{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TBY2NLQG6K6EC3BPV74CZ4C6SO","short_pith_number":"pith:TBY2NLQG","schema_version":"1.0","canonical_sha256":"9871a6ae06f2bc416c2faff82cf05e939ddb6fc0c31bd9aa3da36195495dfae0","source":{"kind":"arxiv","id":"2505.12808","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric P. Xing, Haojian Jin, Jieyuan Liu, Kun Zhou, Shibo Hao, Somanshu Singla, Tianyang Liu, Xiangdong Zhang, Yanbin Yin, Yifei Shao, Yi Gu, Zhengzhong Liu, Zhen Wang, Zhiting Hu","submitted_at":"2025-05-19T07:34:25Z","abstract_excerpt":"The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (eg MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (eg Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (eg LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few \"authority\" models. To tackle these issues, we propose Decentralized"},"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":"2505.12808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T07:34:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2e425f957e6ff96409a0f4b7621844c4cebcf9db84dd5a5bbfceecef476df0fe","abstract_canon_sha256":"e05b5bd87d335ca703eebd6fcc10f825a66fa3cbd90f8f7f5c3f1fee5bec4f3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:10.039976Z","signature_b64":"i0raXnMzNHruJwZA85XBfn+FmJO5I2jZWDv50bqva8nZap1JBNMM0c6DtsrwcK8pa5G32yMYKAHZ07nP6jpdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9871a6ae06f2bc416c2faff82cf05e939ddb6fc0c31bd9aa3da36195495dfae0","last_reissued_at":"2026-07-05T11:05:10.039533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:10.039533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric P. Xing, Haojian Jin, Jieyuan Liu, Kun Zhou, Shibo Hao, Somanshu Singla, Tianyang Liu, Xiangdong Zhang, Yanbin Yin, Yifei Shao, Yi Gu, Zhengzhong Liu, Zhen Wang, Zhiting Hu","submitted_at":"2025-05-19T07:34:25Z","abstract_excerpt":"The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever. Standard practices nowadays face fundamental trade-offs: closed-ended question-based benchmarks (eg MMLU) struggle with saturation as newer models emerge, while crowd-sourced leaderboards (eg Chatbot Arena) rely on costly and slow human judges. Recently, automated methods (eg LLM-as-a-judge) shed light on the scalability, but risk bias by relying on one or a few \"authority\" models. To tackle these issues, we propose Decentralized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12808","kind":"arxiv","version":1},"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/2505.12808/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":"2505.12808","created_at":"2026-07-05T11:05:10.039591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12808v1","created_at":"2026-07-05T11:05:10.039591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12808","created_at":"2026-07-05T11:05:10.039591+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBY2NLQG6K6E","created_at":"2026-07-05T11:05:10.039591+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBY2NLQG6K6EC3BP","created_at":"2026-07-05T11:05:10.039591+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBY2NLQG","created_at":"2026-07-05T11:05:10.039591+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO","json":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO.json","graph_json":"https://pith.science/api/pith-number/TBY2NLQG6K6EC3BPV74CZ4C6SO/graph.json","events_json":"https://pith.science/api/pith-number/TBY2NLQG6K6EC3BPV74CZ4C6SO/events.json","paper":"https://pith.science/paper/TBY2NLQG"},"agent_actions":{"view_html":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO","download_json":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO.json","view_paper":"https://pith.science/paper/TBY2NLQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12808&json=true","fetch_graph":"https://pith.science/api/pith-number/TBY2NLQG6K6EC3BPV74CZ4C6SO/graph.json","fetch_events":"https://pith.science/api/pith-number/TBY2NLQG6K6EC3BPV74CZ4C6SO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO/action/storage_attestation","attest_author":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO/action/author_attestation","sign_citation":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO/action/citation_signature","submit_replication":"https://pith.science/pith/TBY2NLQG6K6EC3BPV74CZ4C6SO/action/replication_record"}},"created_at":"2026-07-05T11:05:10.039591+00:00","updated_at":"2026-07-05T11:05:10.039591+00:00"}