{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TC4WMJGLAO4BZBANMZOBVMJQNA","short_pith_number":"pith:TC4WMJGL","canonical_record":{"source":{"id":"2605.23362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:26:08Z","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"157886ee4ba55b5bcbbf6334ed57396825662cd8d457360fa028982b60911ae4","abstract_canon_sha256":"5a97bf9dd44973df35faa3aa3c83cb33b9b516e8f5e0a2c0b6bc46a39683476d"},"schema_version":"1.0"},"canonical_sha256":"98b96624cb03b81c840d665c1ab1306817c5df83ec44952bbc8d931cdd8e4f7d","source":{"kind":"arxiv","id":"2605.23362","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TC4WMJGLAO4BZBANMZOBVMJQNA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T08:26:08Z","cross_cats_sorted":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"157886ee4ba55b5bcbbf6334ed57396825662cd8d457360fa028982b60911ae4","abstract_canon_sha256":"5a97bf9dd44973df35faa3aa3c83cb33b9b516e8f5e0a2c0b6bc46a39683476d"},"schema_version":"1.0"},"canonical_sha256":"98b96624cb03b81c840d665c1ab1306817c5df83ec44952bbc8d931cdd8e4f7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:50.844450Z","signature_b64":"R+E9l1sp9jQ5it5DWfcssK5vvkG1tb98Jnpz/ohNBXTE6aqNV/rlYGF8RWMKyrkkVqaFTuFYmH9oznmva/geBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b96624cb03b81c840d665c1ab1306817c5df83ec44952bbc8d931cdd8e4f7d","last_reissued_at":"2026-05-25T02:01:50.843602Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:50.843602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23362","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kYNdFMK9vL0z4Suu9RT/U0Ac0Co5XcS85CTzqazjQTEVanjdqJ6tWpcAfdN8rtMXujflyVx0lo7UVq48N4j7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:41:37.767748Z"},"content_sha256":"911a871d0abc0fcef518b0ac5ffc4250d3700f4576c17af87a293fd080183e87","schema_version":"1.0","event_id":"sha256:911a871d0abc0fcef518b0ac5ffc4250d3700f4576c17af87a293fd080183e87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TC4WMJGLAO4BZBANMZOBVMJQNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instance-Optimal Estimation with Multiple LLM Judges on a Budget","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","math.IT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Alexandre Prouti\\`ere, Junghyun Lee, Sanghwa Kim, Se-Young Yun, Yassir Jedra","submitted_at":"2026-05-22T08:26:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23362","kind":"arxiv","version":1},"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/2605.23362/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":"2026-05-25T02:01:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3w8hu3AxN1DcTR1QY3nDqwQSU06yHVBoCqlJBBfGpSCHuh11uPtQw73j/ml8paWfBE/RNAtWBqFwglrv50ifDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T11:41:37.768211Z"},"content_sha256":"451beac4cc4a719d686d4c50fed217eb7a1b54de62ac03c4eeca53572a19040f","schema_version":"1.0","event_id":"sha256:451beac4cc4a719d686d4c50fed217eb7a1b54de62ac03c4eeca53572a19040f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/bundle.json","state_url":"https://pith.science/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/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":"2026-05-25T11:41:37Z","links":{"resolver":"https://pith.science/pith/TC4WMJGLAO4BZBANMZOBVMJQNA","bundle":"https://pith.science/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/bundle.json","state":"https://pith.science/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TC4WMJGLAO4BZBANMZOBVMJQNA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xqyElz3NDRUFc/GUVwCOB2nn/GYIpghqls2E/5DXouI16wtpNiUHJFMg40twz5Nctf727utM4ylPaxcZF+7pBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T11:41:37.771330Z","bundle_sha256":"ae6b3ac8e23a38ca6d0f8d7a50e8c6ac7ce9c250e0710238275f0efb14bf2c3a"}}