{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6B7T7PR3BQLRDHF3PU4WGFFSDV","short_pith_number":"pith:6B7T7PR3","canonical_record":{"source":{"id":"2209.15154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"62bf710ca1dbaa82e337993f7d08e991e7b9d5f501f424067f41d3637e485ff8","abstract_canon_sha256":"cf1cf2b50c768c7765022bdc536cce4ae1edd24bef00f566641b10ddf5dea872"},"schema_version":"1.0"},"canonical_sha256":"f07f3fbe3b0c17119cbb7d396314b21d53c58832c50c2c8d859690d06437bd0c","source":{"kind":"arxiv","id":"2209.15154","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15154","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15154v3","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15154","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"6B7T7PR3BQLR","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"6B7T7PR3BQLRDHF3","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"6B7T7PR3","created_at":"2026-07-05T05:58:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6B7T7PR3BQLRDHF3PU4WGFFSDV","target":"record","payload":{"canonical_record":{"source":{"id":"2209.15154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:49:31Z","cross_cats_sorted":[],"title_canon_sha256":"62bf710ca1dbaa82e337993f7d08e991e7b9d5f501f424067f41d3637e485ff8","abstract_canon_sha256":"cf1cf2b50c768c7765022bdc536cce4ae1edd24bef00f566641b10ddf5dea872"},"schema_version":"1.0"},"canonical_sha256":"f07f3fbe3b0c17119cbb7d396314b21d53c58832c50c2c8d859690d06437bd0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:28.638900Z","signature_b64":"Sp49Ky5QCehhZMZJLPE7/SJVlEOdI0nDSbAE3lMtgxqSE6VmPA/glC03xtiJBKNRi1VQLHJiHxsT5VZxIJiyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f07f3fbe3b0c17119cbb7d396314b21d53c58832c50c2c8d859690d06437bd0c","last_reissued_at":"2026-07-05T05:58:28.638512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:28.638512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.15154","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"driW0560rQqTOijrpEnWARfcQoyNu01IBsIZz0e+G3fpmxxUp9XWPP8TR7bU2nWg6I5VwaxwC6T+ot8F5Gu5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:55:28.160550Z"},"content_sha256":"25590d2ab8dc7707cbfe749d79f422f0e7f21155904e9969703c541d2807cceb","schema_version":"1.0","event_id":"sha256:25590d2ab8dc7707cbfe749d79f422f0e7f21155904e9969703c541d2807cceb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6B7T7PR3BQLRDHF3PU4WGFFSDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variable-Based Calibration for Machine Learning Classifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Markelle Kelly, Padhraic Smyth","submitted_at":"2022-09-30T00:49:31Z","abstract_excerpt":"The deployment of machine learning classifiers in high-stakes domains requires well-calibrated confidence scores for model predictions. In this paper we introduce the notion of variable-based calibration to characterize calibration properties of a model with respect to a variable of interest, generalizing traditional score-based metrics such as expected calibration error (ECE). In particular, we find that models with near-perfect ECE can exhibit significant miscalibration as a function of features of the data. We demonstrate this phenomenon both theoretically and in practice on multiple well-k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15154","kind":"arxiv","version":3},"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/2209.15154/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":"2026-07-05T05:58:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DoQY6lVHwk4egxO+z5KC3RTU24gf9FvnAky/yc/cTv+Q7fI8DwGrOWhT6+SgKmkrjALe15V9VebETHGELegDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T07:55:28.160909Z"},"content_sha256":"9b91e20b996425d75239ce4929aa5f69f8d131bec401caf72db1b6ced67f867d","schema_version":"1.0","event_id":"sha256:9b91e20b996425d75239ce4929aa5f69f8d131bec401caf72db1b6ced67f867d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/bundle.json","state_url":"https://pith.science/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/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":"2026-07-17T07:55:28Z","links":{"resolver":"https://pith.science/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV","bundle":"https://pith.science/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/bundle.json","state":"https://pith.science/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6B7T7PR3BQLRDHF3PU4WGFFSDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6B7T7PR3BQLRDHF3PU4WGFFSDV","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":"cf1cf2b50c768c7765022bdc536cce4ae1edd24bef00f566641b10ddf5dea872","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:49:31Z","title_canon_sha256":"62bf710ca1dbaa82e337993f7d08e991e7b9d5f501f424067f41d3637e485ff8"},"schema_version":"1.0","source":{"id":"2209.15154","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.15154","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"arxiv_version","alias_value":"2209.15154v3","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15154","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_12","alias_value":"6B7T7PR3BQLR","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_16","alias_value":"6B7T7PR3BQLRDHF3","created_at":"2026-07-05T05:58:28Z"},{"alias_kind":"pith_short_8","alias_value":"6B7T7PR3","created_at":"2026-07-05T05:58:28Z"}],"graph_snapshots":[{"event_id":"sha256:9b91e20b996425d75239ce4929aa5f69f8d131bec401caf72db1b6ced67f867d","target":"graph","created_at":"2026-07-05T05:58:28Z","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/2209.15154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The deployment of machine learning classifiers in high-stakes domains requires well-calibrated confidence scores for model predictions. In this paper we introduce the notion of variable-based calibration to characterize calibration properties of a model with respect to a variable of interest, generalizing traditional score-based metrics such as expected calibration error (ECE). In particular, we find that models with near-perfect ECE can exhibit significant miscalibration as a function of features of the data. We demonstrate this phenomenon both theoretically and in practice on multiple well-k","authors_text":"Markelle Kelly, Padhraic Smyth","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:49:31Z","title":"Variable-Based Calibration for Machine Learning Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15154","kind":"arxiv","version":3},"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":"sha256:25590d2ab8dc7707cbfe749d79f422f0e7f21155904e9969703c541d2807cceb","target":"record","created_at":"2026-07-05T05:58:28Z","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":"cf1cf2b50c768c7765022bdc536cce4ae1edd24bef00f566641b10ddf5dea872","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T00:49:31Z","title_canon_sha256":"62bf710ca1dbaa82e337993f7d08e991e7b9d5f501f424067f41d3637e485ff8"},"schema_version":"1.0","source":{"id":"2209.15154","kind":"arxiv","version":3}},"canonical_sha256":"f07f3fbe3b0c17119cbb7d396314b21d53c58832c50c2c8d859690d06437bd0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f07f3fbe3b0c17119cbb7d396314b21d53c58832c50c2c8d859690d06437bd0c","first_computed_at":"2026-07-05T05:58:28.638512Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:28.638512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sp49Ky5QCehhZMZJLPE7/SJVlEOdI0nDSbAE3lMtgxqSE6VmPA/glC03xtiJBKNRi1VQLHJiHxsT5VZxIJiyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:28.638900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.15154","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25590d2ab8dc7707cbfe749d79f422f0e7f21155904e9969703c541d2807cceb","sha256:9b91e20b996425d75239ce4929aa5f69f8d131bec401caf72db1b6ced67f867d"],"state_sha256":"c8f22934824523a3df908fee4fb1b414ee65112a8d050ebbbeab2b2bcff1ab25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2aOgGX/MZU06kxigzYpFN304dSH0T/FFqid0dn/Yh1hAp1wAmWWpAkA9wkepeKMDOEpkCSAf5jkANrb2yxsEDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T07:55:28.163427Z","bundle_sha256":"cbd3cb8466c626be7f164e817ed1de1a5a40986b4ab23b6f6d853b92399cb682"}}