{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I5OKMWEKX2FOWWPHXVQ6ZNOACE","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":"9aa37d9920370dc6dae09d061b9e4d6166a15990c66e4f423b79db51be1d9572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T11:48:17Z","title_canon_sha256":"683a7f880f0d1fbc18ca14e27a13504a1aba01e00fba1b6a03b3772412fd4325"},"schema_version":"1.0","source":{"id":"2605.29800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29800","created_at":"2026-05-29T02:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29800v1","created_at":"2026-05-29T02:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29800","created_at":"2026-05-29T02:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"I5OKMWEKX2FO","created_at":"2026-05-29T02:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"I5OKMWEKX2FOWWPH","created_at":"2026-05-29T02:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"I5OKMWEK","created_at":"2026-05-29T02:05:53Z"}],"graph_snapshots":[{"event_id":"sha256:b5181a30947742f2d7e6657c80dffbc13546934a654879a85cacea08daa6f241","target":"graph","created_at":"2026-05-29T02:05:53Z","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/2605.29800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM-as-a-judge panels aggregate votes from multiple models, with the expectation that diverse models yield more reliable evaluations. We develop a framework to measure the true informational value of such panels and quantify how far their reliability falls short of the independent-voting ideal. Testing a panel of 9 frontier LLMs from 7 model families on three natural language inference datasets (each with 100 human annotations per item), we find that the 9 judges effectively provide only about 2 independent votes' worth of information. Roughly three-quarters of the panel's nominal independence","authors_text":"Guneet Kohli","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T11:48:17Z","title":"Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29800","kind":"arxiv","version":1},"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:d4267c6cb3322c13bae322ea6e045c8575acd6d42b8645764225ff5bf956a84d","target":"record","created_at":"2026-05-29T02:05:53Z","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":"9aa37d9920370dc6dae09d061b9e4d6166a15990c66e4f423b79db51be1d9572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T11:48:17Z","title_canon_sha256":"683a7f880f0d1fbc18ca14e27a13504a1aba01e00fba1b6a03b3772412fd4325"},"schema_version":"1.0","source":{"id":"2605.29800","kind":"arxiv","version":1}},"canonical_sha256":"475ca6588abe8aeb59e7bd61ecb5c0110e6ad3e9674cf3b10da68caa840aa355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"475ca6588abe8aeb59e7bd61ecb5c0110e6ad3e9674cf3b10da68caa840aa355","first_computed_at":"2026-05-29T02:05:53.054355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:53.054355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tN+IBbL8JgI6iSt5aKTbIRMhFAshqDVSYl8omXGLRuzy/ryPH1Z3OSH+littp8tiiKB2COE1SuvdWe/AI+QlAA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:53.055083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4267c6cb3322c13bae322ea6e045c8575acd6d42b8645764225ff5bf956a84d","sha256:b5181a30947742f2d7e6657c80dffbc13546934a654879a85cacea08daa6f241"],"state_sha256":"db10b41fe162d90df4e041b303e0c36926605d9a6e078c563cc35a53798c8eea"}