{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RUMSEMZUDE4VJDQXTH42MJ2OWH","short_pith_number":"pith:RUMSEMZU","schema_version":"1.0","canonical_sha256":"8d192233341939548e1799f9a6274eb1d525f3a7cd2c9c4506f2afaca7ca6a80","source":{"kind":"arxiv","id":"1808.08166","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study of Rich Subgroup Fairness for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Michael Kearns, Seth Neel, Zhiwei Steven Wu","submitted_at":"2018-08-24T15:08:33Z","abstract_excerpt":"Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent "},"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":"1808.08166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-24T15:08:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0264ebeb50d778f9ff293a9eaf96f67da3266d18ec4435a1784f4cce510965a4","abstract_canon_sha256":"99effe96cad6f8e3e4c0e569642c863062f11b70afaf79424882c783397a85aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:22.239797Z","signature_b64":"54zLuJ0fu96OZ/jdqy/0zZ8ybnmHVg75NBBPXBQSZYkhlOUDIR5UHoSmrm35tunbF2/hx/QGkwC9JSHW+kAOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d192233341939548e1799f9a6274eb1d525f3a7cd2c9c4506f2afaca7ca6a80","last_reissued_at":"2026-05-18T00:07:22.239168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:22.239168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Rich Subgroup Fairness for Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Michael Kearns, Seth Neel, Zhiwei Steven Wu","submitted_at":"2018-08-24T15:08:33Z","abstract_excerpt":"Kearns et al. [2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness. Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension. They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08166","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":"1808.08166","created_at":"2026-05-18T00:07:22.239269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08166v1","created_at":"2026-05-18T00:07:22.239269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08166","created_at":"2026-05-18T00:07:22.239269+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUMSEMZUDE4V","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUMSEMZUDE4VJDQX","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUMSEMZU","created_at":"2026-05-18T12:32:50.500415+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/RUMSEMZUDE4VJDQXTH42MJ2OWH","json":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH.json","graph_json":"https://pith.science/api/pith-number/RUMSEMZUDE4VJDQXTH42MJ2OWH/graph.json","events_json":"https://pith.science/api/pith-number/RUMSEMZUDE4VJDQXTH42MJ2OWH/events.json","paper":"https://pith.science/paper/RUMSEMZU"},"agent_actions":{"view_html":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH","download_json":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH.json","view_paper":"https://pith.science/paper/RUMSEMZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08166&json=true","fetch_graph":"https://pith.science/api/pith-number/RUMSEMZUDE4VJDQXTH42MJ2OWH/graph.json","fetch_events":"https://pith.science/api/pith-number/RUMSEMZUDE4VJDQXTH42MJ2OWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH/action/storage_attestation","attest_author":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH/action/author_attestation","sign_citation":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH/action/citation_signature","submit_replication":"https://pith.science/pith/RUMSEMZUDE4VJDQXTH42MJ2OWH/action/replication_record"}},"created_at":"2026-05-18T00:07:22.239269+00:00","updated_at":"2026-05-18T00:07:22.239269+00:00"}