{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GZI3SVL4KMLZMFV5456MRZPJX5","short_pith_number":"pith:GZI3SVL4","schema_version":"1.0","canonical_sha256":"3651b9557c53179616bde77cc8e5e9bf6c995829bb5b661a95953e12de7d4757","source":{"kind":"arxiv","id":"2202.08836","version":3},"attestation_state":"computed","paper":{"title":"Data-SUITE: Data-centric identification of in-distribution incongruous examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2022-02-17T18:58:31Z","abstract_excerpt":"Systematic quantification of data quality is critical for consistent model performance. Prior works have focused on out-of-distribution data. Instead, we tackle an understudied yet equally important problem of characterizing incongruous regions of in-distribution (ID) data, which may arise from feature space heterogeneity. To this end, we propose a paradigm shift with Data-SUITE: a data-centric AI framework to identify these regions, independent of a task-specific model. Data-SUITE leverages copula modeling, representation learning, and conformal prediction to build feature-wise confidence int"},"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":"2202.08836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T18:58:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18f5d326d7cf12825ec17d3c3966a9232ab9db1763059807c0f26f218d9e5d7a","abstract_canon_sha256":"a960e707e70888326959f2adf77e4d64b4b12e7fc2a5190fac58d64dd8c21128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:12.325423Z","signature_b64":"W5PJUmr+bjW6pZP2HMrm22LhWzumaopbDLqGVZ/0wBTpZ4XWnpqpa63Y0m5tQXeIrxNIFQCAY6B6rMfd7bUEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3651b9557c53179616bde77cc8e5e9bf6c995829bb5b661a95953e12de7d4757","last_reissued_at":"2026-07-05T04:31:12.324915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:12.324915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-SUITE: Data-centric identification of in-distribution incongruous examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2022-02-17T18:58:31Z","abstract_excerpt":"Systematic quantification of data quality is critical for consistent model performance. Prior works have focused on out-of-distribution data. Instead, we tackle an understudied yet equally important problem of characterizing incongruous regions of in-distribution (ID) data, which may arise from feature space heterogeneity. To this end, we propose a paradigm shift with Data-SUITE: a data-centric AI framework to identify these regions, independent of a task-specific model. Data-SUITE leverages copula modeling, representation learning, and conformal prediction to build feature-wise confidence int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08836","kind":"arxiv","version":3},"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/2202.08836/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":"2202.08836","created_at":"2026-07-05T04:31:12.324972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08836v3","created_at":"2026-07-05T04:31:12.324972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08836","created_at":"2026-07-05T04:31:12.324972+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZI3SVL4KMLZ","created_at":"2026-07-05T04:31:12.324972+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZI3SVL4KMLZMFV5","created_at":"2026-07-05T04:31:12.324972+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZI3SVL4","created_at":"2026-07-05T04:31:12.324972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5","json":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5.json","graph_json":"https://pith.science/api/pith-number/GZI3SVL4KMLZMFV5456MRZPJX5/graph.json","events_json":"https://pith.science/api/pith-number/GZI3SVL4KMLZMFV5456MRZPJX5/events.json","paper":"https://pith.science/paper/GZI3SVL4"},"agent_actions":{"view_html":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5","download_json":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5.json","view_paper":"https://pith.science/paper/GZI3SVL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08836&json=true","fetch_graph":"https://pith.science/api/pith-number/GZI3SVL4KMLZMFV5456MRZPJX5/graph.json","fetch_events":"https://pith.science/api/pith-number/GZI3SVL4KMLZMFV5456MRZPJX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5/action/storage_attestation","attest_author":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5/action/author_attestation","sign_citation":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5/action/citation_signature","submit_replication":"https://pith.science/pith/GZI3SVL4KMLZMFV5456MRZPJX5/action/replication_record"}},"created_at":"2026-07-05T04:31:12.324972+00:00","updated_at":"2026-07-05T04:31:12.324972+00:00"}