{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NOOS6RYRIU6ZLUYGTO37KCRNVJ","short_pith_number":"pith:NOOS6RYR","schema_version":"1.0","canonical_sha256":"6b9d2f4711453d95d3069bb7f50a2daa475785b7d4d717800879a6e3fcaaa6e2","source":{"kind":"arxiv","id":"1804.04503","version":2},"attestation_state":"computed","paper":{"title":"Unleashing Linear Optimizers for Group-Fair Learning and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Tauman Kalai, Daniel Alabi, Nicole Immorlica","submitted_at":"2018-04-11T02:51:07Z","abstract_excerpt":"Most systems and learning algorithms optimize average performance or average loss -- one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. This arises, for example, when balancing performance or loss with fairness across people. We prove that, from a computational perspective, optimizing arbitrary objectives that take into account performance over a small number of groups is not significantly harder to optimize than average performance. Our main result is a polynomial-time reduction that uses a linear optimizer to o"},"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":"1804.04503","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T02:51:07Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"64debf513e742813bda95fa46b42b1b4e40dd96bbae4818d3316c334fcc02fbd","abstract_canon_sha256":"3211bef9f62ca904a3e29c047aaaf3b9334d0a94d720e01083e641c931db5b9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:21.458685Z","signature_b64":"12yaU8WLjoykAPNtlSJypkfaAut7bJZQzSw/FyH5kjkTfPsARpQdLpb0NgCihg/Q2XikUU6/BgDHXxcQOR3zCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b9d2f4711453d95d3069bb7f50a2daa475785b7d4d717800879a6e3fcaaa6e2","last_reissued_at":"2026-05-18T00:14:21.458107Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:21.458107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing Linear Optimizers for Group-Fair Learning and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Tauman Kalai, Daniel Alabi, Nicole Immorlica","submitted_at":"2018-04-11T02:51:07Z","abstract_excerpt":"Most systems and learning algorithms optimize average performance or average loss -- one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. This arises, for example, when balancing performance or loss with fairness across people. We prove that, from a computational perspective, optimizing arbitrary objectives that take into account performance over a small number of groups is not significantly harder to optimize than average performance. Our main result is a polynomial-time reduction that uses a linear optimizer to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04503","kind":"arxiv","version":2},"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":"1804.04503","created_at":"2026-05-18T00:14:21.458195+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.04503v2","created_at":"2026-05-18T00:14:21.458195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04503","created_at":"2026-05-18T00:14:21.458195+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOOS6RYRIU6Z","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOOS6RYRIU6ZLUYG","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOOS6RYR","created_at":"2026-05-18T12:32:40.477152+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/NOOS6RYRIU6ZLUYGTO37KCRNVJ","json":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ.json","graph_json":"https://pith.science/api/pith-number/NOOS6RYRIU6ZLUYGTO37KCRNVJ/graph.json","events_json":"https://pith.science/api/pith-number/NOOS6RYRIU6ZLUYGTO37KCRNVJ/events.json","paper":"https://pith.science/paper/NOOS6RYR"},"agent_actions":{"view_html":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ","download_json":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ.json","view_paper":"https://pith.science/paper/NOOS6RYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.04503&json=true","fetch_graph":"https://pith.science/api/pith-number/NOOS6RYRIU6ZLUYGTO37KCRNVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NOOS6RYRIU6ZLUYGTO37KCRNVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ/action/storage_attestation","attest_author":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ/action/author_attestation","sign_citation":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ/action/citation_signature","submit_replication":"https://pith.science/pith/NOOS6RYRIU6ZLUYGTO37KCRNVJ/action/replication_record"}},"created_at":"2026-05-18T00:14:21.458195+00:00","updated_at":"2026-05-18T00:14:21.458195+00:00"}