{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NKEDGBHRWJPY3P3B4JRDLQVCOS","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":"26b85c588d5015457f50d6799d6f8f7d58aba396e95ddc5ee94e96396d529240","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-27T17:48:55Z","title_canon_sha256":"2df7728d2d316131840ef94e90b79244d71a25192a6f7201857f7f9779f1e08b"},"schema_version":"1.0","source":{"id":"2403.18802","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18802","created_at":"2026-07-05T09:32:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18802v4","created_at":"2026-07-05T09:32:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18802","created_at":"2026-07-05T09:32:06Z"},{"alias_kind":"pith_short_12","alias_value":"NKEDGBHRWJPY","created_at":"2026-07-05T09:32:06Z"},{"alias_kind":"pith_short_16","alias_value":"NKEDGBHRWJPY3P3B","created_at":"2026-07-05T09:32:06Z"},{"alias_kind":"pith_short_8","alias_value":"NKEDGBHR","created_at":"2026-07-05T09:32:06Z"}],"graph_snapshots":[{"event_id":"sha256:f658ddef1c8ceb54d65dbecf9614030edaca39766f3f43a18001e48a0c261ff6","target":"graph","created_at":"2026-07-05T09:32:06Z","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/2403.18802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often generate content that contains factual errors when responding to fact-seeking prompts on open-ended topics. To benchmark a model's long-form factuality in open domains, we first use GPT-4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE). SAFE utilizes an LLM to break down a long-form response into a set of individual facts and to evaluate the accuracy of","authors_text":"Chengrun Yang, Cosmo Du, Da Huang, Daiyi Peng, Dustin Tran, Jerry Wei, Jie Huang, Nathan Hu, Quoc V. Le, Ruibo Liu, Xinying Song, Yifeng Lu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18802","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":"sha256:886e08f179565bbeeed26671ebaddd272677a956397373c22c542f5d14ab69b8","target":"record","created_at":"2026-07-05T09:32:06Z","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":"26b85c588d5015457f50d6799d6f8f7d58aba396e95ddc5ee94e96396d529240","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-27T17:48:55Z","title_canon_sha256":"2df7728d2d316131840ef94e90b79244d71a25192a6f7201857f7f9779f1e08b"},"schema_version":"1.0","source":{"id":"2403.18802","kind":"arxiv","version":4}},"canonical_sha256":"6a883304f1b25f8dbf61e26235c2a274a3917240cf481e9b8492ec2ca1d3e800","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a883304f1b25f8dbf61e26235c2a274a3917240cf481e9b8492ec2ca1d3e800","first_computed_at":"2026-07-05T09:32:06.500217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:06.500217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fs3pwEtNJXG9DYknN/u2jJHNH4YdPl/GJgq4E54T/f35MwowJJQ+Qcd2Bedz9wLsK3giJC7b7SDukmXrTjNmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:06.500759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18802","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:886e08f179565bbeeed26671ebaddd272677a956397373c22c542f5d14ab69b8","sha256:f658ddef1c8ceb54d65dbecf9614030edaca39766f3f43a18001e48a0c261ff6"],"state_sha256":"4460a1e771f1b46a3893f8c0f0b2b12453295cce08184a7bca93f9e8cb8425cc"}