{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TSBTQFEVFEXUEIR2GKYDWFASIR","short_pith_number":"pith:TSBTQFEV","schema_version":"1.0","canonical_sha256":"9c83381495292f42223a32b03b14124478b6a868e04eea9755350bd4d5dde2f0","source":{"kind":"arxiv","id":"2606.29720","version":1},"attestation_state":"computed","paper":{"title":"The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Zewen Liu","submitted_at":"2026-06-29T02:55:04Z","abstract_excerpt":"Resampling methods such as SMOTE and random under/over-sampling are standard tools for class-imbalanced classification, almost always evaluated by minority-class accuracy or F1. Prior work has established that undersampling degrades probability calibration by distorting the training prior [1]. We extend this lens to synthetic oversampling (SMOTE) and provide a practical, evidence-based guide to when calibration damage matters and how to fix it. Across five public datasets (imbalance ratio 1.9-70) and two ensemble models (random forest, gradient boosting), with ten seeds and paired statistics, "},"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":"2606.29720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T02:55:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b0160625d000893cd73d1f631210ce6c4eb5f6d528da1d49e41806a0e17aab3d","abstract_canon_sha256":"3194ddb0ff2ab1133be7dd9ace7aacf5b71e53e7ea9bd91590df7cde8eec0948"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:32.006124Z","signature_b64":"lUl/CcBAPsxEz9YGlzCvpjjN1yGeNT8wBidqRKjfl3i59pjG0nBL4nyaR7as1T9RFOMXI2805SANCU8wz2mzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c83381495292f42223a32b03b14124478b6a868e04eea9755350bd4d5dde2f0","last_reissued_at":"2026-06-30T02:17:32.005484Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:32.005484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Zewen Liu","submitted_at":"2026-06-29T02:55:04Z","abstract_excerpt":"Resampling methods such as SMOTE and random under/over-sampling are standard tools for class-imbalanced classification, almost always evaluated by minority-class accuracy or F1. Prior work has established that undersampling degrades probability calibration by distorting the training prior [1]. We extend this lens to synthetic oversampling (SMOTE) and provide a practical, evidence-based guide to when calibration damage matters and how to fix it. Across five public datasets (imbalance ratio 1.9-70) and two ensemble models (random forest, gradient boosting), with ten seeds and paired statistics, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29720","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/2606.29720/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":"2606.29720","created_at":"2026-06-30T02:17:32.005567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29720v1","created_at":"2026-06-30T02:17:32.005567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29720","created_at":"2026-06-30T02:17:32.005567+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSBTQFEVFEXU","created_at":"2026-06-30T02:17:32.005567+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSBTQFEVFEXUEIR2","created_at":"2026-06-30T02:17:32.005567+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSBTQFEV","created_at":"2026-06-30T02:17:32.005567+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/TSBTQFEVFEXUEIR2GKYDWFASIR","json":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR.json","graph_json":"https://pith.science/api/pith-number/TSBTQFEVFEXUEIR2GKYDWFASIR/graph.json","events_json":"https://pith.science/api/pith-number/TSBTQFEVFEXUEIR2GKYDWFASIR/events.json","paper":"https://pith.science/paper/TSBTQFEV"},"agent_actions":{"view_html":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR","download_json":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR.json","view_paper":"https://pith.science/paper/TSBTQFEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29720&json=true","fetch_graph":"https://pith.science/api/pith-number/TSBTQFEVFEXUEIR2GKYDWFASIR/graph.json","fetch_events":"https://pith.science/api/pith-number/TSBTQFEVFEXUEIR2GKYDWFASIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR/action/storage_attestation","attest_author":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR/action/author_attestation","sign_citation":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR/action/citation_signature","submit_replication":"https://pith.science/pith/TSBTQFEVFEXUEIR2GKYDWFASIR/action/replication_record"}},"created_at":"2026-06-30T02:17:32.005567+00:00","updated_at":"2026-06-30T02:17:32.005567+00:00"}