{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y42PHZ7CFSNAONY5C5XHW5D56A","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":"c67897e1b5ca33d7dfac87001167a692d674067ce75c9bb66db724d1a700b459","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:06:00Z","title_canon_sha256":"eed7f4ddec5dde80a7bcf1868ac7f576ed08aa7d75e4ec51747808e6e52f5b6f"},"schema_version":"1.0","source":{"id":"2305.14251","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14251","created_at":"2026-07-05T06:59:32Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14251v2","created_at":"2026-07-05T06:59:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14251","created_at":"2026-07-05T06:59:32Z"},{"alias_kind":"pith_short_12","alias_value":"Y42PHZ7CFSNA","created_at":"2026-07-05T06:59:32Z"},{"alias_kind":"pith_short_16","alias_value":"Y42PHZ7CFSNAONY5","created_at":"2026-07-05T06:59:32Z"},{"alias_kind":"pith_short_8","alias_value":"Y42PHZ7C","created_at":"2026-07-05T06:59:32Z"}],"graph_snapshots":[{"event_id":"sha256:2c79724f78544fb94bc24d53b20d567dbb6b9f7e9fe82f44f955a0557e6e6453","target":"graph","created_at":"2026-07-05T06:59:32Z","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/2305.14251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly. In this paper, we introduce FACTSCORE, a new evaluation that breaks a generation into a series of atomic facts and computes the percentage of atomic facts supported by a reliable knowledge source. We conduct an extensive human evaluation to obtain FACTSCOREs of people biographies generated by seve","authors_text":"Hannaneh Hajishirzi, Kalpesh Krishna, Luke Zettlemoyer, Mike Lewis, Mohit Iyyer, Pang Wei Koh, Sewon Min, Wen-tau Yih, Xinxi Lyu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:06:00Z","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14251","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":"sha256:00da899d300bd4460fb22ef3d09e358ee4fee0ada27355d0f4f9f4e65a424c4b","target":"record","created_at":"2026-07-05T06:59:32Z","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":"c67897e1b5ca33d7dfac87001167a692d674067ce75c9bb66db724d1a700b459","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:06:00Z","title_canon_sha256":"eed7f4ddec5dde80a7bcf1868ac7f576ed08aa7d75e4ec51747808e6e52f5b6f"},"schema_version":"1.0","source":{"id":"2305.14251","kind":"arxiv","version":2}},"canonical_sha256":"c734f3e7e22c9a07371d176e7b747df0277d44860df33126d79c8df4c05a14e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c734f3e7e22c9a07371d176e7b747df0277d44860df33126d79c8df4c05a14e2","first_computed_at":"2026-07-05T06:59:32.206376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:32.206376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UsYbezGwPWz2sKraiMTnODbygNCl2zlOWifb5X3Aymc5PHsufgrDoKd3MrTwjnftGKmlBOPHXlQ+rGJfsTDOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:32.206854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14251","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00da899d300bd4460fb22ef3d09e358ee4fee0ada27355d0f4f9f4e65a424c4b","sha256:2c79724f78544fb94bc24d53b20d567dbb6b9f7e9fe82f44f955a0557e6e6453"],"state_sha256":"74bab4214959cfb5a420eb6d538cbb5fdbca97387d4bbd4dfe64aa284bd86253"}