{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJDBFMWH5N75BYDFB4NFEJQU5T","short_pith_number":"pith:ZJDBFMWH","schema_version":"1.0","canonical_sha256":"ca4612b2c7eb7fd0e0650f1a522614ece0ef21bb3d434cc0cc345f0de627f979","source":{"kind":"arxiv","id":"2310.08491","version":2},"attestation_state":"computed","paper":{"title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hwaran Lee, James Thorne, Jamin Shin, Joel Jang, Minjoon Seo, Sangdoo Yun, Seongjin Shin, Seungone Kim, Shayne Longpre, Sungdong Kim, Yejin Cho","submitted_at":"2023-10-12T16:50:08Z","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) "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.08491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T16:50:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cca9b95f5126c057f76942930e5e70a3006ead67100ca041d46acbd161a0b2fe","abstract_canon_sha256":"5c7cdaa2013d7f91258eb52422fff5fc1c5a5f16ea59371d9d2e51e3bd353740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:04.867723Z","signature_b64":"GgBes473vN70ubJff0tm/Zzw5ApXOgKNhWtL7FCiHQMYbBsE0DDtcEOSGkw2/V83mA5LLqX2WCAa7avRvWGbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4612b2c7eb7fd0e0650f1a522614ece0ef21bb3d434cc0cc345f0de627f979","last_reissued_at":"2026-07-05T07:54:04.867204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:04.867204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hwaran Lee, James Thorne, Jamin Shin, Joel Jang, Minjoon Seo, Sangdoo Yun, Seongjin Shin, Seungone Kim, Shayne Longpre, Sungdong Kim, Yejin Cho","submitted_at":"2023-10-12T16:50:08Z","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) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08491","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.08491/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.08491","created_at":"2026-07-05T07:54:04.867266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08491v2","created_at":"2026-07-05T07:54:04.867266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08491","created_at":"2026-07-05T07:54:04.867266+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJDBFMWH5N75","created_at":"2026-07-05T07:54:04.867266+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJDBFMWH5N75BYDF","created_at":"2026-07-05T07:54:04.867266+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJDBFMWH","created_at":"2026-07-05T07:54:04.867266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08535","citing_title":"When the Judge Changes, So Does the Measurement: Auditing LLM-as-Judge Reliability","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08700","citing_title":"Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05968","citing_title":"InfluMatch: Frontier-Quality KOL Search at 4B-Model Cost","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06196","citing_title":"Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19714","citing_title":"AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17162","citing_title":"MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11635","citing_title":"Are LLMs Bad at Moral Reasoning?","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00093","citing_title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28158","citing_title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01451","citing_title":"Before and After Temperature: A Distributional View of Creative LLM Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05465","citing_title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19237","citing_title":"Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robots","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24235","citing_title":"PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10020","citing_title":"Self-Rewarding Language Models","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20273","citing_title":"ActuBench: A Multi-Agent LLM Pipeline for Generation and Evaluation of Actuarial Reasoning Tasks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05912","citing_title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T","json":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T.json","graph_json":"https://pith.science/api/pith-number/ZJDBFMWH5N75BYDFB4NFEJQU5T/graph.json","events_json":"https://pith.science/api/pith-number/ZJDBFMWH5N75BYDFB4NFEJQU5T/events.json","paper":"https://pith.science/paper/ZJDBFMWH"},"agent_actions":{"view_html":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T","download_json":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T.json","view_paper":"https://pith.science/paper/ZJDBFMWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08491&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJDBFMWH5N75BYDFB4NFEJQU5T/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJDBFMWH5N75BYDFB4NFEJQU5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T/action/storage_attestation","attest_author":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T/action/author_attestation","sign_citation":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T/action/citation_signature","submit_replication":"https://pith.science/pith/ZJDBFMWH5N75BYDFB4NFEJQU5T/action/replication_record"}},"created_at":"2026-07-05T07:54:04.867266+00:00","updated_at":"2026-07-05T07:54:04.867266+00:00"}