{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3APNEQ36PD5ZPCEOQJQT5PH2NS","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":"e769af4029ebb904fabb1575fd486478e820e0897678739e513939cdc14bbb86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T17:30:36Z","title_canon_sha256":"a4b26ef9c969dd8771965393d0accbc00bed078e8e888c3825321a7a0829ef53"},"schema_version":"1.0","source":{"id":"2606.26053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26053","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26053v1","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26053","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"3APNEQ36PD5Z","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"3APNEQ36PD5ZPCEO","created_at":"2026-06-25T01:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"3APNEQ36","created_at":"2026-06-25T01:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:17d1c9b3e4643a3c0de7dd9ee0ff958b44e9a3d50707bae10853e509e37cf516","target":"graph","created_at":"2026-06-25T01:18:47Z","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/2606.26053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anru R. Zhang, Pengfei Lyu, Zhengchi Ma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T17:30:36Z","title":"When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26053","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":"sha256:8ee0dc41b5e3acfb7c799883eda577396171cfe1ca8f819bb90272a77d0c413b","target":"record","created_at":"2026-06-25T01:18:47Z","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":"e769af4029ebb904fabb1575fd486478e820e0897678739e513939cdc14bbb86","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-24T17:30:36Z","title_canon_sha256":"a4b26ef9c969dd8771965393d0accbc00bed078e8e888c3825321a7a0829ef53"},"schema_version":"1.0","source":{"id":"2606.26053","kind":"arxiv","version":1}},"canonical_sha256":"d81ed2437e78fb97888e82613ebcfa6cb6797017a32b263329d3320872e3eac9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d81ed2437e78fb97888e82613ebcfa6cb6797017a32b263329d3320872e3eac9","first_computed_at":"2026-06-25T01:18:47.133479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:47.133479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TV4QrACB3wtKauThcyDpAaNp0J2XZfVCjdfF9AvXqyn875HaexQQV+xXP+H2HkJqns3Oi2CWUSi7hMe+UHQiAQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:47.133856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ee0dc41b5e3acfb7c799883eda577396171cfe1ca8f819bb90272a77d0c413b","sha256:17d1c9b3e4643a3c0de7dd9ee0ff958b44e9a3d50707bae10853e509e37cf516"],"state_sha256":"04923354c5a0d5e8c4329a3ae1c9f1ca6c69d48d7b9407c2bce897b93ff5a0d3"}