{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BSWKFUJEEH2WKLHTIYUTIUJ6PT","short_pith_number":"pith:BSWKFUJE","canonical_record":{"source":{"id":"2505.03475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T12:28:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3626894074623880c61cf5a2b991cf865e323e15ebe1f141d9e4b34a2309310","abstract_canon_sha256":"228199e715121b521e1436cfaf4a459ee7b1b53d62dacfff8ac69b838ab8fbd9"},"schema_version":"1.0"},"canonical_sha256":"0caca2d12421f5652cf3462934513e7cd32bb4228871780653bed6cfa2b11573","source":{"kind":"arxiv","id":"2505.03475","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03475","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03475v2","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03475","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"BSWKFUJEEH2W","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"BSWKFUJEEH2WKLHT","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"BSWKFUJE","created_at":"2026-07-05T11:11:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BSWKFUJEEH2WKLHTIYUTIUJ6PT","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T12:28:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b3626894074623880c61cf5a2b991cf865e323e15ebe1f141d9e4b34a2309310","abstract_canon_sha256":"228199e715121b521e1436cfaf4a459ee7b1b53d62dacfff8ac69b838ab8fbd9"},"schema_version":"1.0"},"canonical_sha256":"0caca2d12421f5652cf3462934513e7cd32bb4228871780653bed6cfa2b11573","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:44.702609Z","signature_b64":"r8aHK7klLY439+CBFWR6TuWQ07D5Huquz9TG2hUOMppjYmsKz+gdzVMZyb/MHdl3dHgk33uPmVClNf5S6+QLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0caca2d12421f5652cf3462934513e7cd32bb4228871780653bed6cfa2b11573","last_reissued_at":"2026-07-05T11:11:44.702126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:44.702126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03475","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:11:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mV73Ko1I3ZZqURS9mKZUyeXcNOXA9S+stVoebdBDbPuN+6W/azLvbzeKUAifb+92MvfkH70249cGBY/4+ZKxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:53:24.813073Z"},"content_sha256":"442d1f6b5d3d710bbb343af31b332073f82ef019ef3b764599163d16b43fd937","schema_version":"1.0","event_id":"sha256:442d1f6b5d3d710bbb343af31b332073f82ef019ef3b764599163d16b43fd937"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BSWKFUJEEH2WKLHTIYUTIUJ6PT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"am-ELO: A Stable Framework for Arena-based LLM Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiatong Li, Jie Ouyang, Mingyue Cheng, Qi Liu, Shijin Wang, Shuanghong Shen, Yan Zhuang, Zirui Liu","submitted_at":"2025-05-06T12:28:50Z","abstract_excerpt":"Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03475","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/2505.03475/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":"2026-07-05T11:11:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qFjE/eO1ZARU7UlOsxupEzjilQic/DimkNaSzCbLZ8xXpCCzNVDFsR9hPfuNEll52PUb1kZC6NS/NR9T11aoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T09:53:24.813572Z"},"content_sha256":"eb66f7686efe640e177c1672157b284e58827e03895e84abe70849bdcefac5a7","schema_version":"1.0","event_id":"sha256:eb66f7686efe640e177c1672157b284e58827e03895e84abe70849bdcefac5a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/bundle.json","state_url":"https://pith.science/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/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":"2026-08-13T09:53:24Z","links":{"resolver":"https://pith.science/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT","bundle":"https://pith.science/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/bundle.json","state":"https://pith.science/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSWKFUJEEH2WKLHTIYUTIUJ6PT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BSWKFUJEEH2WKLHTIYUTIUJ6PT","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":"228199e715121b521e1436cfaf4a459ee7b1b53d62dacfff8ac69b838ab8fbd9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T12:28:50Z","title_canon_sha256":"b3626894074623880c61cf5a2b991cf865e323e15ebe1f141d9e4b34a2309310"},"schema_version":"1.0","source":{"id":"2505.03475","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03475","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03475v2","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03475","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"BSWKFUJEEH2W","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"BSWKFUJEEH2WKLHT","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"BSWKFUJE","created_at":"2026-07-05T11:11:44Z"}],"graph_snapshots":[{"event_id":"sha256:eb66f7686efe640e177c1672157b284e58827e03895e84abe70849bdcefac5a7","target":"graph","created_at":"2026-07-05T11:11:44Z","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/2505.03475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Arena-based evaluation is a fundamental yet significant evaluation paradigm for modern AI models, especially large language models (LLMs). Existing framework based on ELO rating system suffers from the inevitable instability problem due to ranking inconsistency and the lack of attention to the varying abilities of annotators. In this paper, we introduce a novel stable arena framework to address these issues by enhancing the ELO Rating System. Specifically, we replace the iterative update method with a Maximum Likelihood Estimation (MLE) approach, m-ELO, and provide theoretical proof of the con","authors_text":"Jiatong Li, Jie Ouyang, Mingyue Cheng, Qi Liu, Shijin Wang, Shuanghong Shen, Yan Zhuang, Zirui Liu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T12:28:50Z","title":"am-ELO: A Stable Framework for Arena-based LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03475","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":"sha256:442d1f6b5d3d710bbb343af31b332073f82ef019ef3b764599163d16b43fd937","target":"record","created_at":"2026-07-05T11:11:44Z","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":"228199e715121b521e1436cfaf4a459ee7b1b53d62dacfff8ac69b838ab8fbd9","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-06T12:28:50Z","title_canon_sha256":"b3626894074623880c61cf5a2b991cf865e323e15ebe1f141d9e4b34a2309310"},"schema_version":"1.0","source":{"id":"2505.03475","kind":"arxiv","version":2}},"canonical_sha256":"0caca2d12421f5652cf3462934513e7cd32bb4228871780653bed6cfa2b11573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0caca2d12421f5652cf3462934513e7cd32bb4228871780653bed6cfa2b11573","first_computed_at":"2026-07-05T11:11:44.702126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:44.702126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r8aHK7klLY439+CBFWR6TuWQ07D5Huquz9TG2hUOMppjYmsKz+gdzVMZyb/MHdl3dHgk33uPmVClNf5S6+QLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:44.702609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03475","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:442d1f6b5d3d710bbb343af31b332073f82ef019ef3b764599163d16b43fd937","sha256:eb66f7686efe640e177c1672157b284e58827e03895e84abe70849bdcefac5a7"],"state_sha256":"5318c3e2b31c9e250314ea3385b3a1b309a706e25f996008daa70b2929b432d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SlwSj6/SyAnEiLFc8OiemkhfqbsbJKImnmkciPV1JCkngLFbjjybZLSp4a0dq1E+/vF0CQpHOJJJdKAXnHm+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T09:53:24.817707Z","bundle_sha256":"12005d46c58b1293c9388f3e91b53995ac566a8573c0c8878987a20e4a73dd99"}}