{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PXZITQHJP2W2PXZXHQUWM7Q5YA","short_pith_number":"pith:PXZITQHJ","schema_version":"1.0","canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","source":{"kind":"arxiv","id":"2405.20267","version":4},"attestation_state":"computed","paper":{"title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deli Zhao, Lidong Bing, Ruochen Zhao, Weiwen Xu, Wenxuan Zhang, Yew Ken Chia","submitted_at":"2024-05-30T17:19:19Z","abstract_excerpt":"As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibility and unreliability, leading users to prefer human voting platforms like Chatbot Arena. However, human evaluations require significant manual effort. To address this, we propose the Auto-Arena, an innovative framework that automates the entire evaluation process using LLM-powered agents. Firstly, an LLM examiner generates questions. Then, two LLM candidates engage in a multi-round peer battle based on individual q"},"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":"2405.20267","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"cefa869da2e3fab53b2c0a34042d12862674810d7cfd3ccb4a7484d1e59de837","abstract_canon_sha256":"55b55271409e42cadfadf0e217c69a3f6b536873e9f587a40b84a3942afc1b55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:49.488691Z","signature_b64":"zEPa9tUWe0ONs+9U4xcGS/Pc+0i3AoS0Utq1PAI9vDLjSuI/YJD6D+2kY+KH99HKI4LRP+/HKg32taWbkpimBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","last_reissued_at":"2026-07-05T09:16:49.488201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:49.488201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deli Zhao, Lidong Bing, Ruochen Zhao, Weiwen Xu, Wenxuan Zhang, Yew Ken Chia","submitted_at":"2024-05-30T17:19:19Z","abstract_excerpt":"As LLMs continuously evolve, there is an urgent need for a reliable evaluation method that delivers trustworthy results promptly. Currently, static benchmarks suffer from inflexibility and unreliability, leading users to prefer human voting platforms like Chatbot Arena. However, human evaluations require significant manual effort. To address this, we propose the Auto-Arena, an innovative framework that automates the entire evaluation process using LLM-powered agents. Firstly, an LLM examiner generates questions. Then, two LLM candidates engage in a multi-round peer battle based on individual q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20267","kind":"arxiv","version":4},"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/2405.20267/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":"2405.20267","created_at":"2026-07-05T09:16:49.488257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20267v4","created_at":"2026-07-05T09:16:49.488257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20267","created_at":"2026-07-05T09:16:49.488257+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXZITQHJP2W2","created_at":"2026-07-05T09:16:49.488257+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXZITQHJP2W2PXZX","created_at":"2026-07-05T09:16:49.488257+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXZITQHJ","created_at":"2026-07-05T09:16:49.488257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19228","citing_title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":297,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA","json":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA.json","graph_json":"https://pith.science/api/pith-number/PXZITQHJP2W2PXZXHQUWM7Q5YA/graph.json","events_json":"https://pith.science/api/pith-number/PXZITQHJP2W2PXZXHQUWM7Q5YA/events.json","paper":"https://pith.science/paper/PXZITQHJ"},"agent_actions":{"view_html":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA","download_json":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA.json","view_paper":"https://pith.science/paper/PXZITQHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20267&json=true","fetch_graph":"https://pith.science/api/pith-number/PXZITQHJP2W2PXZXHQUWM7Q5YA/graph.json","fetch_events":"https://pith.science/api/pith-number/PXZITQHJP2W2PXZXHQUWM7Q5YA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/action/storage_attestation","attest_author":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/action/author_attestation","sign_citation":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/action/citation_signature","submit_replication":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/action/replication_record"}},"created_at":"2026-07-05T09:16:49.488257+00:00","updated_at":"2026-07-05T09:16:49.488257+00:00"}