{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UG5YIDSPIIPEVFUJVJZ6GKFVL6","short_pith_number":"pith:UG5YIDSP","schema_version":"1.0","canonical_sha256":"a1bb840e4f421e4a9689aa73e328b55fb5f621960c8070c6a8e231fa6b95169d","source":{"kind":"arxiv","id":"1807.00392","version":1},"attestation_state":"computed","paper":{"title":"Gradient Reversal Against Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Edward Raff, Jared Sylvester","submitted_at":"2018-07-01T20:46:20Z","abstract_excerpt":"No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has only one (insensitive) hyper-parameter, and provides improved individual and group fairness. We use the flexibility of GRAD to demonstrate multi-attribute protection."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.00392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-07-01T20:46:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fa610c7bdd50abcdc7215a0b13474263086fb7b455cfc386f36c812399dd743d","abstract_canon_sha256":"3b1ef4bacac9eca9d3af3b028e5c3037d4c5cd4e332b39a2756ffbc3339ceeb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:55.015457Z","signature_b64":"E79yRWcMDgYPOl2peulWUHo9OSAh0Ss20eMhWMPY2L3OVjQMySuzP9rkDdFz2lWiLjmrrXBjxBlAKVmsOFNDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1bb840e4f421e4a9689aa73e328b55fb5f621960c8070c6a8e231fa6b95169d","last_reissued_at":"2026-05-18T00:11:55.014868Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:55.014868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Reversal Against Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Edward Raff, Jared Sylvester","submitted_at":"2018-07-01T20:46:20Z","abstract_excerpt":"No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has only one (insensitive) hyper-parameter, and provides improved individual and group fairness. We use the flexibility of GRAD to demonstrate multi-attribute protection."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00392","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.00392","created_at":"2026-05-18T00:11:55.014950+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00392v1","created_at":"2026-05-18T00:11:55.014950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00392","created_at":"2026-05-18T00:11:55.014950+00:00"},{"alias_kind":"pith_short_12","alias_value":"UG5YIDSPIIPE","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UG5YIDSPIIPEVFUJ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UG5YIDSP","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6","json":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6.json","graph_json":"https://pith.science/api/pith-number/UG5YIDSPIIPEVFUJVJZ6GKFVL6/graph.json","events_json":"https://pith.science/api/pith-number/UG5YIDSPIIPEVFUJVJZ6GKFVL6/events.json","paper":"https://pith.science/paper/UG5YIDSP"},"agent_actions":{"view_html":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6","download_json":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6.json","view_paper":"https://pith.science/paper/UG5YIDSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00392&json=true","fetch_graph":"https://pith.science/api/pith-number/UG5YIDSPIIPEVFUJVJZ6GKFVL6/graph.json","fetch_events":"https://pith.science/api/pith-number/UG5YIDSPIIPEVFUJVJZ6GKFVL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6/action/storage_attestation","attest_author":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6/action/author_attestation","sign_citation":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6/action/citation_signature","submit_replication":"https://pith.science/pith/UG5YIDSPIIPEVFUJVJZ6GKFVL6/action/replication_record"}},"created_at":"2026-05-18T00:11:55.014950+00:00","updated_at":"2026-05-18T00:11:55.014950+00:00"}