{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D6APUHQ7G6LELANV55HENZHP2Q","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":"eea647f8d01139cb52907e9d2f91439bdb7fe1f8d17f1d651e7c4e961f014584","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T01:17:23Z","title_canon_sha256":"d18da3de635b8242de3b10d8320e4a85e1e3836c9686e98b666e758bd3d768ef"},"schema_version":"1.0","source":{"id":"2410.11171","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11171","created_at":"2026-07-05T11:34:44Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11171v3","created_at":"2026-07-05T11:34:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11171","created_at":"2026-07-05T11:34:44Z"},{"alias_kind":"pith_short_12","alias_value":"D6APUHQ7G6LE","created_at":"2026-07-05T11:34:44Z"},{"alias_kind":"pith_short_16","alias_value":"D6APUHQ7G6LELANV","created_at":"2026-07-05T11:34:44Z"},{"alias_kind":"pith_short_8","alias_value":"D6APUHQ7","created_at":"2026-07-05T11:34:44Z"}],"graph_snapshots":[{"event_id":"sha256:95f5f528cf614371d95d46fb0bb511f9954348a8d1b72e4412df913e6f180796","target":"graph","created_at":"2026-07-05T11:34:44Z","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/2410.11171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data rebalancing techniques, including oversampling and undersampling, are a common approach to addressing the challenges of imbalanced data. To tackle unresolved problems related to both oversampling and undersampling, we propose a new undersampling approach that: (i) avoids the pitfalls of noise and overlap caused by synthetic data and (ii) avoids the pitfall of under-fitting caused by random undersampling. Instead of undersampling majority data randomly, our method undersamples datapoints based on their ability to improve model loss. Using improved model loss as a proxy measurement for clas","authors_text":"Karen Medlin, Krishnan Raghavan, Sven Leyffer","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T01:17:23Z","title":"A Bilevel Optimization Framework for Imbalanced Data Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11171","kind":"arxiv","version":3},"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:fc4ca09939cb52575bfd0a658171f509f7c2edfa5dc605761faa4e76f4500914","target":"record","created_at":"2026-07-05T11:34:44Z","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":"eea647f8d01139cb52907e9d2f91439bdb7fe1f8d17f1d651e7c4e961f014584","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T01:17:23Z","title_canon_sha256":"d18da3de635b8242de3b10d8320e4a85e1e3836c9686e98b666e758bd3d768ef"},"schema_version":"1.0","source":{"id":"2410.11171","kind":"arxiv","version":3}},"canonical_sha256":"1f80fa1e1f37964581b5ef4e46e4efd41561b92157a44c483050699a65469308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f80fa1e1f37964581b5ef4e46e4efd41561b92157a44c483050699a65469308","first_computed_at":"2026-07-05T11:34:44.271006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:44.271006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Th8Myv3lRGG/kl13o3MTehO+UQzY0ZKGCeyb4uZzhrsD6Mx0iYJI3OYwr1BpiEyabL7C78DRsUKkJzhrOt2WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:44.271484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11171","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc4ca09939cb52575bfd0a658171f509f7c2edfa5dc605761faa4e76f4500914","sha256:95f5f528cf614371d95d46fb0bb511f9954348a8d1b72e4412df913e6f180796"],"state_sha256":"4c296b91ad5c4991972aba8ae6066a4d91f3a0500cfd3794386df6b441b3b296"}