{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JQRCIHE4MOGFAA4DISVHHOJJHE","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":"839e083fba7ccd5f16118a580155f638b5908f68482b153237458501d1aa3619","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T19:02:48Z","title_canon_sha256":"3c627c04fae7b710c767033a2472e9f4d77bfa55df4079e7950c90f3f232eecd"},"schema_version":"1.0","source":{"id":"2401.06855","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06855","created_at":"2026-07-05T08:54:46Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06855v4","created_at":"2026-07-05T08:54:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06855","created_at":"2026-07-05T08:54:46Z"},{"alias_kind":"pith_short_12","alias_value":"JQRCIHE4MOGF","created_at":"2026-07-05T08:54:46Z"},{"alias_kind":"pith_short_16","alias_value":"JQRCIHE4MOGFAA4D","created_at":"2026-07-05T08:54:46Z"},{"alias_kind":"pith_short_8","alias_value":"JQRCIHE4","created_at":"2026-07-05T08:54:46Z"}],"graph_snapshots":[{"event_id":"sha256:da44d0c3d1caffe63fd11f7712686dd996b0b10069ae1ac241cb5c1505e1a6df","target":"graph","created_at":"2026-07-05T08:54:46Z","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/2401.06855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LMs) are prone to generate factual errors, which are often called hallucinations. In this paper, we introduce a comprehensive taxonomy of hallucinations and argue that hallucinations manifest in diverse forms, each requiring varying degrees of careful assessments to verify factuality. We propose a novel task of automatic fine-grained hallucination detection and construct a new evaluation benchmark, FavaBench, that includes about one thousand fine-grained human judgments on three LM outputs across various domains. Our analysis reveals that ChatGPT and Llama2-Chat (70B, 7B","authors_text":"Abhika Mishra, Akari Asai, Graham Neubig, Hannaneh Hajishirzi, Vidhisha Balachandran, Yizhong Wang, Yulia Tsvetkov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T19:02:48Z","title":"Fine-grained Hallucination Detection and Editing for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06855","kind":"arxiv","version":4},"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":"sha256:9a3a47b9293a3fb8c3880281356d7208adff7061f75e118550f00fc1682190f8","target":"record","created_at":"2026-07-05T08:54:46Z","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":"839e083fba7ccd5f16118a580155f638b5908f68482b153237458501d1aa3619","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T19:02:48Z","title_canon_sha256":"3c627c04fae7b710c767033a2472e9f4d77bfa55df4079e7950c90f3f232eecd"},"schema_version":"1.0","source":{"id":"2401.06855","kind":"arxiv","version":4}},"canonical_sha256":"4c22241c9c638c50038344aa73b9293929474826c6b17177ec7ace07d7db1cc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c22241c9c638c50038344aa73b9293929474826c6b17177ec7ace07d7db1cc3","first_computed_at":"2026-07-05T08:54:46.076275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:54:46.076275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1R+pDHMEuBEEiCilY5hJFWj80Bvmn7UcC9d6+WOgHevBwY4686waAVTYvRjk5Gh+fPbYMXMGyzevGskZ0NAoBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:54:46.076649Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06855","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a3a47b9293a3fb8c3880281356d7208adff7061f75e118550f00fc1682190f8","sha256:da44d0c3d1caffe63fd11f7712686dd996b0b10069ae1ac241cb5c1505e1a6df"],"state_sha256":"7f86e91607dfb730a1c3b03bb9015813417713936eaad7e553bc694122ef4e29"}