{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HG2SRMFCPBBGNOJYOB5PIXSUJI","short_pith_number":"pith:HG2SRMFC","schema_version":"1.0","canonical_sha256":"39b528b0a2784266b938707af45e544a0a548ca95e8d508d1efa5f1ed4c683b1","source":{"kind":"arxiv","id":"1710.04394","version":1},"attestation_state":"computed","paper":{"title":"Provably Fair Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Soon Ong, Daniel McNamara, Robert C. Williamson","submitted_at":"2017-10-12T07:37:52Z","abstract_excerpt":"Machine learning systems are increasingly used to make decisions about people's lives, such as whether to give someone a loan or whether to interview someone for a job. This has led to considerable interest in making such machine learning systems fair. One approach is to transform the input data used by the algorithm. This can be achieved by passing each input data point through a representation function prior to its use in training or testing. Techniques for learning such representation functions from data have been successful empirically, but typically lack theoretical fairness guarantees. W"},"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":"1710.04394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-12T07:37:52Z","cross_cats_sorted":[],"title_canon_sha256":"bd41611544246e48da2857faf55bb73b14f593bf6ce64b9bdf3165c292c6233c","abstract_canon_sha256":"0da8ca626efd6401f9dc0a54e5909abd03548cc49679cbf42d91eff10edccd9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:01.191139Z","signature_b64":"5ycdKMuPPCdeg6K/tSB1qv+mGk9CWYRypHJc71nHaJ0Dk9vIcZhJwo7jDDT2L59G1zhJN0niJqVfDH0Ur0SFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39b528b0a2784266b938707af45e544a0a548ca95e8d508d1efa5f1ed4c683b1","last_reissued_at":"2026-05-18T00:33:01.190555Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:01.190555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Fair Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Soon Ong, Daniel McNamara, Robert C. Williamson","submitted_at":"2017-10-12T07:37:52Z","abstract_excerpt":"Machine learning systems are increasingly used to make decisions about people's lives, such as whether to give someone a loan or whether to interview someone for a job. This has led to considerable interest in making such machine learning systems fair. One approach is to transform the input data used by the algorithm. This can be achieved by passing each input data point through a representation function prior to its use in training or testing. Techniques for learning such representation functions from data have been successful empirically, but typically lack theoretical fairness guarantees. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04394","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":"1710.04394","created_at":"2026-05-18T00:33:01.190652+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.04394v1","created_at":"2026-05-18T00:33:01.190652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04394","created_at":"2026-05-18T00:33:01.190652+00:00"},{"alias_kind":"pith_short_12","alias_value":"HG2SRMFCPBBG","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HG2SRMFCPBBGNOJY","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HG2SRMFC","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23145","citing_title":"Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI","json":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI.json","graph_json":"https://pith.science/api/pith-number/HG2SRMFCPBBGNOJYOB5PIXSUJI/graph.json","events_json":"https://pith.science/api/pith-number/HG2SRMFCPBBGNOJYOB5PIXSUJI/events.json","paper":"https://pith.science/paper/HG2SRMFC"},"agent_actions":{"view_html":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI","download_json":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI.json","view_paper":"https://pith.science/paper/HG2SRMFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.04394&json=true","fetch_graph":"https://pith.science/api/pith-number/HG2SRMFCPBBGNOJYOB5PIXSUJI/graph.json","fetch_events":"https://pith.science/api/pith-number/HG2SRMFCPBBGNOJYOB5PIXSUJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI/action/storage_attestation","attest_author":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI/action/author_attestation","sign_citation":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI/action/citation_signature","submit_replication":"https://pith.science/pith/HG2SRMFCPBBGNOJYOB5PIXSUJI/action/replication_record"}},"created_at":"2026-05-18T00:33:01.190652+00:00","updated_at":"2026-05-18T00:33:01.190652+00:00"}