{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M33TI4MLEWGRNFXGYN3CU3HANS","short_pith_number":"pith:M33TI4ML","canonical_record":{"source":{"id":"2406.03142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T10:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"88679f8bc96b8298039f58d390808ae1b0aac1ded757ce79e0d70b641b403928","abstract_canon_sha256":"4694b0c3c71bae21a81a3b3123feae93a95f98436c3ec18697277dfa614bfecf"},"schema_version":"1.0"},"canonical_sha256":"66f734718b258d1696e6c3762a6ce06cadd7b5d8651bbff06b0596c88c4ee41e","source":{"kind":"arxiv","id":"2406.03142","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03142","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03142v2","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03142","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"M33TI4MLEWGR","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"M33TI4MLEWGRNFXG","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"M33TI4ML","created_at":"2026-07-05T09:16:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M33TI4MLEWGRNFXGYN3CU3HANS","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T10:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"88679f8bc96b8298039f58d390808ae1b0aac1ded757ce79e0d70b641b403928","abstract_canon_sha256":"4694b0c3c71bae21a81a3b3123feae93a95f98436c3ec18697277dfa614bfecf"},"schema_version":"1.0"},"canonical_sha256":"66f734718b258d1696e6c3762a6ce06cadd7b5d8651bbff06b0596c88c4ee41e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:49.649947Z","signature_b64":"FjEpVwsTEVnK5OMSWyctMMVNKsNrBJGcLkO7yJMgY0PhA5FQ2okU12GC8hPDwnF+RTCx5Ze1/+a5fbHjq+LSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66f734718b258d1696e6c3762a6ce06cadd7b5d8651bbff06b0596c88c4ee41e","last_reissued_at":"2026-07-05T09:16:49.649452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:49.649452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03142","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ErT25WN98TyAok3zgFOiqDE36k4PBkqhctOpneAyvLQwlvo++G83uOHXHqRyTTUXOZoX7dk0tYtwgwUWqMcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T11:59:34.468983Z"},"content_sha256":"0de847e0897758c9fcf9416c160a6c9ff025ebaac8ccfcbf9c9aa2c4a745d5f4","schema_version":"1.0","event_id":"sha256:0de847e0897758c9fcf9416c160a6c9ff025ebaac8ccfcbf9c9aa2c4a745d5f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M33TI4MLEWGRNFXGYN3CU3HANS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Power of Randomization in Fair Classification and Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amit Deshpande, Sushant Agarwal","submitted_at":"2024-06-05T10:55:11Z","abstract_excerpt":"Fair classification and fair representation learning are two important problems in supervised and unsupervised fair machine learning, respectively. Fair classification asks for a classifier that maximizes accuracy on a given data distribution subject to fairness constraints. Fair representation maps a given data distribution over the original feature space to a distribution over a new representation space such that all classifiers over the representation satisfy fairness. In this paper, we examine the power of randomization in both these problems to minimize the loss of accuracy that results w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03142","kind":"arxiv","version":2},"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/2406.03142/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":"2026-07-05T09:16:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFd/iRo+G8F4g4aEcggwrHaSpH93Uime1uJC/lQA9bChMJGlAcfbJu96c3vHPTMcUlc9z4qNAT0v58jYax5GBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T11:59:34.469613Z"},"content_sha256":"59d3a2d6fd90b7592a0c024cd8ad313a447b6e0b92778cb6921e608c55d64bcd","schema_version":"1.0","event_id":"sha256:59d3a2d6fd90b7592a0c024cd8ad313a447b6e0b92778cb6921e608c55d64bcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M33TI4MLEWGRNFXGYN3CU3HANS/bundle.json","state_url":"https://pith.science/pith/M33TI4MLEWGRNFXGYN3CU3HANS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M33TI4MLEWGRNFXGYN3CU3HANS/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":"2026-07-12T11:59:34Z","links":{"resolver":"https://pith.science/pith/M33TI4MLEWGRNFXGYN3CU3HANS","bundle":"https://pith.science/pith/M33TI4MLEWGRNFXGYN3CU3HANS/bundle.json","state":"https://pith.science/pith/M33TI4MLEWGRNFXGYN3CU3HANS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M33TI4MLEWGRNFXGYN3CU3HANS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M33TI4MLEWGRNFXGYN3CU3HANS","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":"4694b0c3c71bae21a81a3b3123feae93a95f98436c3ec18697277dfa614bfecf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T10:55:11Z","title_canon_sha256":"88679f8bc96b8298039f58d390808ae1b0aac1ded757ce79e0d70b641b403928"},"schema_version":"1.0","source":{"id":"2406.03142","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03142","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03142v2","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03142","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"M33TI4MLEWGR","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"M33TI4MLEWGRNFXG","created_at":"2026-07-05T09:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"M33TI4ML","created_at":"2026-07-05T09:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:59d3a2d6fd90b7592a0c024cd8ad313a447b6e0b92778cb6921e608c55d64bcd","target":"graph","created_at":"2026-07-05T09:16:49Z","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/2406.03142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fair classification and fair representation learning are two important problems in supervised and unsupervised fair machine learning, respectively. Fair classification asks for a classifier that maximizes accuracy on a given data distribution subject to fairness constraints. Fair representation maps a given data distribution over the original feature space to a distribution over a new representation space such that all classifiers over the representation satisfy fairness. In this paper, we examine the power of randomization in both these problems to minimize the loss of accuracy that results w","authors_text":"Amit Deshpande, Sushant Agarwal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T10:55:11Z","title":"On the Power of Randomization in Fair Classification and Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03142","kind":"arxiv","version":2},"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":"sha256:0de847e0897758c9fcf9416c160a6c9ff025ebaac8ccfcbf9c9aa2c4a745d5f4","target":"record","created_at":"2026-07-05T09:16:49Z","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":"4694b0c3c71bae21a81a3b3123feae93a95f98436c3ec18697277dfa614bfecf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T10:55:11Z","title_canon_sha256":"88679f8bc96b8298039f58d390808ae1b0aac1ded757ce79e0d70b641b403928"},"schema_version":"1.0","source":{"id":"2406.03142","kind":"arxiv","version":2}},"canonical_sha256":"66f734718b258d1696e6c3762a6ce06cadd7b5d8651bbff06b0596c88c4ee41e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66f734718b258d1696e6c3762a6ce06cadd7b5d8651bbff06b0596c88c4ee41e","first_computed_at":"2026-07-05T09:16:49.649452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:49.649452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjEpVwsTEVnK5OMSWyctMMVNKsNrBJGcLkO7yJMgY0PhA5FQ2okU12GC8hPDwnF+RTCx5Ze1/+a5fbHjq+LSCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:49.649947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03142","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0de847e0897758c9fcf9416c160a6c9ff025ebaac8ccfcbf9c9aa2c4a745d5f4","sha256:59d3a2d6fd90b7592a0c024cd8ad313a447b6e0b92778cb6921e608c55d64bcd"],"state_sha256":"40dadd7f04973d53f76698dea90c3d147105869ce13e1b8c4decb879846440a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jgy9qVPqPPpeOPadAErX7nbR3c/0K+OAvKOARXFtHYawraZHQzy4vgK4IFfvxDL+pPwu3U7KXCqIOochx+7aDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T11:59:34.482959Z","bundle_sha256":"346eb5a52d504a7a222b01f59ec39b1e6e8077a286bd5d8b90e4ca26b423560b"}}