{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GZI3SVL4KMLZMFV5456MRZPJX5","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":"a960e707e70888326959f2adf77e4d64b4b12e7fc2a5190fac58d64dd8c21128","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T18:58:31Z","title_canon_sha256":"18f5d326d7cf12825ec17d3c3966a9232ab9db1763059807c0f26f218d9e5d7a"},"schema_version":"1.0","source":{"id":"2202.08836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08836","created_at":"2026-07-05T04:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08836v3","created_at":"2026-07-05T04:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08836","created_at":"2026-07-05T04:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"GZI3SVL4KMLZ","created_at":"2026-07-05T04:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"GZI3SVL4KMLZMFV5","created_at":"2026-07-05T04:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"GZI3SVL4","created_at":"2026-07-05T04:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:29b780a722c79569a69ccca2f3c06e81e2f96c42d1e58309efeadde43b7db98d","target":"graph","created_at":"2026-07-05T04:31:12Z","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/2202.08836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"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":"2022-02-17T18:58:31Z","title":"Data-SUITE: Data-centric identification of in-distribution incongruous examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08836","kind":"arxiv","version":3},"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:c4c6f9f6d0f71d7645fef59c059919e888a51e38075339c74597748bb12352b6","target":"record","created_at":"2026-07-05T04:31:12Z","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":"a960e707e70888326959f2adf77e4d64b4b12e7fc2a5190fac58d64dd8c21128","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-17T18:58:31Z","title_canon_sha256":"18f5d326d7cf12825ec17d3c3966a9232ab9db1763059807c0f26f218d9e5d7a"},"schema_version":"1.0","source":{"id":"2202.08836","kind":"arxiv","version":3}},"canonical_sha256":"3651b9557c53179616bde77cc8e5e9bf6c995829bb5b661a95953e12de7d4757","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3651b9557c53179616bde77cc8e5e9bf6c995829bb5b661a95953e12de7d4757","first_computed_at":"2026-07-05T04:31:12.324915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:12.324915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W5PJUmr+bjW6pZP2HMrm22LhWzumaopbDLqGVZ/0wBTpZ4XWnpqpa63Y0m5tQXeIrxNIFQCAY6B6rMfd7bUEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:12.325423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.08836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4c6f9f6d0f71d7645fef59c059919e888a51e38075339c74597748bb12352b6","sha256:29b780a722c79569a69ccca2f3c06e81e2f96c42d1e58309efeadde43b7db98d"],"state_sha256":"1b2144776592416a962280b833b552e75beeb3acae2abc6175fd1f19e5af439c"}