{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3Q2D2O5EBVXQLNSCXAQUD7OV74","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":"79a96d4b4c6c5cd0b65d6995221f3c8b1f094216ac0409d355852647baf8b39c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T01:41:02Z","title_canon_sha256":"79cb28abb07c450f15945002304a3f67e3a684325cf3c41f0cc22b88cfbe24a3"},"schema_version":"1.0","source":{"id":"2410.18359","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18359","created_at":"2026-07-05T11:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18359v3","created_at":"2026-07-05T11:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18359","created_at":"2026-07-05T11:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"3Q2D2O5EBVXQ","created_at":"2026-07-05T11:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"3Q2D2O5EBVXQLNSC","created_at":"2026-07-05T11:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"3Q2D2O5E","created_at":"2026-07-05T11:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:42d8aae5a15fb844056b51817303dcd1dfe2068a8e5921d4478a92d273f78dcc","target":"graph","created_at":"2026-07-05T11:13:14Z","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/2410.18359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with claim-level factuality feedback. We conduct data augmentation on a combination of public judgment datasets to train FenCE to (1) generate textual critiques along with scores and (2) make claim-level judgment based on diverse source documents obtained by various tools. We then present a framework that leverages FenCE to improve the factuality of LM generators by co","authors_text":"Arya Talebzadeh, Carolyn Rose, Daniel Fried, Di Jin, Han Fang, Hejia Zhang, Pradyot Prakash, Quintin Fettes, Sinong Wang, Wenxuan Zhou, Yiqing Xie, Yuning Mao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T01:41:02Z","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18359","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":"sha256:53eb2ebb4fa1086811396f551d259bbebb7cf3896390a4f6429507445cdff9ab","target":"record","created_at":"2026-07-05T11:13:14Z","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":"79a96d4b4c6c5cd0b65d6995221f3c8b1f094216ac0409d355852647baf8b39c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T01:41:02Z","title_canon_sha256":"79cb28abb07c450f15945002304a3f67e3a684325cf3c41f0cc22b88cfbe24a3"},"schema_version":"1.0","source":{"id":"2410.18359","kind":"arxiv","version":3}},"canonical_sha256":"dc343d3ba40d6f05b642b82141fdd5ff183496bba09e0809ac627bf20a16ff6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc343d3ba40d6f05b642b82141fdd5ff183496bba09e0809ac627bf20a16ff6c","first_computed_at":"2026-07-05T11:13:14.761838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:14.761838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UexOQPhOWM2IKbMxl94j4ekBdTRljjzkdo/X4mGrJxv2p3BewXTqFJcKa7SfYGBlU125spx9LWnkWLz2WeDsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:14.762368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18359","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53eb2ebb4fa1086811396f551d259bbebb7cf3896390a4f6429507445cdff9ab","sha256:42d8aae5a15fb844056b51817303dcd1dfe2068a8e5921d4478a92d273f78dcc"],"state_sha256":"0f822e4fecd19c36970d10220fbd1ea6e095fdac87b7d27256fbc5e64aa452df"}