{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ODGAXORC33475HGDMBYSPWJQDB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f76902dff896f13cd16806c2123c583418415fb22ae535cb6a80288596662de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T08:57:55Z","title_canon_sha256":"61e995e05a87dc5002e76d71d6aedef2ad6c93d5b3bc3cda1a44fd9c9e45aca3"},"schema_version":"1.0","source":{"id":"2210.13043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13043","created_at":"2026-07-05T05:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13043v1","created_at":"2026-07-05T05:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13043","created_at":"2026-07-05T05:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"ODGAXORC3347","created_at":"2026-07-05T05:09:35Z"},{"alias_kind":"pith_short_16","alias_value":"ODGAXORC33475HGD","created_at":"2026-07-05T05:09:35Z"},{"alias_kind":"pith_short_8","alias_value":"ODGAXORC","created_at":"2026-07-05T05:09:35Z"}],"graph_snapshots":[{"event_id":"sha256:cdcaf10a152c1ad2e56f95de5bca97343c9399b6168a005935c82f64b5cf5dd1","target":"graph","created_at":"2026-07-05T05:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.13043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ioana Bica, Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T08:57:55Z","title":"Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13043","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a58fa92beffdbaf36b7cbe0dfdc269a2dcd1a8d635d035290fd4e38da5b012ca","target":"record","created_at":"2026-07-05T05:09:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f76902dff896f13cd16806c2123c583418415fb22ae535cb6a80288596662de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T08:57:55Z","title_canon_sha256":"61e995e05a87dc5002e76d71d6aedef2ad6c93d5b3bc3cda1a44fd9c9e45aca3"},"schema_version":"1.0","source":{"id":"2210.13043","kind":"arxiv","version":1}},"canonical_sha256":"70cc0bba22def9fe9cc3607127d930187f23ef858dadd6c96c6ef98501edef1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70cc0bba22def9fe9cc3607127d930187f23ef858dadd6c96c6ef98501edef1f","first_computed_at":"2026-07-05T05:09:35.642578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:09:35.642578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5/etJzO6oSdSRFq9OQVO2QXPDif9ggRI8E2SVDndSfclaDhJutAgciIz2fPEeuaS1vEUeyqELQPgHItf+seIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:09:35.642987Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a58fa92beffdbaf36b7cbe0dfdc269a2dcd1a8d635d035290fd4e38da5b012ca","sha256:cdcaf10a152c1ad2e56f95de5bca97343c9399b6168a005935c82f64b5cf5dd1"],"state_sha256":"d96927800e17ab892d14a108e4cc59b9b30a2f035699c831f732be09c5135aac"}