{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JLQ7NGO5FTSH5PKHW4SCCLGERI","short_pith_number":"pith:JLQ7NGO5","schema_version":"1.0","canonical_sha256":"4ae1f699dd2ce47ebd47b724212cc48a25b6552cee189cc5f096aac734fb828e","source":{"kind":"arxiv","id":"2101.02084","version":1},"attestation_state":"computed","paper":{"title":"Fairness with Continuous Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Silvia Chiappa","submitted_at":"2021-01-06T15:10:10Z","abstract_excerpt":"Whilst optimal transport (OT) is increasingly being recognized as a powerful and flexible approach for dealing with fairness issues, current OT fairness methods are confined to the use of discrete OT. In this paper, we leverage recent advances from the OT literature to introduce a stochastic-gradient fairness method based on a dual formulation of continuous OT. We show that this method gives superior performance to discrete OT methods when little data is available to solve the OT problem, and similar performance otherwise. We also show that both continuous and discrete OT methods are able to c"},"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":"2101.02084","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-06T15:10:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3e1ab7cb7639ae2fad46083f87c7919bf24e12429f08dd01a9672d06353299c3","abstract_canon_sha256":"a87737bdc5b7b6864580ad19762b9d746a030f2ca4e2bce904f8fd21f3801938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:03.035695Z","signature_b64":"vD1YS/34Hp29yUadvMuQ/26s/O/rhqjz9cJLdu0ON8zHt+pf3P+NN9FpV3X9sTF8RTXjUgGkjVvObowauVPpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae1f699dd2ce47ebd47b724212cc48a25b6552cee189cc5f096aac734fb828e","last_reissued_at":"2026-07-05T02:05:03.035283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:03.035283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness with Continuous Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Silvia Chiappa","submitted_at":"2021-01-06T15:10:10Z","abstract_excerpt":"Whilst optimal transport (OT) is increasingly being recognized as a powerful and flexible approach for dealing with fairness issues, current OT fairness methods are confined to the use of discrete OT. In this paper, we leverage recent advances from the OT literature to introduce a stochastic-gradient fairness method based on a dual formulation of continuous OT. We show that this method gives superior performance to discrete OT methods when little data is available to solve the OT problem, and similar performance otherwise. We also show that both continuous and discrete OT methods are able to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02084","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/2101.02084/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2101.02084","created_at":"2026-07-05T02:05:03.035341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02084v1","created_at":"2026-07-05T02:05:03.035341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02084","created_at":"2026-07-05T02:05:03.035341+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLQ7NGO5FTSH","created_at":"2026-07-05T02:05:03.035341+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLQ7NGO5FTSH5PKH","created_at":"2026-07-05T02:05:03.035341+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLQ7NGO5","created_at":"2026-07-05T02:05:03.035341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28251","citing_title":"Counterfactually Fair Regression via Optimal Transport","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI","json":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI.json","graph_json":"https://pith.science/api/pith-number/JLQ7NGO5FTSH5PKHW4SCCLGERI/graph.json","events_json":"https://pith.science/api/pith-number/JLQ7NGO5FTSH5PKHW4SCCLGERI/events.json","paper":"https://pith.science/paper/JLQ7NGO5"},"agent_actions":{"view_html":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI","download_json":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI.json","view_paper":"https://pith.science/paper/JLQ7NGO5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02084&json=true","fetch_graph":"https://pith.science/api/pith-number/JLQ7NGO5FTSH5PKHW4SCCLGERI/graph.json","fetch_events":"https://pith.science/api/pith-number/JLQ7NGO5FTSH5PKHW4SCCLGERI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI/action/storage_attestation","attest_author":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI/action/author_attestation","sign_citation":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI/action/citation_signature","submit_replication":"https://pith.science/pith/JLQ7NGO5FTSH5PKHW4SCCLGERI/action/replication_record"}},"created_at":"2026-07-05T02:05:03.035341+00:00","updated_at":"2026-07-05T02:05:03.035341+00:00"}