{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D6APUHQ7G6LELANV55HENZHP2Q","short_pith_number":"pith:D6APUHQ7","schema_version":"1.0","canonical_sha256":"1f80fa1e1f37964581b5ef4e46e4efd41561b92157a44c483050699a65469308","source":{"kind":"arxiv","id":"2410.11171","version":3},"attestation_state":"computed","paper":{"title":"A Bilevel Optimization Framework for Imbalanced Data Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karen Medlin, Krishnan Raghavan, Sven Leyffer","submitted_at":"2024-10-15T01:17:23Z","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"},"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":"2410.11171","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T01:17:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"d18da3de635b8242de3b10d8320e4a85e1e3836c9686e98b666e758bd3d768ef","abstract_canon_sha256":"eea647f8d01139cb52907e9d2f91439bdb7fe1f8d17f1d651e7c4e961f014584"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:44.271484Z","signature_b64":"Th8Myv3lRGG/kl13o3MTehO+UQzY0ZKGCeyb4uZzhrsD6Mx0iYJI3OYwr1BpiEyabL7C78DRsUKkJzhrOt2WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f80fa1e1f37964581b5ef4e46e4efd41561b92157a44c483050699a65469308","last_reissued_at":"2026-07-05T11:34:44.271006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:44.271006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bilevel Optimization Framework for Imbalanced Data Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Karen Medlin, Krishnan Raghavan, Sven Leyffer","submitted_at":"2024-10-15T01:17:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11171","kind":"arxiv","version":3},"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/2410.11171/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":"2410.11171","created_at":"2026-07-05T11:34:44.271064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11171v3","created_at":"2026-07-05T11:34:44.271064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11171","created_at":"2026-07-05T11:34:44.271064+00:00"},{"alias_kind":"pith_short_12","alias_value":"D6APUHQ7G6LE","created_at":"2026-07-05T11:34:44.271064+00:00"},{"alias_kind":"pith_short_16","alias_value":"D6APUHQ7G6LELANV","created_at":"2026-07-05T11:34:44.271064+00:00"},{"alias_kind":"pith_short_8","alias_value":"D6APUHQ7","created_at":"2026-07-05T11:34:44.271064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11315","citing_title":"Sampling Imbalanced Data with Multi-objective Bilevel Optimization","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q","json":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q.json","graph_json":"https://pith.science/api/pith-number/D6APUHQ7G6LELANV55HENZHP2Q/graph.json","events_json":"https://pith.science/api/pith-number/D6APUHQ7G6LELANV55HENZHP2Q/events.json","paper":"https://pith.science/paper/D6APUHQ7"},"agent_actions":{"view_html":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q","download_json":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q.json","view_paper":"https://pith.science/paper/D6APUHQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11171&json=true","fetch_graph":"https://pith.science/api/pith-number/D6APUHQ7G6LELANV55HENZHP2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/D6APUHQ7G6LELANV55HENZHP2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q/action/storage_attestation","attest_author":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q/action/author_attestation","sign_citation":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q/action/citation_signature","submit_replication":"https://pith.science/pith/D6APUHQ7G6LELANV55HENZHP2Q/action/replication_record"}},"created_at":"2026-07-05T11:34:44.271064+00:00","updated_at":"2026-07-05T11:34:44.271064+00:00"}