{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NTDL4KZD5I3W4M74XRDIT7MEFL","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":"3630d87f08a4b68ee8d4fa23eb08213a297c564fe50d2dfd825e1f4054dd4727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T18:50:34Z","title_canon_sha256":"3e372c623e1fce5ecb209b0f5867188a832fecd666880abd9c38043185befe07"},"schema_version":"1.0","source":{"id":"2211.08412","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08412","created_at":"2026-07-05T07:19:17Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08412v2","created_at":"2026-07-05T07:19:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08412","created_at":"2026-07-05T07:19:17Z"},{"alias_kind":"pith_short_12","alias_value":"NTDL4KZD5I3W","created_at":"2026-07-05T07:19:17Z"},{"alias_kind":"pith_short_16","alias_value":"NTDL4KZD5I3W4M74","created_at":"2026-07-05T07:19:17Z"},{"alias_kind":"pith_short_8","alias_value":"NTDL4KZD","created_at":"2026-07-05T07:19:17Z"}],"graph_snapshots":[{"event_id":"sha256:1f77e338df55df916f946a91e3b656fd58b3a319ab635e62b35e1e94e37a99a8","target":"graph","created_at":"2026-07-05T07:19:17Z","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/2211.08412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large language models (LLMs) have proven to be effective on a large variety of tasks, they are also known to hallucinate information. To measure whether an LLM prefers factually consistent continuations of its input, we propose a new benchmark called FIB(Factual Inconsistency Benchmark) that focuses on the task of summarization. Specifically, our benchmark involves comparing the scores an LLM assigns to a factually consistent versus a factually inconsistent summary for an input news article. For factually consistent summaries, we use human-written reference summaries that we manually ver","authors_text":"Anisha Mascarenhas, Colin Raffel, Derek Tam, Mohit Bansal, Sarah Kwan, Shiyue Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T18:50:34Z","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08412","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":"sha256:1825a36c3052f623b19e875413817bb0882c6364263435bf8855f1cd3bfe81bf","target":"record","created_at":"2026-07-05T07:19:17Z","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":"3630d87f08a4b68ee8d4fa23eb08213a297c564fe50d2dfd825e1f4054dd4727","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T18:50:34Z","title_canon_sha256":"3e372c623e1fce5ecb209b0f5867188a832fecd666880abd9c38043185befe07"},"schema_version":"1.0","source":{"id":"2211.08412","kind":"arxiv","version":2}},"canonical_sha256":"6cc6be2b23ea376e33fcbc4689fd842afba0a015ed20ef926efe4ab4163cebfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cc6be2b23ea376e33fcbc4689fd842afba0a015ed20ef926efe4ab4163cebfa","first_computed_at":"2026-07-05T07:19:17.755901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:17.755901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bd4yn9xC/6YZUqsTzlgPCMptbWITh8Z6haldk918qvcEpFqtvBG654SbFWF4p++kvUpfgaLAzEWW3r5+IG3sCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:17.756398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08412","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1825a36c3052f623b19e875413817bb0882c6364263435bf8855f1cd3bfe81bf","sha256:1f77e338df55df916f946a91e3b656fd58b3a319ab635e62b35e1e94e37a99a8"],"state_sha256":"26426f8cf9484bf386d0a2f50849d9284c263ce3c8c8764dbe03f02b14a92fee"}