{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FMCKHIVQEMAU52UYOTVF4R7I3D","short_pith_number":"pith:FMCKHIVQ","schema_version":"1.0","canonical_sha256":"2b04a3a2b023014eea9874ea5e47e8d8f26b3491e6beaf322e66c7b582c0df24","source":{"kind":"arxiv","id":"2310.18970","version":1},"attestation_state":"computed","paper":{"title":"TRIAGE: Characterizing and auditing training data for improved regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat, Zhaozhi Qian","submitted_at":"2023-10-29T10:31:59Z","abstract_excerpt":"Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classification settings, with regression settings largely understudied. To address this, we introduce TRIAGE, a novel data characterization framework tailored to regression tasks and compatible with a broad class of regressors. TRIAGE utilizes conformal predictive distributions to provide a model-agnostic scoring method, the TRIAGE score. We operationalize t"},"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":"2310.18970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-29T10:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"0563f21c1b16884d617135be8ee4f7c8e4cfde0f1bb1a5544fb80f00fda00cda","abstract_canon_sha256":"8b8f68a2d0918a20fe2cd70eb5da5d11b92e74c711b336cc9be7ce5ba5ad0a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:44.078078Z","signature_b64":"LlwSPVEFzTy55DJNzjd39TGX04cdkyxdxNRr/YAp0puo7QVQZsNyzxXjgEhQ4ZU1/A98Bt738vRGIfmfXTa3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b04a3a2b023014eea9874ea5e47e8d8f26b3491e6beaf322e66c7b582c0df24","last_reissued_at":"2026-07-05T07:06:44.077577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:44.077577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRIAGE: Characterizing and auditing training data for improved regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Crabb\\'e, Mihaela van der Schaar, Nabeel Seedat, Zhaozhi Qian","submitted_at":"2023-10-29T10:31:59Z","abstract_excerpt":"Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classification settings, with regression settings largely understudied. To address this, we introduce TRIAGE, a novel data characterization framework tailored to regression tasks and compatible with a broad class of regressors. TRIAGE utilizes conformal predictive distributions to provide a model-agnostic scoring method, the TRIAGE score. We operationalize t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18970","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/2310.18970/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":"2310.18970","created_at":"2026-07-05T07:06:44.077637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18970v1","created_at":"2026-07-05T07:06:44.077637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18970","created_at":"2026-07-05T07:06:44.077637+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMCKHIVQEMAU","created_at":"2026-07-05T07:06:44.077637+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMCKHIVQEMAU52UY","created_at":"2026-07-05T07:06:44.077637+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMCKHIVQ","created_at":"2026-07-05T07:06:44.077637+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/FMCKHIVQEMAU52UYOTVF4R7I3D","json":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D.json","graph_json":"https://pith.science/api/pith-number/FMCKHIVQEMAU52UYOTVF4R7I3D/graph.json","events_json":"https://pith.science/api/pith-number/FMCKHIVQEMAU52UYOTVF4R7I3D/events.json","paper":"https://pith.science/paper/FMCKHIVQ"},"agent_actions":{"view_html":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D","download_json":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D.json","view_paper":"https://pith.science/paper/FMCKHIVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18970&json=true","fetch_graph":"https://pith.science/api/pith-number/FMCKHIVQEMAU52UYOTVF4R7I3D/graph.json","fetch_events":"https://pith.science/api/pith-number/FMCKHIVQEMAU52UYOTVF4R7I3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D/action/storage_attestation","attest_author":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D/action/author_attestation","sign_citation":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D/action/citation_signature","submit_replication":"https://pith.science/pith/FMCKHIVQEMAU52UYOTVF4R7I3D/action/replication_record"}},"created_at":"2026-07-05T07:06:44.077637+00:00","updated_at":"2026-07-05T07:06:44.077637+00:00"}