{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GRML4ZLTAB3X2APA5ITKUI5SWY","short_pith_number":"pith:GRML4ZLT","schema_version":"1.0","canonical_sha256":"3458be657300777d01e0ea26aa23b2b60c3eee843e2195085561fb58bda94f66","source":{"kind":"arxiv","id":"2404.04865","version":1},"attestation_state":"computed","paper":{"title":"On the Learnability of Out-of-distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Han, Feng Liu, Jie Lu, Yixuan Li, Zhen Fang","submitted_at":"2024-04-07T08:17:48Z","abstract_excerpt":"Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the"},"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":"2404.04865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-07T08:17:48Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"318a67e39232f1f2dc20cdd40aab9ba4bf70f05741fc277dbcc46d871af5a5fd","abstract_canon_sha256":"d35fcb8d80844ede10c88da843cafe086a5d376ea7c5bc350036992eb9505959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:22.830188Z","signature_b64":"z5OfJxcc12jDw7x3e/rk9VbDNgnxzMp5GyuGO/mYnE3PMRwGMoyQ6x6CegxZEEZG+VUGV4B8/qwVEVIA7pbOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3458be657300777d01e0ea26aa23b2b60c3eee843e2195085561fb58bda94f66","last_reissued_at":"2026-07-05T08:05:22.829762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:22.829762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Learnability of Out-of-distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Han, Feng Liu, Jie Lu, Yixuan Li, Zhen Fang","submitted_at":"2024-04-07T08:17:48Z","abstract_excerpt":"Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04865","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/2404.04865/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":"2404.04865","created_at":"2026-07-05T08:05:22.829819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04865v1","created_at":"2026-07-05T08:05:22.829819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04865","created_at":"2026-07-05T08:05:22.829819+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRML4ZLTAB3X","created_at":"2026-07-05T08:05:22.829819+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRML4ZLTAB3X2APA","created_at":"2026-07-05T08:05:22.829819+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRML4ZLT","created_at":"2026-07-05T08:05:22.829819+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/GRML4ZLTAB3X2APA5ITKUI5SWY","json":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY.json","graph_json":"https://pith.science/api/pith-number/GRML4ZLTAB3X2APA5ITKUI5SWY/graph.json","events_json":"https://pith.science/api/pith-number/GRML4ZLTAB3X2APA5ITKUI5SWY/events.json","paper":"https://pith.science/paper/GRML4ZLT"},"agent_actions":{"view_html":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY","download_json":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY.json","view_paper":"https://pith.science/paper/GRML4ZLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04865&json=true","fetch_graph":"https://pith.science/api/pith-number/GRML4ZLTAB3X2APA5ITKUI5SWY/graph.json","fetch_events":"https://pith.science/api/pith-number/GRML4ZLTAB3X2APA5ITKUI5SWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY/action/storage_attestation","attest_author":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY/action/author_attestation","sign_citation":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY/action/citation_signature","submit_replication":"https://pith.science/pith/GRML4ZLTAB3X2APA5ITKUI5SWY/action/replication_record"}},"created_at":"2026-07-05T08:05:22.829819+00:00","updated_at":"2026-07-05T08:05:22.829819+00:00"}