{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6WMOTI6R76G56MXQ33HUFRGZPO","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":"1d3993a54e90bac3c1d970c7f87c4399e2c80943cfc41e78f4f24a44290d3e22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T02:08:51Z","title_canon_sha256":"d70bd43b7dbf1c4653e708ff02f465a647221486486d5286895e26786a962886"},"schema_version":"1.0","source":{"id":"2504.12589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12589","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12589v1","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12589","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"6WMOTI6R76G5","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"6WMOTI6R76G56MXQ","created_at":"2026-07-05T10:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"6WMOTI6R","created_at":"2026-07-05T10:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:d20f1ea61c4301b2ea3707a9d10909d058d38d742711d76ddc8f9a3176868bbc","target":"graph","created_at":"2026-07-05T10:50:19Z","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/2504.12589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM ensembles are widely used for LLM judges. However, how to estimate their accuracy, especially in an efficient way, is unknown. In this paper, we present a principled maximum a posteriori (MAP) framework for an economical and precise estimation of the performance of LLM ensemble judgment. We first propose a mixture of Beta-Binomial distributions to model the judgment distribution, revising from the vanilla Binomial distribution. Next, we introduce a conformal prediction-driven approach that enables adaptive stopping during iterative sampling to balance accuracy with efficiency. Furthermore,","authors_text":"Faizan Siddiqui, Huaizhi Qu, Inyoung Choi, Kwonjoon Lee, Qi Long, Song Wang, Sukwon Yun, Tianlong Chen, Zhen Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T02:08:51Z","title":"Efficient MAP Estimation of LLM Judgment Performance with Prior Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12589","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:ce46a7101da98276a5712fed90b100953f589e9c7b25e836f311e342c7fefa01","target":"record","created_at":"2026-07-05T10:50:19Z","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":"1d3993a54e90bac3c1d970c7f87c4399e2c80943cfc41e78f4f24a44290d3e22","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-17T02:08:51Z","title_canon_sha256":"d70bd43b7dbf1c4653e708ff02f465a647221486486d5286895e26786a962886"},"schema_version":"1.0","source":{"id":"2504.12589","kind":"arxiv","version":1}},"canonical_sha256":"f598e9a3d1ff8ddf32f0decf42c4d97bb14d49ab9c0e9abb8beb47e23c13d195","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f598e9a3d1ff8ddf32f0decf42c4d97bb14d49ab9c0e9abb8beb47e23c13d195","first_computed_at":"2026-07-05T10:50:19.116097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:19.116097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dbzstiHhtm5thLG/fg8rM7Q1flWWcsMkds/i/S4Xmyod+bODAGOyqR4MNelf8Hu4Fl32NWZxK+HrMQWFThMJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:19.116604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce46a7101da98276a5712fed90b100953f589e9c7b25e836f311e342c7fefa01","sha256:d20f1ea61c4301b2ea3707a9d10909d058d38d742711d76ddc8f9a3176868bbc"],"state_sha256":"fb3d21dc5bdafd573e1c2e34894b0a9035cd167161bd5963627b4200de8a09d0"}