{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S7V5BVK7NGC3W3DRR262RWRKDY","short_pith_number":"pith:S7V5BVK7","schema_version":"1.0","canonical_sha256":"97ebd0d55f6985bb6c718ebda8da2a1e38100868b7c9a1ced21023ce43f3b0b8","source":{"kind":"arxiv","id":"2306.09425","version":1},"attestation_state":"computed","paper":{"title":"Arbitrariness Lies Beyond the Fairness-Accuracy Frontier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Carol Xuan Long, Flavio P. Calmon, Hsiang Hsu, Wael Alghamdi","submitted_at":"2023-06-15T18:15:46Z","abstract_excerpt":"Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions in machine learning optimized solely for group fairness and accuracy can exacerbate predictive multiplicity. Consequently, state-of-the-art fairness interventions can mask high predictive multiplicity behind favorable group fairness and accuracy metrics. We argue that a third axis of ``arbitrariness'' should be considered when deploying models to aid decisio"},"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":"2306.09425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T18:15:46Z","cross_cats_sorted":["cs.CY","cs.IT","math.IT"],"title_canon_sha256":"bc1201a6d082b0c4bb321b52b00e059c7023b4b28cb063d050ca90a50e24c279","abstract_canon_sha256":"374a88af38b9797779e1f4bfcc688a330147e4bb63a1037b4c47780c305b2f83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:19.923866Z","signature_b64":"5u4JBsFSoAjixtVkc6XimEzNbmgahKW6y6DsZLGywGiRusrLsH7i5HimusXbLM5iWQ8GjPKG+pfLMR5MHL0CBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97ebd0d55f6985bb6c718ebda8da2a1e38100868b7c9a1ced21023ce43f3b0b8","last_reissued_at":"2026-07-05T06:21:19.923414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:19.923414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arbitrariness Lies Beyond the Fairness-Accuracy Frontier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Carol Xuan Long, Flavio P. Calmon, Hsiang Hsu, Wael Alghamdi","submitted_at":"2023-06-15T18:15:46Z","abstract_excerpt":"Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions in machine learning optimized solely for group fairness and accuracy can exacerbate predictive multiplicity. Consequently, state-of-the-art fairness interventions can mask high predictive multiplicity behind favorable group fairness and accuracy metrics. We argue that a third axis of ``arbitrariness'' should be considered when deploying models to aid decisio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09425","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/2306.09425/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":"2306.09425","created_at":"2026-07-05T06:21:19.923465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09425v1","created_at":"2026-07-05T06:21:19.923465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09425","created_at":"2026-07-05T06:21:19.923465+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7V5BVK7NGC3","created_at":"2026-07-05T06:21:19.923465+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7V5BVK7NGC3W3DR","created_at":"2026-07-05T06:21:19.923465+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7V5BVK7","created_at":"2026-07-05T06:21:19.923465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.11981","citing_title":"Welfare as a Guiding Principle for Machine Learning -- From Compass, to Lens, to Roadmap","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09520","citing_title":"Rashomon Sets and Model Multiplicity in Federated Learning","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY","json":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY.json","graph_json":"https://pith.science/api/pith-number/S7V5BVK7NGC3W3DRR262RWRKDY/graph.json","events_json":"https://pith.science/api/pith-number/S7V5BVK7NGC3W3DRR262RWRKDY/events.json","paper":"https://pith.science/paper/S7V5BVK7"},"agent_actions":{"view_html":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY","download_json":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY.json","view_paper":"https://pith.science/paper/S7V5BVK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09425&json=true","fetch_graph":"https://pith.science/api/pith-number/S7V5BVK7NGC3W3DRR262RWRKDY/graph.json","fetch_events":"https://pith.science/api/pith-number/S7V5BVK7NGC3W3DRR262RWRKDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY/action/storage_attestation","attest_author":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY/action/author_attestation","sign_citation":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY/action/citation_signature","submit_replication":"https://pith.science/pith/S7V5BVK7NGC3W3DRR262RWRKDY/action/replication_record"}},"created_at":"2026-07-05T06:21:19.923465+00:00","updated_at":"2026-07-05T06:21:19.923465+00:00"}