{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K6BJG4FOVVQO6RQKAZ36KZH5L4","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":"ca1166b608686eac62ae3a314c2e1d81901cd5f42fbe08128d620489baf1e9a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T14:41:57Z","title_canon_sha256":"f896bb7bd49b321248ffad008c0531ddd20a103eabad093c76b37a7dabff7037"},"schema_version":"1.0","source":{"id":"2311.09000","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09000","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09000v3","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09000","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"K6BJG4FOVVQO","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"K6BJG4FOVVQO6RQK","created_at":"2026-07-05T08:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"K6BJG4FO","created_at":"2026-07-05T08:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:e074055d13040f46a0fb80866da855a675b30c9e2878d5a1acee36cd038eebd9","target":"graph","created_at":"2026-07-05T08:08:19Z","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/2311.09000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T14:41:57Z","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09000","kind":"arxiv","version":3},"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":"sha256:81a6466d032342347ecea03c3e47ea8f2e53174132486ad9d2ca452665eb3d27","target":"record","created_at":"2026-07-05T08:08:19Z","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":"ca1166b608686eac62ae3a314c2e1d81901cd5f42fbe08128d620489baf1e9a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T14:41:57Z","title_canon_sha256":"f896bb7bd49b321248ffad008c0531ddd20a103eabad093c76b37a7dabff7037"},"schema_version":"1.0","source":{"id":"2311.09000","kind":"arxiv","version":3}},"canonical_sha256":"57829370aead60ef460a0677e564fd5f378b8c4187f6f56709da15f13147c1ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57829370aead60ef460a0677e564fd5f378b8c4187f6f56709da15f13147c1ef","first_computed_at":"2026-07-05T08:08:19.169945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:19.169945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lNFRdbmX8fRZgOGPRq53BlqLtfoLelP9WAwassKto3+hFz9ijj4DCDu25J8VvJ1FoUkLIytpjt9bQqwI5TBjAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:19.170412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09000","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81a6466d032342347ecea03c3e47ea8f2e53174132486ad9d2ca452665eb3d27","sha256:e074055d13040f46a0fb80866da855a675b30c9e2878d5a1acee36cd038eebd9"],"state_sha256":"6a4c90073725289835a3cdee33775914b06c3999c6e0199dce6a2c344984e79d"}