{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2BRKM65PHXOGMNRMIZDRKIXVRD","short_pith_number":"pith:2BRKM65P","canonical_record":{"source":{"id":"2012.15259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T18:15:05Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"d75205b0377412394ff350affaef255b2f743dbae1ddf96dad5990c366ce0ad5","abstract_canon_sha256":"7c1323d34358bd7b27fd15353d6a2e2c77c75890e758af4954bed308276f8847"},"schema_version":"1.0"},"canonical_sha256":"d062a67baf3ddc66362c46471522f588cfc04286dfd9dc401b21c2a8b1380e7a","source":{"kind":"arxiv","id":"2012.15259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15259","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15259v1","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15259","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"2BRKM65PHXOG","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"2BRKM65PHXOGMNRM","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"2BRKM65P","created_at":"2026-07-05T02:03:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2BRKM65PHXOGMNRMIZDRKIXVRD","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T18:15:05Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"d75205b0377412394ff350affaef255b2f743dbae1ddf96dad5990c366ce0ad5","abstract_canon_sha256":"7c1323d34358bd7b27fd15353d6a2e2c77c75890e758af4954bed308276f8847"},"schema_version":"1.0"},"canonical_sha256":"d062a67baf3ddc66362c46471522f588cfc04286dfd9dc401b21c2a8b1380e7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:06.138672Z","signature_b64":"2r3ZgiYGmaMOV8SylsEDOrr5vPPtmaxOSfQP1MPfWZEPmIpF7EYw+6SIpKiY9an/RkPRJp7LhrJuMFZYULQ2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d062a67baf3ddc66362c46471522f588cfc04286dfd9dc401b21c2a8b1380e7a","last_reissued_at":"2026-07-05T02:03:06.138326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:06.138326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15259","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":"2026-07-05T02:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c703kTITK/ywYGjF+2SIke5CN42+ur4YIisDIwLP4r5sSjQWuFi7GBVpLuyBp7D65W+d3Swl+uT392FNDkMeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:04:48.703544Z"},"content_sha256":"c44c4961922d946af7f076cca6ec7edde663bd9478df68f66beb26a4e2193b60","schema_version":"1.0","event_id":"sha256:c44c4961922d946af7f076cca6ec7edde663bd9478df68f66beb26a4e2193b60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2BRKM65PHXOGMNRMIZDRKIXVRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Maximal Correlation Approach to Imposing Fairness in Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Wornell, Joshua Lee, Leonid Karlinsky, Prasanna Sattigeri, Rameswar Panda, Rogerio Feris, Yuheng Bu","submitted_at":"2020-12-30T18:15:05Z","abstract_excerpt":"As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information-theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables which are more computationally efficient than existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15259","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/2012.15259/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":"2026-07-05T02:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nclTfft/Hc8gDCIeIDvaeNI1JCgS8ZoZBOgDYjxhhrRTYMWcxN4jObecUdrGb6c/5Ad9rma4LoSqvkzX7sp5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:04:48.703931Z"},"content_sha256":"73288c719f7ad4d672988bcabecdf4a8b1cfe29f5cf752569844d1781a398f5d","schema_version":"1.0","event_id":"sha256:73288c719f7ad4d672988bcabecdf4a8b1cfe29f5cf752569844d1781a398f5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/bundle.json","state_url":"https://pith.science/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/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":"2026-07-09T02:04:48Z","links":{"resolver":"https://pith.science/pith/2BRKM65PHXOGMNRMIZDRKIXVRD","bundle":"https://pith.science/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/bundle.json","state":"https://pith.science/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BRKM65PHXOGMNRMIZDRKIXVRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2BRKM65PHXOGMNRMIZDRKIXVRD","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":"7c1323d34358bd7b27fd15353d6a2e2c77c75890e758af4954bed308276f8847","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T18:15:05Z","title_canon_sha256":"d75205b0377412394ff350affaef255b2f743dbae1ddf96dad5990c366ce0ad5"},"schema_version":"1.0","source":{"id":"2012.15259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15259","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15259v1","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15259","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"2BRKM65PHXOG","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"2BRKM65PHXOGMNRM","created_at":"2026-07-05T02:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"2BRKM65P","created_at":"2026-07-05T02:03:06Z"}],"graph_snapshots":[{"event_id":"sha256:73288c719f7ad4d672988bcabecdf4a8b1cfe29f5cf752569844d1781a398f5d","target":"graph","created_at":"2026-07-05T02:03:06Z","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/2012.15259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information-theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables which are more computationally efficient than existin","authors_text":"Gregory Wornell, Joshua Lee, Leonid Karlinsky, Prasanna Sattigeri, Rameswar Panda, Rogerio Feris, Yuheng Bu","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T18:15:05Z","title":"A Maximal Correlation Approach to Imposing Fairness in Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15259","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:c44c4961922d946af7f076cca6ec7edde663bd9478df68f66beb26a4e2193b60","target":"record","created_at":"2026-07-05T02:03:06Z","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":"7c1323d34358bd7b27fd15353d6a2e2c77c75890e758af4954bed308276f8847","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-30T18:15:05Z","title_canon_sha256":"d75205b0377412394ff350affaef255b2f743dbae1ddf96dad5990c366ce0ad5"},"schema_version":"1.0","source":{"id":"2012.15259","kind":"arxiv","version":1}},"canonical_sha256":"d062a67baf3ddc66362c46471522f588cfc04286dfd9dc401b21c2a8b1380e7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d062a67baf3ddc66362c46471522f588cfc04286dfd9dc401b21c2a8b1380e7a","first_computed_at":"2026-07-05T02:03:06.138326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:03:06.138326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2r3ZgiYGmaMOV8SylsEDOrr5vPPtmaxOSfQP1MPfWZEPmIpF7EYw+6SIpKiY9an/RkPRJp7LhrJuMFZYULQ2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:03:06.138672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c44c4961922d946af7f076cca6ec7edde663bd9478df68f66beb26a4e2193b60","sha256:73288c719f7ad4d672988bcabecdf4a8b1cfe29f5cf752569844d1781a398f5d"],"state_sha256":"55fb2d62c95ac419ed30c00e038f79a686789fa40857b943725f72c683467a0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s880ubTaBvJJfeBeRX9L/WOs3s8WYBPuoHsdQonnHHMY0xA+KpLb+pRinbVINBUVE66Hd7mmHHu4vyiyi/eMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:04:48.705955Z","bundle_sha256":"ebfcebcdf0cf544f1cb0b79773dec38bb57c1e479f0cac1205c5c0fcd59a9e32"}}