{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CVKUROCCVEMGDBCA6XXC3AYTNW","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":"2c9f4624d135604100504c581f551077d8f024cd94f48b6f7266bf160a3458d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-01-29T15:01:28Z","title_canon_sha256":"44d5c5f4c594fe4b37f68815cd8ccc8b2b55a51688adb71083b5fe2bfcb9abfb"},"schema_version":"1.0","source":{"id":"2601.21817","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21817","created_at":"2026-06-05T01:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21817v2","created_at":"2026-06-05T01:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21817","created_at":"2026-06-05T01:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"CVKUROCCVEMG","created_at":"2026-06-05T01:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"CVKUROCCVEMGDBCA","created_at":"2026-06-05T01:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"CVKUROCC","created_at":"2026-06-05T01:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:8fde5d03c9bb76d6f468620da24a730a21859c3ba14a3aaff891f2a19f94f1b5","target":"graph","created_at":"2026-06-05T01:14:33Z","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/2601.21817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates. More data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and ","authors_text":"Doudou Zhou, Jiawei Wu, Mingyuan Xu, Xinzi Tan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-01-29T15:01:28Z","title":"A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21817","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:dc81409782d0489908db93ed4b27a9a922ffb19aacbe812eda03f0567f7f0449","target":"record","created_at":"2026-06-05T01:14:33Z","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":"2c9f4624d135604100504c581f551077d8f024cd94f48b6f7266bf160a3458d3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-01-29T15:01:28Z","title_canon_sha256":"44d5c5f4c594fe4b37f68815cd8ccc8b2b55a51688adb71083b5fe2bfcb9abfb"},"schema_version":"1.0","source":{"id":"2601.21817","kind":"arxiv","version":2}},"canonical_sha256":"155548b842a918618440f5ee2d83136d99b19e18245dd34de5ee171fa44ffded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"155548b842a918618440f5ee2d83136d99b19e18245dd34de5ee171fa44ffded","first_computed_at":"2026-06-05T01:14:33.824115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:33.824115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jNxV8cL6MZLAbFJrduHCs0VHcJvlDvBU1JjpHKhhi4umjFo3AjwgDvL003seBZe2Yr8SWujX98p56YwPVSx+AQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:33.824922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21817","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc81409782d0489908db93ed4b27a9a922ffb19aacbe812eda03f0567f7f0449","sha256:8fde5d03c9bb76d6f468620da24a730a21859c3ba14a3aaff891f2a19f94f1b5"],"state_sha256":"64a67a97ad5d55fd3d9b74ded5b5e8a171cc46b7069a430d1de149a6293dfb30"}