{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3APNEQ36PD5ZPCEOQJQT5PH2NS","short_pith_number":"pith:3APNEQ36","schema_version":"1.0","canonical_sha256":"d81ed2437e78fb97888e82613ebcfa6cb6797017a32b263329d3320872e3eac9","source":{"kind":"arxiv","id":"2606.26053","version":1},"attestation_state":"computed","paper":{"title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anru R. Zhang, Pengfei Lyu, Zhengchi Ma","submitted_at":"2026-06-24T17:30:36Z","abstract_excerpt":"Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood. This paper develops a framework for characterizing when synthetic minority augmentation can improve threshold-integrated and threshold-optimized metrics, including AUROC, AUPRC, best-threshold balanced accuracy, and best-threshold \\(\\F_1\\) score. We separate the effect of augmentation into two components: a change in effective class weighting and a discrepancy between the synthetic and true minority distributions. Under well-specified score"},"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":"2606.26053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T17:30:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4b26ef9c969dd8771965393d0accbc00bed078e8e888c3825321a7a0829ef53","abstract_canon_sha256":"e769af4029ebb904fabb1575fd486478e820e0897678739e513939cdc14bbb86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:47.133856Z","signature_b64":"TV4QrACB3wtKauThcyDpAaNp0J2XZfVCjdfF9AvXqyn875HaexQQV+xXP+H2HkJqns3Oi2CWUSi7hMe+UHQiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d81ed2437e78fb97888e82613ebcfa6cb6797017a32b263329d3320872e3eac9","last_reissued_at":"2026-06-25T01:18:47.133479Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:47.133479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anru R. Zhang, Pengfei Lyu, Zhengchi Ma","submitted_at":"2026-06-24T17:30:36Z","abstract_excerpt":"Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood. This paper develops a framework for characterizing when synthetic minority augmentation can improve threshold-integrated and threshold-optimized metrics, including AUROC, AUPRC, best-threshold balanced accuracy, and best-threshold \\(\\F_1\\) score. We separate the effect of augmentation into two components: a change in effective class weighting and a discrepancy between the synthetic and true minority distributions. Under well-specified score"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26053","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/2606.26053/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":"2606.26053","created_at":"2026-06-25T01:18:47.133542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26053v1","created_at":"2026-06-25T01:18:47.133542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26053","created_at":"2026-06-25T01:18:47.133542+00:00"},{"alias_kind":"pith_short_12","alias_value":"3APNEQ36PD5Z","created_at":"2026-06-25T01:18:47.133542+00:00"},{"alias_kind":"pith_short_16","alias_value":"3APNEQ36PD5ZPCEO","created_at":"2026-06-25T01:18:47.133542+00:00"},{"alias_kind":"pith_short_8","alias_value":"3APNEQ36","created_at":"2026-06-25T01:18:47.133542+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/3APNEQ36PD5ZPCEOQJQT5PH2NS","json":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS.json","graph_json":"https://pith.science/api/pith-number/3APNEQ36PD5ZPCEOQJQT5PH2NS/graph.json","events_json":"https://pith.science/api/pith-number/3APNEQ36PD5ZPCEOQJQT5PH2NS/events.json","paper":"https://pith.science/paper/3APNEQ36"},"agent_actions":{"view_html":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS","download_json":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS.json","view_paper":"https://pith.science/paper/3APNEQ36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26053&json=true","fetch_graph":"https://pith.science/api/pith-number/3APNEQ36PD5ZPCEOQJQT5PH2NS/graph.json","fetch_events":"https://pith.science/api/pith-number/3APNEQ36PD5ZPCEOQJQT5PH2NS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS/action/storage_attestation","attest_author":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS/action/author_attestation","sign_citation":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS/action/citation_signature","submit_replication":"https://pith.science/pith/3APNEQ36PD5ZPCEOQJQT5PH2NS/action/replication_record"}},"created_at":"2026-06-25T01:18:47.133542+00:00","updated_at":"2026-06-25T01:18:47.133542+00:00"}