{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QKUAHWGF4L4PDBMD4AYGI7WTVX","short_pith_number":"pith:QKUAHWGF","schema_version":"1.0","canonical_sha256":"82a803d8c5e2f8f18583e030647ed3adc27708b0175fe72c8cd09106f144e329","source":{"kind":"arxiv","id":"2104.01109","version":1},"attestation_state":"computed","paper":{"title":"AI Fairness via Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Neil Joshi, Phil Burlina","submitted_at":"2021-03-15T22:55:51Z","abstract_excerpt":"While deep learning (DL) approaches are reaching human-level performance for many tasks, including for diagnostics AI, the focus is now on challenges possibly affecting DL deployment, including AI privacy, domain generalization, and fairness. This last challenge is addressed in this study. Here we look at a novel method for ensuring AI fairness with respect to protected or sensitive factors. This method uses domain adaptation via training set enhancement to tackle bias-causing training data imbalance. More specifically, it uses generative models that allow the generation of more synthetic trai"},"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":"2104.01109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-15T22:55:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f54435ad21f0463dbfa67e35182d7b97f5ffd697d38234c881ed05b4ac2067e5","abstract_canon_sha256":"a148fdd194c30e5ec08568d5d4f66be720c4ac03af401170127400d5d34e4055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:44.846912Z","signature_b64":"IeOkl3VheECAonXKqQhDSIG3u74vLvD5jNVA7BgxYb7yMVUccu58pPlr9V1XTCbjUKlkIFCjCM1I2E//w70zDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82a803d8c5e2f8f18583e030647ed3adc27708b0175fe72c8cd09106f144e329","last_reissued_at":"2026-07-05T02:28:44.846575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:44.846575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Fairness via Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Neil Joshi, Phil Burlina","submitted_at":"2021-03-15T22:55:51Z","abstract_excerpt":"While deep learning (DL) approaches are reaching human-level performance for many tasks, including for diagnostics AI, the focus is now on challenges possibly affecting DL deployment, including AI privacy, domain generalization, and fairness. This last challenge is addressed in this study. Here we look at a novel method for ensuring AI fairness with respect to protected or sensitive factors. This method uses domain adaptation via training set enhancement to tackle bias-causing training data imbalance. More specifically, it uses generative models that allow the generation of more synthetic trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01109","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/2104.01109/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":"2104.01109","created_at":"2026-07-05T02:28:44.846635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01109v1","created_at":"2026-07-05T02:28:44.846635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01109","created_at":"2026-07-05T02:28:44.846635+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKUAHWGF4L4P","created_at":"2026-07-05T02:28:44.846635+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKUAHWGF4L4PDBMD","created_at":"2026-07-05T02:28:44.846635+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKUAHWGF","created_at":"2026-07-05T02:28:44.846635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07885","citing_title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX","json":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX.json","graph_json":"https://pith.science/api/pith-number/QKUAHWGF4L4PDBMD4AYGI7WTVX/graph.json","events_json":"https://pith.science/api/pith-number/QKUAHWGF4L4PDBMD4AYGI7WTVX/events.json","paper":"https://pith.science/paper/QKUAHWGF"},"agent_actions":{"view_html":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX","download_json":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX.json","view_paper":"https://pith.science/paper/QKUAHWGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01109&json=true","fetch_graph":"https://pith.science/api/pith-number/QKUAHWGF4L4PDBMD4AYGI7WTVX/graph.json","fetch_events":"https://pith.science/api/pith-number/QKUAHWGF4L4PDBMD4AYGI7WTVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX/action/storage_attestation","attest_author":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX/action/author_attestation","sign_citation":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX/action/citation_signature","submit_replication":"https://pith.science/pith/QKUAHWGF4L4PDBMD4AYGI7WTVX/action/replication_record"}},"created_at":"2026-07-05T02:28:44.846635+00:00","updated_at":"2026-07-05T02:28:44.846635+00:00"}