{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YCJH37LN6QT4MRJKJ5C7ROZTLK","short_pith_number":"pith:YCJH37LN","schema_version":"1.0","canonical_sha256":"c0927dfd6df427c6452a4f45f8bb335aa49ea4e6031582c08b49e035a4fe8c1c","source":{"kind":"arxiv","id":"2606.01034","version":1},"attestation_state":"computed","paper":{"title":"A Finite-Calibration Regime Map for LLM Judge Panels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Bin Zhu, Yanghui Rao","submitted_at":"2026-05-31T05:50:27Z","abstract_excerpt":"We study when LLM judge panels should be calibrated with low-dimensional stackers versus joint output tables under finite human-label budgets. Low-dimensional stackers have small estimation cost but miss interactions, whereas joint-table calibrators can represent interactions but pay for cell counts and unseen patterns. We cast this tradeoff as a finite-calibration regime map and instantiate it as Finite-Calibration Panel Selection, a deployable validation selector over judge path, prefix size, and aggregator family with table and parametric estimation diagnostics. On RewardBench, LLMBar, Summ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.01034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T05:50:27Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"d9cfafb667aca9aa951df7cae52049ba280b71d591ddadb59149c89b4388ac84","abstract_canon_sha256":"e5dccae1dc9fb1b4e0afbee45726f357bc35892dcb95616fd8143763afcc7abe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:19.117939Z","signature_b64":"TmNP+PFgOef6l8fHZ4veGB/2SRMVfu103QZqGny49mUIcu0r9/7aJafRZ7z7k6iUCFSaSqZ7CttJHpgg9iALCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0927dfd6df427c6452a4f45f8bb335aa49ea4e6031582c08b49e035a4fe8c1c","last_reissued_at":"2026-06-02T01:04:19.117520Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:19.117520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Finite-Calibration Regime Map for LLM Judge Panels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Bin Zhu, Yanghui Rao","submitted_at":"2026-05-31T05:50:27Z","abstract_excerpt":"We study when LLM judge panels should be calibrated with low-dimensional stackers versus joint output tables under finite human-label budgets. Low-dimensional stackers have small estimation cost but miss interactions, whereas joint-table calibrators can represent interactions but pay for cell counts and unseen patterns. We cast this tradeoff as a finite-calibration regime map and instantiate it as Finite-Calibration Panel Selection, a deployable validation selector over judge path, prefix size, and aggregator family with table and parametric estimation diagnostics. On RewardBench, LLMBar, Summ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01034","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/2606.01034/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.01034","created_at":"2026-06-02T01:04:19.117585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01034v1","created_at":"2026-06-02T01:04:19.117585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01034","created_at":"2026-06-02T01:04:19.117585+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCJH37LN6QT4","created_at":"2026-06-02T01:04:19.117585+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCJH37LN6QT4MRJK","created_at":"2026-06-02T01:04:19.117585+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCJH37LN","created_at":"2026-06-02T01:04:19.117585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK","json":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK.json","graph_json":"https://pith.science/api/pith-number/YCJH37LN6QT4MRJKJ5C7ROZTLK/graph.json","events_json":"https://pith.science/api/pith-number/YCJH37LN6QT4MRJKJ5C7ROZTLK/events.json","paper":"https://pith.science/paper/YCJH37LN"},"agent_actions":{"view_html":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK","download_json":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK.json","view_paper":"https://pith.science/paper/YCJH37LN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01034&json=true","fetch_graph":"https://pith.science/api/pith-number/YCJH37LN6QT4MRJKJ5C7ROZTLK/graph.json","fetch_events":"https://pith.science/api/pith-number/YCJH37LN6QT4MRJKJ5C7ROZTLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK/action/storage_attestation","attest_author":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK/action/author_attestation","sign_citation":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK/action/citation_signature","submit_replication":"https://pith.science/pith/YCJH37LN6QT4MRJKJ5C7ROZTLK/action/replication_record"}},"created_at":"2026-06-02T01:04:19.117585+00:00","updated_at":"2026-06-02T01:04:19.117585+00:00"}