{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PKZQWL6EQOBGJCJ3LSI3RRSUVT","short_pith_number":"pith:PKZQWL6E","schema_version":"1.0","canonical_sha256":"7ab30b2fc4838264893b5c91b8c654acd7a98ff3dafebdfa50dd15e2e4f127df","source":{"kind":"arxiv","id":"2607.16239","version":1},"attestation_state":"computed","paper":{"title":"BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.LG","authors_text":"Anlan Zhang, Avi Feller, David Arbour, Lei Shi, Rita Lyu, Ritwik Sinha, Saayan Mitra, Tong Yu, Zhengmian Hu","submitted_at":"2026-06-26T00:31:00Z","abstract_excerpt":"AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains. When uncalibrated AI evaluations are used for model ranking, item scoring, or population-level quality reporting, these biases can directly distort downstream decisions. We propose BACON, a four-stage pipeline that combines budgeted human calibration with multiple AI-judge outputs to produce more accurate annotations. BACON constructs full-coverage auxiliary features for every item, including mu"},"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":"2607.16239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T00:31:00Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"cfefbd8a498705e42055bd90f690e277114dfc99447c7f8a86fe6cc8c6585e4b","abstract_canon_sha256":"f89cec4d95466f49d21021562315525282ce84be81d342bbe673a1b7aa076208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:07.517959Z","signature_b64":"29W8+kGlxPYAgc9H5giuMxwnU+5kxKLtSm5yypEoRDLH66TaGbrLvdrAvQB9ySRMFNS7Z39g7aU2GHtzhL3PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ab30b2fc4838264893b5c91b8c654acd7a98ff3dafebdfa50dd15e2e4f127df","last_reissued_at":"2026-07-21T00:20:07.517109Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:07.517109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.LG","authors_text":"Anlan Zhang, Avi Feller, David Arbour, Lei Shi, Rita Lyu, Ritwik Sinha, Saayan Mitra, Tong Yu, Zhengmian Hu","submitted_at":"2026-06-26T00:31:00Z","abstract_excerpt":"AI judges offer a scalable, low-cost alternative to human evaluation, but their outputs can be biased relative to human preferences and highly item-dependent, varying across judges, tasks, and domains. When uncalibrated AI evaluations are used for model ranking, item scoring, or population-level quality reporting, these biases can directly distort downstream decisions. We propose BACON, a four-stage pipeline that combines budgeted human calibration with multiple AI-judge outputs to produce more accurate annotations. BACON constructs full-coverage auxiliary features for every item, including mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16239","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/2607.16239/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":"2607.16239","created_at":"2026-07-21T00:20:07.517552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16239v1","created_at":"2026-07-21T00:20:07.517552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16239","created_at":"2026-07-21T00:20:07.517552+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKZQWL6EQOBG","created_at":"2026-07-21T00:20:07.517552+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKZQWL6EQOBGJCJ3","created_at":"2026-07-21T00:20:07.517552+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKZQWL6E","created_at":"2026-07-21T00:20:07.517552+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/PKZQWL6EQOBGJCJ3LSI3RRSUVT","json":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT.json","graph_json":"https://pith.science/api/pith-number/PKZQWL6EQOBGJCJ3LSI3RRSUVT/graph.json","events_json":"https://pith.science/api/pith-number/PKZQWL6EQOBGJCJ3LSI3RRSUVT/events.json","paper":"https://pith.science/paper/PKZQWL6E"},"agent_actions":{"view_html":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT","download_json":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT.json","view_paper":"https://pith.science/paper/PKZQWL6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16239&json=true","fetch_graph":"https://pith.science/api/pith-number/PKZQWL6EQOBGJCJ3LSI3RRSUVT/graph.json","fetch_events":"https://pith.science/api/pith-number/PKZQWL6EQOBGJCJ3LSI3RRSUVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT/action/storage_attestation","attest_author":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT/action/author_attestation","sign_citation":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT/action/citation_signature","submit_replication":"https://pith.science/pith/PKZQWL6EQOBGJCJ3LSI3RRSUVT/action/replication_record"}},"created_at":"2026-07-21T00:20:07.517552+00:00","updated_at":"2026-07-21T00:20:07.517552+00:00"}