{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ODGAXORC33475HGDMBYSPWJQDB","short_pith_number":"pith:ODGAXORC","schema_version":"1.0","canonical_sha256":"70cc0bba22def9fe9cc3607127d930187f23ef858dadd6c96c6ef98501edef1f","source":{"kind":"arxiv","id":"2210.13043","version":1},"attestation_state":"computed","paper":{"title":"Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ioana Bica, Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2022-10-24T08:57:55Z","abstract_excerpt":"High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue of outcome heterogeneity - this is prevalent in areas such as healthcare, where patients with similar features can have different outcomes, thus making reliable predictions challenging. To tackle this, we propose Data-IQ, a framework to systematically stratify examples into subgroups with respect to their outcomes. We do this by analyzing the behavior of individual examples during training, based on their predictive "},"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":"2210.13043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T08:57:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61e995e05a87dc5002e76d71d6aedef2ad6c93d5b3bc3cda1a44fd9c9e45aca3","abstract_canon_sha256":"1f76902dff896f13cd16806c2123c583418415fb22ae535cb6a80288596662de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:35.642987Z","signature_b64":"5/etJzO6oSdSRFq9OQVO2QXPDif9ggRI8E2SVDndSfclaDhJutAgciIz2fPEeuaS1vEUeyqELQPgHItf+seIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cc0bba22def9fe9cc3607127d930187f23ef858dadd6c96c6ef98501edef1f","last_reissued_at":"2026-07-05T05:09:35.642578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:35.642578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ioana Bica, Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2022-10-24T08:57:55Z","abstract_excerpt":"High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue of outcome heterogeneity - this is prevalent in areas such as healthcare, where patients with similar features can have different outcomes, thus making reliable predictions challenging. To tackle this, we propose Data-IQ, a framework to systematically stratify examples into subgroups with respect to their outcomes. We do this by analyzing the behavior of individual examples during training, based on their predictive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13043","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/2210.13043/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":"2210.13043","created_at":"2026-07-05T05:09:35.642633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13043v1","created_at":"2026-07-05T05:09:35.642633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13043","created_at":"2026-07-05T05:09:35.642633+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODGAXORC3347","created_at":"2026-07-05T05:09:35.642633+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODGAXORC33475HGD","created_at":"2026-07-05T05:09:35.642633+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODGAXORC","created_at":"2026-07-05T05:09:35.642633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.20786","citing_title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB","json":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB.json","graph_json":"https://pith.science/api/pith-number/ODGAXORC33475HGDMBYSPWJQDB/graph.json","events_json":"https://pith.science/api/pith-number/ODGAXORC33475HGDMBYSPWJQDB/events.json","paper":"https://pith.science/paper/ODGAXORC"},"agent_actions":{"view_html":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB","download_json":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB.json","view_paper":"https://pith.science/paper/ODGAXORC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13043&json=true","fetch_graph":"https://pith.science/api/pith-number/ODGAXORC33475HGDMBYSPWJQDB/graph.json","fetch_events":"https://pith.science/api/pith-number/ODGAXORC33475HGDMBYSPWJQDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB/action/storage_attestation","attest_author":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB/action/author_attestation","sign_citation":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB/action/citation_signature","submit_replication":"https://pith.science/pith/ODGAXORC33475HGDMBYSPWJQDB/action/replication_record"}},"created_at":"2026-07-05T05:09:35.642633+00:00","updated_at":"2026-07-05T05:09:35.642633+00:00"}