{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BBIBN67UAPKIZROG4Z5CHGX7PV","short_pith_number":"pith:BBIBN67U","canonical_record":{"source":{"id":"1802.06309","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T23:38:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4558b3f56f373ed47f5d8623b80f439daa13cdae29da911d832c197c63c86b73","abstract_canon_sha256":"981c28cf77f151c411b60b82a620dc764c66256d3b84e7dde3d2d80facde3613"},"schema_version":"1.0"},"canonical_sha256":"085016fbf403d48cc5c6e67a239aff7d7e5c3a81efc504c94ee6af29f675c353","source":{"kind":"arxiv","id":"1802.06309","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06309","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06309v3","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06309","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"BBIBN67UAPKI","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBIBN67UAPKIZROG","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBIBN67U","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BBIBN67UAPKIZROG4Z5CHGX7PV","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06309","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T23:38:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4558b3f56f373ed47f5d8623b80f439daa13cdae29da911d832c197c63c86b73","abstract_canon_sha256":"981c28cf77f151c411b60b82a620dc764c66256d3b84e7dde3d2d80facde3613"},"schema_version":"1.0"},"canonical_sha256":"085016fbf403d48cc5c6e67a239aff7d7e5c3a81efc504c94ee6af29f675c353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.212386Z","signature_b64":"yoZWNTR91aMexjfObTDSVLvY3k5S1ICDVsYA1hdxxZ++oB/MYlgQm3Fu5kWT8Z4Q4uqTahdJoHBBjreN4mnOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085016fbf403d48cc5c6e67a239aff7d7e5c3a81efc504c94ee6af29f675c353","last_reissued_at":"2026-05-18T00:02:45.211958Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.211958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06309","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":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JE1rZnaFEV8vsk4Yq/CtsRQEWyvokObOnPCQz64SwaaOY97Kxbz7BmZAmUtN3BNUpRbepKBuLMgpTGXGXPkkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:38:55.024191Z"},"content_sha256":"5630e16dfaf193b6cc54d23535681e978c84a3d2df28b3e87cda3933a88c56cc","schema_version":"1.0","event_id":"sha256:5630e16dfaf193b6cc54d23535681e978c84a3d2df28b3e87cda3933a88c56cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BBIBN67UAPKIZROG4Z5CHGX7PV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Adversarially Fair and Transferable Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Madras, Elliot Creager, Richard Zemel, Toniann Pitassi","submitted_at":"2018-02-17T23:38:29Z","abstract_excerpt":"In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06309","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":""},"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":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd/8tWhfPVig8ah+3oRNP3gsiEX/SmswtNAG7aew5zkBxT5Vq+kfc21frXpftsGzCmN2fxqGDwX157SZJqB4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:38:55.024834Z"},"content_sha256":"6f417f4be5238e1ec088f0021723a453d248fef4bd193c3e7955659f93d02082","schema_version":"1.0","event_id":"sha256:6f417f4be5238e1ec088f0021723a453d248fef4bd193c3e7955659f93d02082"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/bundle.json","state_url":"https://pith.science/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/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":"2026-05-26T10:38:55Z","links":{"resolver":"https://pith.science/pith/BBIBN67UAPKIZROG4Z5CHGX7PV","bundle":"https://pith.science/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/bundle.json","state":"https://pith.science/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBIBN67UAPKIZROG4Z5CHGX7PV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BBIBN67UAPKIZROG4Z5CHGX7PV","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":"981c28cf77f151c411b60b82a620dc764c66256d3b84e7dde3d2d80facde3613","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T23:38:29Z","title_canon_sha256":"4558b3f56f373ed47f5d8623b80f439daa13cdae29da911d832c197c63c86b73"},"schema_version":"1.0","source":{"id":"1802.06309","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06309","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06309v3","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06309","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"BBIBN67UAPKI","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"BBIBN67UAPKIZROG","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"BBIBN67U","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:6f417f4be5238e1ec088f0021723a453d248fef4bd193c3e7955659f93d02082","target":"graph","created_at":"2026-05-18T00:02:45Z","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"},"paper":{"abstract_excerpt":"In this paper, we advocate for representation learning as the key to mitigating unfair prediction outcomes downstream. Motivated by a scenario where learned representations are used by third parties with unknown objectives, we propose and explore adversarial representation learning as a natural method of ensuring those parties act fairly. We connect group fairness (demographic parity, equalized odds, and equal opportunity) to different adversarial objectives. Through worst-case theoretical guarantees and experimental validation, we show that the choice of this objective is crucial to fair pred","authors_text":"David Madras, Elliot Creager, Richard Zemel, Toniann Pitassi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T23:38:29Z","title":"Learning Adversarially Fair and Transferable Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06309","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":"sha256:5630e16dfaf193b6cc54d23535681e978c84a3d2df28b3e87cda3933a88c56cc","target":"record","created_at":"2026-05-18T00:02:45Z","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":"981c28cf77f151c411b60b82a620dc764c66256d3b84e7dde3d2d80facde3613","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T23:38:29Z","title_canon_sha256":"4558b3f56f373ed47f5d8623b80f439daa13cdae29da911d832c197c63c86b73"},"schema_version":"1.0","source":{"id":"1802.06309","kind":"arxiv","version":3}},"canonical_sha256":"085016fbf403d48cc5c6e67a239aff7d7e5c3a81efc504c94ee6af29f675c353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"085016fbf403d48cc5c6e67a239aff7d7e5c3a81efc504c94ee6af29f675c353","first_computed_at":"2026-05-18T00:02:45.211958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:45.211958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yoZWNTR91aMexjfObTDSVLvY3k5S1ICDVsYA1hdxxZ++oB/MYlgQm3Fu5kWT8Z4Q4uqTahdJoHBBjreN4mnOBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:45.212386Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06309","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5630e16dfaf193b6cc54d23535681e978c84a3d2df28b3e87cda3933a88c56cc","sha256:6f417f4be5238e1ec088f0021723a453d248fef4bd193c3e7955659f93d02082"],"state_sha256":"1e6e9394c99918139e0f3e32609b4f6b172df901a6d27231a638284d4b0de0a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTAoL4yrrCLY9p/esYXp/iP4jrZb9i28epWF2wwN35mK20WJrGDAGn2OFKsSZ0oPOKBRXvBq0gHAI25K+GI9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:38:55.027783Z","bundle_sha256":"4d094dce4a915dddf6adbcb547c9b876289d64983985a920dcd2bc6b46bfd774"}}