{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WDLU7ZJ3NDMGEE23C74E2M4SEZ","short_pith_number":"pith:WDLU7ZJ3","schema_version":"1.0","canonical_sha256":"b0d74fe53b68d862135b17f84d3392265d82e38d570e83b460cbfa7235ce7f7e","source":{"kind":"arxiv","id":"2303.03995","version":2},"attestation_state":"computed","paper":{"title":"Group conditional validity via multi-group learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Navid Ardeshir, Samuel Deng","submitted_at":"2023-03-07T15:51:03Z","abstract_excerpt":"We consider the problem of distribution-free conformal prediction and the criterion of group conditional validity. This criterion is motivated by many practical scenarios including hidden stratification and group fairness. Existing methods achieve such guarantees under either restrictive grouping structure or distributional assumptions, or they are overly-conservative under heteroskedastic noise. We propose a simple reduction to the problem of achieving validity guarantees for individual populations by leveraging algorithms for a problem called multi-group learning. This allows us to port theo"},"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":"2303.03995","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-07T15:51:03Z","cross_cats_sorted":["math.ST","stat.TH"],"title_canon_sha256":"515b3a18f055e95042a570534a1567ef2149de3460b521f3d363f6edb5f94476","abstract_canon_sha256":"78c5272f0906957249764a2885c49b478dd76709f75d0f5c92b7ddf9aee37ba8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:27.572216Z","signature_b64":"49oM55oYEA9EeqCkMCPbTEP0w1FcKV/Pw08aDbXyaIw6ebvJgP7nxlvI+GnHae5FjXpjMyMguC11Y3l6SNI9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d74fe53b68d862135b17f84d3392265d82e38d570e83b460cbfa7235ce7f7e","last_reissued_at":"2026-07-05T05:52:27.571713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:27.571713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group conditional validity via multi-group learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel Hsu, Navid Ardeshir, Samuel Deng","submitted_at":"2023-03-07T15:51:03Z","abstract_excerpt":"We consider the problem of distribution-free conformal prediction and the criterion of group conditional validity. This criterion is motivated by many practical scenarios including hidden stratification and group fairness. Existing methods achieve such guarantees under either restrictive grouping structure or distributional assumptions, or they are overly-conservative under heteroskedastic noise. We propose a simple reduction to the problem of achieving validity guarantees for individual populations by leveraging algorithms for a problem called multi-group learning. This allows us to port theo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03995","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.03995/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":"2303.03995","created_at":"2026-07-05T05:52:27.571779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03995v2","created_at":"2026-07-05T05:52:27.571779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03995","created_at":"2026-07-05T05:52:27.571779+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDLU7ZJ3NDMG","created_at":"2026-07-05T05:52:27.571779+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDLU7ZJ3NDMGEE23","created_at":"2026-07-05T05:52:27.571779+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDLU7ZJ3","created_at":"2026-07-05T05:52:27.571779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05562","citing_title":"Socio-Conformal Calibration in Complex Survey Data: Marginal Validity Is Not Enough for Subgroup Reliability","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ","json":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ.json","graph_json":"https://pith.science/api/pith-number/WDLU7ZJ3NDMGEE23C74E2M4SEZ/graph.json","events_json":"https://pith.science/api/pith-number/WDLU7ZJ3NDMGEE23C74E2M4SEZ/events.json","paper":"https://pith.science/paper/WDLU7ZJ3"},"agent_actions":{"view_html":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ","download_json":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ.json","view_paper":"https://pith.science/paper/WDLU7ZJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03995&json=true","fetch_graph":"https://pith.science/api/pith-number/WDLU7ZJ3NDMGEE23C74E2M4SEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WDLU7ZJ3NDMGEE23C74E2M4SEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ/action/storage_attestation","attest_author":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ/action/author_attestation","sign_citation":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ/action/citation_signature","submit_replication":"https://pith.science/pith/WDLU7ZJ3NDMGEE23C74E2M4SEZ/action/replication_record"}},"created_at":"2026-07-05T05:52:27.571779+00:00","updated_at":"2026-07-05T05:52:27.571779+00:00"}