{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PKZQWL6EQOBGJCJ3LSI3RRSUVT","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":"f89cec4d95466f49d21021562315525282ce84be81d342bbe673a1b7aa076208","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T00:31:00Z","title_canon_sha256":"cfefbd8a498705e42055bd90f690e277114dfc99447c7f8a86fe6cc8c6585e4b"},"schema_version":"1.0","source":{"id":"2607.16239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16239","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16239v1","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16239","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"PKZQWL6EQOBG","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"PKZQWL6EQOBGJCJ3","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"PKZQWL6E","created_at":"2026-07-21T00:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:eb7aed3d7e4e9910282d4734de60b1b9ae1849d68eaa66ddde3c8952c30f6149","target":"graph","created_at":"2026-07-21T00:20:07Z","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/2607.16239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anlan Zhang, Avi Feller, David Arbour, Lei Shi, Rita Lyu, Ritwik Sinha, Saayan Mitra, Tong Yu, Zhengmian Hu","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T00:31:00Z","title":"BACON: Budgeted Human Calibration for Modeling and Evaluation with Multiple AI Judges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16239","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":"sha256:0ecbc2a7b0b23d178bfdecb8a8595f09ff607df19834cbca2bd1f7f802c8be37","target":"record","created_at":"2026-07-21T00:20:07Z","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":"f89cec4d95466f49d21021562315525282ce84be81d342bbe673a1b7aa076208","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T00:31:00Z","title_canon_sha256":"cfefbd8a498705e42055bd90f690e277114dfc99447c7f8a86fe6cc8c6585e4b"},"schema_version":"1.0","source":{"id":"2607.16239","kind":"arxiv","version":1}},"canonical_sha256":"7ab30b2fc4838264893b5c91b8c654acd7a98ff3dafebdfa50dd15e2e4f127df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ab30b2fc4838264893b5c91b8c654acd7a98ff3dafebdfa50dd15e2e4f127df","first_computed_at":"2026-07-21T00:20:07.517109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:07.517109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"29W8+kGlxPYAgc9H5giuMxwnU+5kxKLtSm5yypEoRDLH66TaGbrLvdrAvQB9ySRMFNS7Z39g7aU2GHtzhL3PAQ==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:07.517959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ecbc2a7b0b23d178bfdecb8a8595f09ff607df19834cbca2bd1f7f802c8be37","sha256:eb7aed3d7e4e9910282d4734de60b1b9ae1849d68eaa66ddde3c8952c30f6149"],"state_sha256":"5ce2a32d3dc8c790999bd9017151293a30c2c12a447c43f1407e485881572a00"}