{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJZRD5GE53K3LTGKLYIPLKHWX2","short_pith_number":"pith:YJZRD5GE","schema_version":"1.0","canonical_sha256":"c27311f4c4eed5b5ccca5e10f5a8f6be930f006363aa035bd68928406a58b3c8","source":{"kind":"arxiv","id":"2310.03146","version":5},"attestation_state":"computed","paper":{"title":"Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Wang, Albert Montillo, Son Nguyen","submitted_at":"2023-10-04T20:18:45Z","abstract_excerpt":"Traditional deep learning (DL) models have two ubiquitous limitations. First, they assume training samples are independent and identically distributed (i.i.d), an assumption often violated in real-world datasets where samples have additional correlation due to repeat measurements (e.g., on the same participants in a longitudinal study or cells from the same sequencer). This leads to performance degradation, limited generalization, and covariate confounding, which induces Type I and Type II errors. Second, DL models typically prioritize overall accuracy, favoring accuracy on the majority while "},"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":"2310.03146","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T20:18:45Z","cross_cats_sorted":[],"title_canon_sha256":"a9142b78239b3437a038c9726a3d536e14e502967d6dcb9b2df7010c10b4ce81","abstract_canon_sha256":"215b2907dc5a92030eb6a4e565ab000af3ddeb8e169f5e1cd6d1e7fe776e0c26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:06.733570Z","signature_b64":"rFpPQclG3bb1XdCZB6VKeYQXdJJh4YkUPzkZ4aJ4EB+DOEbBsBeUTjGOALznteIHJC9Epeye27/NZj/xl9aRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c27311f4c4eed5b5ccca5e10f5a8f6be930f006363aa035bd68928406a58b3c8","last_reissued_at":"2026-07-05T09:55:06.733093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:06.733093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fairness-enhancing mixed effects deep learning improves fairness on in- and out-of-distribution clustered (non-iid) data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Wang, Albert Montillo, Son Nguyen","submitted_at":"2023-10-04T20:18:45Z","abstract_excerpt":"Traditional deep learning (DL) models have two ubiquitous limitations. First, they assume training samples are independent and identically distributed (i.i.d), an assumption often violated in real-world datasets where samples have additional correlation due to repeat measurements (e.g., on the same participants in a longitudinal study or cells from the same sequencer). This leads to performance degradation, limited generalization, and covariate confounding, which induces Type I and Type II errors. Second, DL models typically prioritize overall accuracy, favoring accuracy on the majority while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03146","kind":"arxiv","version":5},"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/2310.03146/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":"2310.03146","created_at":"2026-07-05T09:55:06.733164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03146v5","created_at":"2026-07-05T09:55:06.733164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03146","created_at":"2026-07-05T09:55:06.733164+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJZRD5GE53K3","created_at":"2026-07-05T09:55:06.733164+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJZRD5GE53K3LTGK","created_at":"2026-07-05T09:55:06.733164+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJZRD5GE","created_at":"2026-07-05T09:55:06.733164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.17330","citing_title":"SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2","json":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2.json","graph_json":"https://pith.science/api/pith-number/YJZRD5GE53K3LTGKLYIPLKHWX2/graph.json","events_json":"https://pith.science/api/pith-number/YJZRD5GE53K3LTGKLYIPLKHWX2/events.json","paper":"https://pith.science/paper/YJZRD5GE"},"agent_actions":{"view_html":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2","download_json":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2.json","view_paper":"https://pith.science/paper/YJZRD5GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03146&json=true","fetch_graph":"https://pith.science/api/pith-number/YJZRD5GE53K3LTGKLYIPLKHWX2/graph.json","fetch_events":"https://pith.science/api/pith-number/YJZRD5GE53K3LTGKLYIPLKHWX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2/action/storage_attestation","attest_author":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2/action/author_attestation","sign_citation":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2/action/citation_signature","submit_replication":"https://pith.science/pith/YJZRD5GE53K3LTGKLYIPLKHWX2/action/replication_record"}},"created_at":"2026-07-05T09:55:06.733164+00:00","updated_at":"2026-07-05T09:55:06.733164+00:00"}