662e2a6440bc8cab33768cc58b04c9bfbbec21e8327d3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f2206d25572c43b0662e2a6440bc8cab33768cc58b04c9bfbbec21e8327d3e","first_computed_at":"2026-07-05T09:58:25.692784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:25.692784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfQHUqO+K1TSNyp292vzsESOLve4mJ3S5GHmB2y8G8WhIF0Ev/T7eEI42RHKPS6m0B85ZZV7LVRgSQ3zdTiYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:25.693269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e99ba00f1036d4bc38b8a51f904045828c0887c99c7141fb1200b583a0c8b7e5","sha256:c389aeff72653f2478e9c80ad4b13847047c52ee4f8be98d7339643ef78aeeeb"],"state_sha256":"0bbf7fc3c5c8040cce81de3e526fc88ab8642fbe800844eebc4faa09546c29f0"}