{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZJDBFMWH5N75BYDFB4NFEJQU5T","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":"5c7cdaa2013d7f91258eb52422fff5fc1c5a5f16ea59371d9d2e51e3bd353740","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T16:50:08Z","title_canon_sha256":"cca9b95f5126c057f76942930e5e70a3006ead67100ca041d46acbd161a0b2fe"},"schema_version":"1.0","source":{"id":"2310.08491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08491","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08491v2","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08491","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZJDBFMWH5N75","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZJDBFMWH5N75BYDF","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZJDBFMWH","created_at":"2026-07-05T07:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:24f7cd71d818ae43a590cff76d75e94457910bc746f0f2c0a2a4803c79f5f74b","target":"graph","created_at":"2026-07-05T07:54:04Z","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/2310.08491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, using a powerful proprietary Large Language Model (LLM) (e.g., GPT-4) as an evaluator for long-form responses has become the de facto standard. However, for practitioners with large-scale evaluation tasks and custom criteria in consideration (e.g., child-readability), using proprietary LLMs as an evaluator is unreliable due to the closed-source nature, uncontrolled versioning, and prohibitive costs. In this work, we propose Prometheus, a fully open-source LLM that is on par with GPT-4's evaluation capabilities when the appropriate reference materials (reference answer, score rubric) ","authors_text":"Hwaran Lee, James Thorne, Jamin Shin, Joel Jang, Minjoon Seo, Sangdoo Yun, Seongjin Shin, Seungone Kim, Shayne Longpre, Sungdong Kim, Yejin Cho","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T16:50:08Z","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08491","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:b6337c4ea37c1631c52c6378bafd50192858795341f3bd4ff2b2cfaf4be34a7d","target":"record","created_at":"2026-07-05T07:54:04Z","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":"5c7cdaa2013d7f91258eb52422fff5fc1c5a5f16ea59371d9d2e51e3bd353740","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T16:50:08Z","title_canon_sha256":"cca9b95f5126c057f76942930e5e70a3006ead67100ca041d46acbd161a0b2fe"},"schema_version":"1.0","source":{"id":"2310.08491","kind":"arxiv","version":2}},"canonical_sha256":"ca4612b2c7eb7fd0e0650f1a522614ece0ef21bb3d434cc0cc345f0de627f979","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca4612b2c7eb7fd0e0650f1a522614ece0ef21bb3d434cc0cc345f0de627f979","first_computed_at":"2026-07-05T07:54:04.867204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:04.867204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GgBes473vN70ubJff0tm/Zzw5ApXOgKNhWtL7FCiHQMYbBsE0DDtcEOSGkw2/V83mA5LLqX2WCAa7avRvWGbDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:04.867723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6337c4ea37c1631c52c6378bafd50192858795341f3bd4ff2b2cfaf4be34a7d","sha256:24f7cd71d818ae43a590cff76d75e94457910bc746f0f2c0a2a4803c79f5f74b"],"state_sha256":"0dcf9216290e621f19549bac58cf90fff5e8b94842f17662ee2c11a5de3cbcd9"}