{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PXZITQHJP2W2PXZXHQUWM7Q5YA","short_pith_number":"pith:PXZITQHJ","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"},"canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","source":{"kind":"arxiv","id":"2405.20267","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20267","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20267v4","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20267","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"PXZITQHJP2W2","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"PXZITQHJP2W2PXZX","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"PXZITQHJ","created_at":"2026-07-05T09:16:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PXZITQHJP2W2PXZXHQUWM7Q5YA","target":"record","payload":{"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"},"canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","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"},"source_kind":"arxiv","source_id":"2405.20267","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpR/rfzkksauP4ddvjMQa6bOEOICSVt0YlKoXJAC8ztbd2UR8ZEXd34sqTwECu855Bud0BBGKHEw0gZidci2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:05:47.025246Z"},"content_sha256":"2972d9ccb9f0ff0062bdb423ce359e87a47d5729a61cf5aeb66e0aa209f7e4a1","schema_version":"1.0","event_id":"sha256:2972d9ccb9f0ff0062bdb423ce359e87a47d5729a61cf5aeb66e0aa209f7e4a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PXZITQHJP2W2PXZXHQUWM7Q5YA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8fYJBJzSQtzwYpfa32SWwMzDmB/MuvT8N6dULqxfq0VGclmBWrFryi9pjrmuLqw7UUrHhQ6HC+T+OThKJ80LBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:05:47.025662Z"},"content_sha256":"a97125c30af9da77d2974ad3dc7ff1b9769f5da744eaea1b412b4e7603b1f0d8","schema_version":"1.0","event_id":"sha256:a97125c30af9da77d2974ad3dc7ff1b9769f5da744eaea1b412b4e7603b1f0d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/bundle.json","state_url":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T05:05:47Z","links":{"resolver":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA","bundle":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/bundle.json","state":"https://pith.science/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXZITQHJP2W2PXZXHQUWM7Q5YA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXZITQHJP2W2PXZXHQUWM7Q5YA","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":"55b55271409e42cadfadf0e217c69a3f6b536873e9f587a40b84a3942afc1b55","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:19:19Z","title_canon_sha256":"cefa869da2e3fab53b2c0a34042d12862674810d7cfd3ccb4a7484d1e59de837"},"schema_version":"1.0","source":{"id":"2405.20267","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20267","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20267v4","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20267","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"PXZITQHJP2W2","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"PXZITQHJP2W2PXZX","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"PXZITQHJ","created_at":"2026-07-05T09:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:a97125c30af9da77d2974ad3dc7ff1b9769f5da744eaea1b412b4e7603b1f0d8","target":"graph","created_at":"2026-07-05T09:16:49Z","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/2405.20267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Deli Zhao, Lidong Bing, Ruochen Zhao, Weiwen Xu, Wenxuan Zhang, Yew Ken Chia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:19:19Z","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20267","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":"sha256:2972d9ccb9f0ff0062bdb423ce359e87a47d5729a61cf5aeb66e0aa209f7e4a1","target":"record","created_at":"2026-07-05T09:16:49Z","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":"55b55271409e42cadfadf0e217c69a3f6b536873e9f587a40b84a3942afc1b55","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T17:19:19Z","title_canon_sha256":"cefa869da2e3fab53b2c0a34042d12862674810d7cfd3ccb4a7484d1e59de837"},"schema_version":"1.0","source":{"id":"2405.20267","kind":"arxiv","version":4}},"canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7df289c0e97eada7df373c29667e1dc033cc13d4aae0dcedb345ce65b22d7f77","first_computed_at":"2026-07-05T09:16:49.488201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:49.488201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zEPa9tUWe0ONs+9U4xcGS/Pc+0i3AoS0Utq1PAI9vDLjSuI/YJD6D+2kY+KH99HKI4LRP+/HKg32taWbkpimBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:49.488691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20267","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2972d9ccb9f0ff0062bdb423ce359e87a47d5729a61cf5aeb66e0aa209f7e4a1","sha256:a97125c30af9da77d2974ad3dc7ff1b9769f5da744eaea1b412b4e7603b1f0d8"],"state_sha256":"6ba1254c87522364eb28611cd197242328b78f704a211119032cb28c001532a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NnqSpWdpU7TkDopTEdfCflS0YN+xLyZSWSayzRBaZtGdEtTgLN8Aj0G6DHsuX7RJrS0sZDvWfjWZAY/QTbADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:05:47.028001Z","bundle_sha256":"03c56be5eacf5fdcfdf99aca1f36e674b7941a5161826e5f87e5ede9da26e1aa"}}