{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TSBTQFEVFEXUEIR2GKYDWFASIR","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":"3194ddb0ff2ab1133be7dd9ace7aacf5b71e53e7ea9bd91590df7cde8eec0948","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T02:55:04Z","title_canon_sha256":"b0160625d000893cd73d1f631210ce6c4eb5f6d528da1d49e41806a0e17aab3d"},"schema_version":"1.0","source":{"id":"2606.29720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29720","created_at":"2026-06-30T02:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29720v1","created_at":"2026-06-30T02:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29720","created_at":"2026-06-30T02:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"TSBTQFEVFEXU","created_at":"2026-06-30T02:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"TSBTQFEVFEXUEIR2","created_at":"2026-06-30T02:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"TSBTQFEV","created_at":"2026-06-30T02:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:8a43e9ac63a27eb843ee486fb79b1929da3b377ef4655b01e48f6abce51ab443","target":"graph","created_at":"2026-06-30T02:17:32Z","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/2606.29720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Zewen Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T02:55:04Z","title":"The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29720","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:b5ac746bb2954493082037f66e7501f29bd2af86796f0f47b5c60d8ba78ae5a2","target":"record","created_at":"2026-06-30T02:17:32Z","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":"3194ddb0ff2ab1133be7dd9ace7aacf5b71e53e7ea9bd91590df7cde8eec0948","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T02:55:04Z","title_canon_sha256":"b0160625d000893cd73d1f631210ce6c4eb5f6d528da1d49e41806a0e17aab3d"},"schema_version":"1.0","source":{"id":"2606.29720","kind":"arxiv","version":1}},"canonical_sha256":"9c83381495292f42223a32b03b14124478b6a868e04eea9755350bd4d5dde2f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c83381495292f42223a32b03b14124478b6a868e04eea9755350bd4d5dde2f0","first_computed_at":"2026-06-30T02:17:32.005484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:32.005484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUl/CcBAPsxEz9YGlzCvpjjN1yGeNT8wBidqRKjfl3i59pjG0nBL4nyaR7as1T9RFOMXI2805SANCU8wz2mzBg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:32.006124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5ac746bb2954493082037f66e7501f29bd2af86796f0f47b5c60d8ba78ae5a2","sha256:8a43e9ac63a27eb843ee486fb79b1929da3b377ef4655b01e48f6abce51ab443"],"state_sha256":"ac51b6324c7fa3067333de277c68c81ab6cbaf368e872c5238d69d6b8cb45baa"}