{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5R3G373V3M2H66EDBJHLLCSFBQ","short_pith_number":"pith:5R3G373V","schema_version":"1.0","canonical_sha256":"ec766dff75db347f78830a4eb58a450c36d775fdd5686a9f855c6c0fd5990a83","source":{"kind":"arxiv","id":"2504.09330","version":2},"attestation_state":"computed","paper":{"title":"Regretful Decisions under Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Berk Ustun, Flavio P. Calmon, Sujay Nagaraj, Yang Liu","submitted_at":"2025-04-12T20:21:24Z","abstract_excerpt":"Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from datasets with noisy labels. In this paper, we study the instance-level impact of learning under label noise. We introduce a notion of regret for this regime, which measures the number of unforeseen mistakes due to noisy labels. We show that standard approaches to learning under label noise can return models that perform well at a population-level while subjecting"},"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":"2504.09330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-12T20:21:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4cf602f55d2461b7908430703d0f4898d3e2a9e3abdd174bd6c98749ec88a59","abstract_canon_sha256":"6e55fa6f590e0e9e2003f496191208806221eaafcb4a224a6dc6fa5ee7d3f8ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:44.658253Z","signature_b64":"zAYtIm3F0u9T4jvpJlq3h7GtaTivU6gorW23tL7+6LX/cHTrA5VO7VOECm4DVX6xRGv2pgpoP+teRUizm7mABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec766dff75db347f78830a4eb58a450c36d775fdd5686a9f855c6c0fd5990a83","last_reissued_at":"2026-07-05T11:17:44.657785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:44.657785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regretful Decisions under Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Berk Ustun, Flavio P. Calmon, Sujay Nagaraj, Yang Liu","submitted_at":"2025-04-12T20:21:24Z","abstract_excerpt":"Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from datasets with noisy labels. In this paper, we study the instance-level impact of learning under label noise. We introduce a notion of regret for this regime, which measures the number of unforeseen mistakes due to noisy labels. We show that standard approaches to learning under label noise can return models that perform well at a population-level while subjecting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09330","kind":"arxiv","version":2},"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/2504.09330/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":"2504.09330","created_at":"2026-07-05T11:17:44.657848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09330v2","created_at":"2026-07-05T11:17:44.657848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09330","created_at":"2026-07-05T11:17:44.657848+00:00"},{"alias_kind":"pith_short_12","alias_value":"5R3G373V3M2H","created_at":"2026-07-05T11:17:44.657848+00:00"},{"alias_kind":"pith_short_16","alias_value":"5R3G373V3M2H66ED","created_at":"2026-07-05T11:17:44.657848+00:00"},{"alias_kind":"pith_short_8","alias_value":"5R3G373V","created_at":"2026-07-05T11:17:44.657848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02169","citing_title":"Statistical Inference for Responsiveness Verification","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ","json":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ.json","graph_json":"https://pith.science/api/pith-number/5R3G373V3M2H66EDBJHLLCSFBQ/graph.json","events_json":"https://pith.science/api/pith-number/5R3G373V3M2H66EDBJHLLCSFBQ/events.json","paper":"https://pith.science/paper/5R3G373V"},"agent_actions":{"view_html":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ","download_json":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ.json","view_paper":"https://pith.science/paper/5R3G373V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09330&json=true","fetch_graph":"https://pith.science/api/pith-number/5R3G373V3M2H66EDBJHLLCSFBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5R3G373V3M2H66EDBJHLLCSFBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ/action/storage_attestation","attest_author":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ/action/author_attestation","sign_citation":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ/action/citation_signature","submit_replication":"https://pith.science/pith/5R3G373V3M2H66EDBJHLLCSFBQ/action/replication_record"}},"created_at":"2026-07-05T11:17:44.657848+00:00","updated_at":"2026-07-05T11:17:44.657848+00:00"}