{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:7Z5LDLB2K7JNZMY5YIQZ4F7GDI","short_pith_number":"pith:7Z5LDLB2","schema_version":"1.0","canonical_sha256":"fe7ab1ac3a57d2dcb31dc2219e17e61a2f6b4be0790e4ac3735c19fdd27ece05","source":{"kind":"arxiv","id":"1412.5244","version":1},"attestation_state":"computed","paper":{"title":"Learning unbiased features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Swersky, Richard Zemel, Yujia Li","submitted_at":"2014-12-17T02:47:22Z","abstract_excerpt":"A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains can be learned readily based on mappings of these salient factors. We propose that an important aim for these representations are to be unbiased. Different forms of representation learning can be derived from alternative definitions of unwanted bias, e.g., bias to particular tasks, domains, or irrelevant underlying data dimensions. One very useful approach to estimating the amount of bias in a representation comes fr"},"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":"1412.5244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-17T02:47:22Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"eb7a5be23eb8cba294b595cfd076ecf895dbeca0feb0f7931cfb4a0014289c15","abstract_canon_sha256":"3f08d61bd7b07937ddf784ed7030cbb2b47f47b5e066b27ebe98841cf3877aad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:03.442021Z","signature_b64":"Ui7dGGF3luBjUqvb9IhEjZmvj6kGOKbLmLa3htIf135QL/6RkO7qFBFUEbY9nibzY8RBcLilFVDu0B1CRAQgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7ab1ac3a57d2dcb31dc2219e17e61a2f6b4be0790e4ac3735c19fdd27ece05","last_reissued_at":"2026-05-18T02:31:03.441433Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:03.441433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning unbiased features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kevin Swersky, Richard Zemel, Yujia Li","submitted_at":"2014-12-17T02:47:22Z","abstract_excerpt":"A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains can be learned readily based on mappings of these salient factors. We propose that an important aim for these representations are to be unbiased. Different forms of representation learning can be derived from alternative definitions of unwanted bias, e.g., bias to particular tasks, domains, or irrelevant underlying data dimensions. One very useful approach to estimating the amount of bias in a representation comes fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.5244","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":"1412.5244","created_at":"2026-05-18T02:31:03.441540+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.5244v1","created_at":"2026-05-18T02:31:03.441540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.5244","created_at":"2026-05-18T02:31:03.441540+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z5LDLB2K7JN","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z5LDLB2K7JNZMY5","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z5LDLB2","created_at":"2026-05-18T12:28:19.803747+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/7Z5LDLB2K7JNZMY5YIQZ4F7GDI","json":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI.json","graph_json":"https://pith.science/api/pith-number/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/graph.json","events_json":"https://pith.science/api/pith-number/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/events.json","paper":"https://pith.science/paper/7Z5LDLB2"},"agent_actions":{"view_html":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI","download_json":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI.json","view_paper":"https://pith.science/paper/7Z5LDLB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.5244&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/action/storage_attestation","attest_author":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/action/author_attestation","sign_citation":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/action/citation_signature","submit_replication":"https://pith.science/pith/7Z5LDLB2K7JNZMY5YIQZ4F7GDI/action/replication_record"}},"created_at":"2026-05-18T02:31:03.441540+00:00","updated_at":"2026-05-18T02:31:03.441540+00:00"}