{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K6BJG4FOVVQO6RQKAZ36KZH5L4","short_pith_number":"pith:K6BJG4FO","schema_version":"1.0","canonical_sha256":"57829370aead60ef460a0677e564fd5f378b8c4187f6f56709da15f13147c1ef","source":{"kind":"arxiv","id":"2311.09000","version":3},"attestation_state":"computed","paper":{"title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Pillai, Aleksandr Rubashevskii, Arnav Arora, Iryna Gurevych, Isabelle Augenstein, Jiahui Geng, Liangming Pan, Nadav Borenstein, Osama Mohammed Afzal, Preslav Nakov, Revanth Gangi Reddy, Yuxia Wang, Zain Muhammad Mujahid","submitted_at":"2023-11-15T14:41:57Z","abstract_excerpt":"The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. In this work, we present a holistic end-to-end solution for annotating the factuality of LLM-generated responses, which encompasses a multi-stage annotation scheme designed to yield detailed labels concerning the verifiability and factual inconsistencies found in LLM outputs. We further construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document, aiming to facilitate the eval"},"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":"2311.09000","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T14:41:57Z","cross_cats_sorted":[],"title_canon_sha256":"f896bb7bd49b321248ffad008c0531ddd20a103eabad093c76b37a7dabff7037","abstract_canon_sha256":"ca1166b608686eac62ae3a314c2e1d81901cd5f42fbe08128d620489baf1e9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:19.170412Z","signature_b64":"lNFRdbmX8fRZgOGPRq53BlqLtfoLelP9WAwassKto3+hFz9ijj4DCDu25J8VvJ1FoUkLIytpjt9bQqwI5TBjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57829370aead60ef460a0677e564fd5f378b8c4187f6f56709da15f13147c1ef","last_reissued_at":"2026-07-05T08:08:19.169945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:19.169945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Pillai, Aleksandr Rubashevskii, Arnav Arora, Iryna Gurevych, Isabelle Augenstein, Jiahui Geng, Liangming Pan, Nadav Borenstein, Osama Mohammed Afzal, Preslav Nakov, Revanth Gangi Reddy, Yuxia Wang, Zain Muhammad Mujahid","submitted_at":"2023-11-15T14:41:57Z","abstract_excerpt":"The increased use of large language models (LLMs) across a variety of real-world applications calls for mechanisms to verify the factual accuracy of their outputs. In this work, we present a holistic end-to-end solution for annotating the factuality of LLM-generated responses, which encompasses a multi-stage annotation scheme designed to yield detailed labels concerning the verifiability and factual inconsistencies found in LLM outputs. We further construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document, aiming to facilitate the eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09000","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/2311.09000/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":"2311.09000","created_at":"2026-07-05T08:08:19.170001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09000v3","created_at":"2026-07-05T08:08:19.170001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09000","created_at":"2026-07-05T08:08:19.170001+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6BJG4FOVVQO","created_at":"2026-07-05T08:08:19.170001+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6BJG4FOVVQO6RQK","created_at":"2026-07-05T08:08:19.170001+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6BJG4FO","created_at":"2026-07-05T08:08:19.170001+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08605","citing_title":"Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4","json":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4.json","graph_json":"https://pith.science/api/pith-number/K6BJG4FOVVQO6RQKAZ36KZH5L4/graph.json","events_json":"https://pith.science/api/pith-number/K6BJG4FOVVQO6RQKAZ36KZH5L4/events.json","paper":"https://pith.science/paper/K6BJG4FO"},"agent_actions":{"view_html":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4","download_json":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4.json","view_paper":"https://pith.science/paper/K6BJG4FO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09000&json=true","fetch_graph":"https://pith.science/api/pith-number/K6BJG4FOVVQO6RQKAZ36KZH5L4/graph.json","fetch_events":"https://pith.science/api/pith-number/K6BJG4FOVVQO6RQKAZ36KZH5L4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4/action/storage_attestation","attest_author":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4/action/author_attestation","sign_citation":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4/action/citation_signature","submit_replication":"https://pith.science/pith/K6BJG4FOVVQO6RQKAZ36KZH5L4/action/replication_record"}},"created_at":"2026-07-05T08:08:19.170001+00:00","updated_at":"2026-07-05T08:08:19.170001+00:00"}