{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z7KXDBM6OW2PQMA7INYOWR4YWI","short_pith_number":"pith:Z7KXDBM6","schema_version":"1.0","canonical_sha256":"cfd571859e75b4f8301f4370eb4798b23eb2282bb8e42fb0c734bbf1206e416f","source":{"kind":"arxiv","id":"2502.01211","version":1},"attestation_state":"computed","paper":{"title":"Privilege Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, Giuseppe Casalicchio, Jose M. Alvarez, Ludwig Bothmann, Philip A. Boustani, Susanne Dandl","submitted_at":"2025-02-03T10:03:25Z","abstract_excerpt":"Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We introduce privilege scores (PS) to measure PA-related privilege by comparing the model predictions in the real world with those in a fair world in which the influence of the PA is removed. At the individual level, PS can identify individuals who qualify for affirmative action; at the global level, PS can inform bias-transforming policies. After presenting estimati"},"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":"2502.01211","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T10:03:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"60b1ad61a583a53b76f7cace6f23fbed73edd6b5b79f5d34887087ea895984a0","abstract_canon_sha256":"f8648da1fb1118ed941e97dbed45248ffedc36fc49fee97b9269df2f51a22c3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:44.352130Z","signature_b64":"MV+Lp2fxLIdCPrbrMb2kWP7wWiQnaDIMH1CSp6q5WQ3dhVrrcsZV2u3K769bikA/UbBrxXQBkeXXAKFxb472Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfd571859e75b4f8301f4370eb4798b23eb2282bb8e42fb0c734bbf1206e416f","last_reissued_at":"2026-07-05T10:08:44.351542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:44.351542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privilege Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, Giuseppe Casalicchio, Jose M. Alvarez, Ludwig Bothmann, Philip A. Boustani, Susanne Dandl","submitted_at":"2025-02-03T10:03:25Z","abstract_excerpt":"Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We introduce privilege scores (PS) to measure PA-related privilege by comparing the model predictions in the real world with those in a fair world in which the influence of the PA is removed. At the individual level, PS can identify individuals who qualify for affirmative action; at the global level, PS can inform bias-transforming policies. After presenting estimati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01211","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/2502.01211/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":"2502.01211","created_at":"2026-07-05T10:08:44.351613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01211v1","created_at":"2026-07-05T10:08:44.351613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01211","created_at":"2026-07-05T10:08:44.351613+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7KXDBM6OW2P","created_at":"2026-07-05T10:08:44.351613+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7KXDBM6OW2PQMA7","created_at":"2026-07-05T10:08:44.351613+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7KXDBM6","created_at":"2026-07-05T10:08:44.351613+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/Z7KXDBM6OW2PQMA7INYOWR4YWI","json":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI.json","graph_json":"https://pith.science/api/pith-number/Z7KXDBM6OW2PQMA7INYOWR4YWI/graph.json","events_json":"https://pith.science/api/pith-number/Z7KXDBM6OW2PQMA7INYOWR4YWI/events.json","paper":"https://pith.science/paper/Z7KXDBM6"},"agent_actions":{"view_html":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI","download_json":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI.json","view_paper":"https://pith.science/paper/Z7KXDBM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01211&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7KXDBM6OW2PQMA7INYOWR4YWI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7KXDBM6OW2PQMA7INYOWR4YWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI/action/storage_attestation","attest_author":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI/action/author_attestation","sign_citation":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI/action/citation_signature","submit_replication":"https://pith.science/pith/Z7KXDBM6OW2PQMA7INYOWR4YWI/action/replication_record"}},"created_at":"2026-07-05T10:08:44.351613+00:00","updated_at":"2026-07-05T10:08:44.351613+00:00"}