{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TC4WMJGLAO4BZBANMZOBVMJQNA","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":"5a97bf9dd44973df35faa3aa3c83cb33b9b516e8f5e0a2c0b6bc46a39683476d","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:26:08Z","title_canon_sha256":"157886ee4ba55b5bcbbf6334ed57396825662cd8d457360fa028982b60911ae4"},"schema_version":"1.0","source":{"id":"2605.23362","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23362","created_at":"2026-05-25T02:01:50Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23362v1","created_at":"2026-05-25T02:01:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23362","created_at":"2026-05-25T02:01:50Z"},{"alias_kind":"pith_short_12","alias_value":"TC4WMJGLAO4B","created_at":"2026-05-25T02:01:50Z"},{"alias_kind":"pith_short_16","alias_value":"TC4WMJGLAO4BZBAN","created_at":"2026-05-25T02:01:50Z"},{"alias_kind":"pith_short_8","alias_value":"TC4WMJGL","created_at":"2026-05-25T02:01:50Z"}],"graph_snapshots":[{"event_id":"sha256:451beac4cc4a719d686d4c50fed217eb7a1b54de62ac03c4eeca53572a19040f","target":"graph","created_at":"2026-05-25T02:01:50Z","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/2605.23362/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating large language models increasingly relies on LLM-as-a-judge protocols, but such evaluations remain costly: different judges have different prices and reliabilities, and the difficulty of each prompt-response pair can vary substantially. This raises a basic allocation question: under a fixed budget, how should one distribute evaluation queries across heterogeneous judges and instances to obtain the most accurate score estimates? We formalize this question as *budgeted heteroskedastic multi-judge estimation*. Given $K$ prompt-response pairs, $J$ judges with known costs, and unknown qu","authors_text":"Alexandre Prouti\\`ere, Junghyun Lee, Sanghwa Kim, Se-Young Yun, Yassir Jedra","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:26:08Z","title":"Instance-Optimal Estimation with Multiple LLM Judges on a Budget"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23362","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":"sha256:911a871d0abc0fcef518b0ac5ffc4250d3700f4576c17af87a293fd080183e87","target":"record","created_at":"2026-05-25T02:01:50Z","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":"5a97bf9dd44973df35faa3aa3c83cb33b9b516e8f5e0a2c0b6bc46a39683476d","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:26:08Z","title_canon_sha256":"157886ee4ba55b5bcbbf6334ed57396825662cd8d457360fa028982b60911ae4"},"schema_version":"1.0","source":{"id":"2605.23362","kind":"arxiv","version":1}},"canonical_sha256":"98b96624cb03b81c840d665c1ab1306817c5df83ec44952bbc8d931cdd8e4f7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98b96624cb03b81c840d665c1ab1306817c5df83ec44952bbc8d931cdd8e4f7d","first_computed_at":"2026-05-25T02:01:50.843602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:50.843602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+E9l1sp9jQ5it5DWfcssK5vvkG1tb98Jnpz/ohNBXTE6aqNV/rlYGF8RWMKyrkkVqaFTuFYmH9oznmva/geBQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:50.844450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23362","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:911a871d0abc0fcef518b0ac5ffc4250d3700f4576c17af87a293fd080183e87","sha256:451beac4cc4a719d686d4c50fed217eb7a1b54de62ac03c4eeca53572a19040f"],"state_sha256":"b24e79f893abb1be43e6c4085ba63aff01f5b6c31c26576b6df636786926d618"}