{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEVV2XWSVCOQKPEFJFEC3GWUWT","short_pith_number":"pith:YEVV2XWS","schema_version":"1.0","canonical_sha256":"c12b5d5ed2a89d053c8549482d9ad4b4e6b86b51f51dc5f1083003b0ff14366f","source":{"kind":"arxiv","id":"2402.03502","version":1},"attestation_state":"computed","paper":{"title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Xuefeng Du, Yixuan Li, Zhen Fang","submitted_at":"2024-02-05T20:36:33Z","abstract_excerpt":"Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing the power of unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and OOD data. This lack of a clean set of OOD samples poses significant challenges in learning an optimal OOD classifier. Currently, there is a lack of research on formally understanding how unlabeled data helps OOD detection. This paper bridges the gap by introducing a new learning framework SAL (Separate An"},"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":"2402.03502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T20:36:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d7aca50395bc71afdb7324a29905c61b429f672f58376d7c8f2396eb57904637","abstract_canon_sha256":"0e8ad3c2c290ccb0d5dc55d31fdfe2b7f026ec4c8f56f498f3718fbaad0687a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:53.342504Z","signature_b64":"Pvg0UmTULb7O8avTCbCbsxYVV+bdmeADB008qdsvGI5ij7VEHBHMxYf8pYPavu1CgtihLINqw4aPz8MHf0/SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c12b5d5ed2a89d053c8549482d9ad4b4e6b86b51f51dc5f1083003b0ff14366f","last_reissued_at":"2026-07-05T07:41:53.342071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:53.342071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Does Unlabeled Data Provably Help Out-of-Distribution Detection?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Xuefeng Du, Yixuan Li, Zhen Fang","submitted_at":"2024-02-05T20:36:33Z","abstract_excerpt":"Using unlabeled data to regularize the machine learning models has demonstrated promise for improving safety and reliability in detecting out-of-distribution (OOD) data. Harnessing the power of unlabeled in-the-wild data is non-trivial due to the heterogeneity of both in-distribution (ID) and OOD data. This lack of a clean set of OOD samples poses significant challenges in learning an optimal OOD classifier. Currently, there is a lack of research on formally understanding how unlabeled data helps OOD detection. This paper bridges the gap by introducing a new learning framework SAL (Separate An"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03502","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/2402.03502/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":"2402.03502","created_at":"2026-07-05T07:41:53.342130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03502v1","created_at":"2026-07-05T07:41:53.342130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03502","created_at":"2026-07-05T07:41:53.342130+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEVV2XWSVCOQ","created_at":"2026-07-05T07:41:53.342130+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEVV2XWSVCOQKPEF","created_at":"2026-07-05T07:41:53.342130+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEVV2XWS","created_at":"2026-07-05T07:41:53.342130+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/YEVV2XWSVCOQKPEFJFEC3GWUWT","json":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT.json","graph_json":"https://pith.science/api/pith-number/YEVV2XWSVCOQKPEFJFEC3GWUWT/graph.json","events_json":"https://pith.science/api/pith-number/YEVV2XWSVCOQKPEFJFEC3GWUWT/events.json","paper":"https://pith.science/paper/YEVV2XWS"},"agent_actions":{"view_html":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT","download_json":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT.json","view_paper":"https://pith.science/paper/YEVV2XWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03502&json=true","fetch_graph":"https://pith.science/api/pith-number/YEVV2XWSVCOQKPEFJFEC3GWUWT/graph.json","fetch_events":"https://pith.science/api/pith-number/YEVV2XWSVCOQKPEFJFEC3GWUWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT/action/storage_attestation","attest_author":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT/action/author_attestation","sign_citation":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT/action/citation_signature","submit_replication":"https://pith.science/pith/YEVV2XWSVCOQKPEFJFEC3GWUWT/action/replication_record"}},"created_at":"2026-07-05T07:41:53.342130+00:00","updated_at":"2026-07-05T07:41:53.342130+00:00"}