{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A26MHF77SMH4HH22QAN6LHUQIP","short_pith_number":"pith:A26MHF77","schema_version":"1.0","canonical_sha256":"06bcc397ff930fc39f5a801be59e9043ebd021a24e6b3fdf0502cca1da2586bb","source":{"kind":"arxiv","id":"2509.02592","version":1},"attestation_state":"computed","paper":{"title":"Beyond Synthetic Augmentation: Group-Aware Threshold Calibration for Robust Balanced Accuracy in Imbalanced Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hunter Gittlin","submitted_at":"2025-08-29T05:57:17Z","abstract_excerpt":"Class imbalance remains a fundamental challenge in machine learning, with traditional solutions often creating as many problems as they solve. We demonstrate that group-aware threshold calibration--setting different decision thresholds for different demographic groups--provides superior robustness compared to synthetic data generation methods. Through extensive experiments, we show that group-specific thresholds achieve 1.5-4% higher balanced accuracy than SMOTE and CT-GAN augmented models while improving worst-group balanced accuracy. Unlike single-threshold approaches that apply one cutoff a"},"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":"2509.02592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T05:57:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70990b8d43ce1e00f7c432adbd93b6af62cf97c6e8d9d7ea12db925c636ce6f7","abstract_canon_sha256":"2e761a321280c3b5295ec5b316e3f4e1bd2a2053b059fbb44a7fd597eccf60e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:53.931938Z","signature_b64":"dPC2xaT3HmMWQ0orCa/MchmFz1gGelj7I8KQBomVqNUc2tCnZfl3r7aCxmZyHiVvHY+Imhd1ZkBYFaxbjQybAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06bcc397ff930fc39f5a801be59e9043ebd021a24e6b3fdf0502cca1da2586bb","last_reissued_at":"2026-07-05T12:03:53.931451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:53.931451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Synthetic Augmentation: Group-Aware Threshold Calibration for Robust Balanced Accuracy in Imbalanced Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hunter Gittlin","submitted_at":"2025-08-29T05:57:17Z","abstract_excerpt":"Class imbalance remains a fundamental challenge in machine learning, with traditional solutions often creating as many problems as they solve. We demonstrate that group-aware threshold calibration--setting different decision thresholds for different demographic groups--provides superior robustness compared to synthetic data generation methods. Through extensive experiments, we show that group-specific thresholds achieve 1.5-4% higher balanced accuracy than SMOTE and CT-GAN augmented models while improving worst-group balanced accuracy. Unlike single-threshold approaches that apply one cutoff a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02592","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/2509.02592/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":"2509.02592","created_at":"2026-07-05T12:03:53.931508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02592v1","created_at":"2026-07-05T12:03:53.931508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02592","created_at":"2026-07-05T12:03:53.931508+00:00"},{"alias_kind":"pith_short_12","alias_value":"A26MHF77SMH4","created_at":"2026-07-05T12:03:53.931508+00:00"},{"alias_kind":"pith_short_16","alias_value":"A26MHF77SMH4HH22","created_at":"2026-07-05T12:03:53.931508+00:00"},{"alias_kind":"pith_short_8","alias_value":"A26MHF77","created_at":"2026-07-05T12:03:53.931508+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/A26MHF77SMH4HH22QAN6LHUQIP","json":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP.json","graph_json":"https://pith.science/api/pith-number/A26MHF77SMH4HH22QAN6LHUQIP/graph.json","events_json":"https://pith.science/api/pith-number/A26MHF77SMH4HH22QAN6LHUQIP/events.json","paper":"https://pith.science/paper/A26MHF77"},"agent_actions":{"view_html":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP","download_json":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP.json","view_paper":"https://pith.science/paper/A26MHF77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02592&json=true","fetch_graph":"https://pith.science/api/pith-number/A26MHF77SMH4HH22QAN6LHUQIP/graph.json","fetch_events":"https://pith.science/api/pith-number/A26MHF77SMH4HH22QAN6LHUQIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP/action/storage_attestation","attest_author":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP/action/author_attestation","sign_citation":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP/action/citation_signature","submit_replication":"https://pith.science/pith/A26MHF77SMH4HH22QAN6LHUQIP/action/replication_record"}},"created_at":"2026-07-05T12:03:53.931508+00:00","updated_at":"2026-07-05T12:03:53.931508+00:00"}