{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SOZY4MVQFDONSWYMSVFTATHXIM","short_pith_number":"pith:SOZY4MVQ","schema_version":"1.0","canonical_sha256":"93b38e32b028dcd95b0c954b304cf743160a1959e48588f9c33a4ce4dad81b83","source":{"kind":"arxiv","id":"2411.14049","version":1},"attestation_state":"computed","paper":{"title":"Out-Of-Distribution Detection with Diversification (Provably)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Changqing Zhang, Haiyun Yao, Huazhu Fu, Qinghua Hu, Xi Peng, Zongbo Han","submitted_at":"2024-11-21T11:56:32Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outliers (e.g., data from the web or other datasets) in training. However, we experimentally reveal that these methods still struggle to generalize their detection capabilities to unknown OOD data, due to the limited diversity of the auxiliary outliers collected. Therefore, we thoroughly examine this problem from the generalization perspective and demonstrate that a more diverse set of auxiliary outliers is essential for "},"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":"2411.14049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T11:56:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7d451da18fa30b0ccd3a35808f109f46f54f486a3f90d9091dfdf5a0e1f78a6a","abstract_canon_sha256":"a6d696268ec30b48c8ff70ae16f99db89b9c1cfe3604989420f969a605cc206c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:40.968037Z","signature_b64":"CshTqKQPQ0wZV84m0PgFFL+GgDAjHE49XIw7fFTy+dmXr5+NZa+mn5GBSfuxV/O8Ml80UnBgOoryxRDeF4rwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93b38e32b028dcd95b0c954b304cf743160a1959e48588f9c33a4ce4dad81b83","last_reissued_at":"2026-07-05T09:38:40.967674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:40.967674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-Of-Distribution Detection with Diversification (Provably)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Changqing Zhang, Haiyun Yao, Huazhu Fu, Qinghua Hu, Xi Peng, Zongbo Han","submitted_at":"2024-11-21T11:56:32Z","abstract_excerpt":"Out-of-distribution (OOD) detection is crucial for ensuring reliable deployment of machine learning models. Recent advancements focus on utilizing easily accessible auxiliary outliers (e.g., data from the web or other datasets) in training. However, we experimentally reveal that these methods still struggle to generalize their detection capabilities to unknown OOD data, due to the limited diversity of the auxiliary outliers collected. Therefore, we thoroughly examine this problem from the generalization perspective and demonstrate that a more diverse set of auxiliary outliers is essential for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14049","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/2411.14049/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":"2411.14049","created_at":"2026-07-05T09:38:40.967729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14049v1","created_at":"2026-07-05T09:38:40.967729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14049","created_at":"2026-07-05T09:38:40.967729+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOZY4MVQFDON","created_at":"2026-07-05T09:38:40.967729+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOZY4MVQFDONSWYM","created_at":"2026-07-05T09:38:40.967729+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOZY4MVQ","created_at":"2026-07-05T09:38:40.967729+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/SOZY4MVQFDONSWYMSVFTATHXIM","json":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM.json","graph_json":"https://pith.science/api/pith-number/SOZY4MVQFDONSWYMSVFTATHXIM/graph.json","events_json":"https://pith.science/api/pith-number/SOZY4MVQFDONSWYMSVFTATHXIM/events.json","paper":"https://pith.science/paper/SOZY4MVQ"},"agent_actions":{"view_html":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM","download_json":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM.json","view_paper":"https://pith.science/paper/SOZY4MVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14049&json=true","fetch_graph":"https://pith.science/api/pith-number/SOZY4MVQFDONSWYMSVFTATHXIM/graph.json","fetch_events":"https://pith.science/api/pith-number/SOZY4MVQFDONSWYMSVFTATHXIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM/action/storage_attestation","attest_author":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM/action/author_attestation","sign_citation":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM/action/citation_signature","submit_replication":"https://pith.science/pith/SOZY4MVQFDONSWYMSVFTATHXIM/action/replication_record"}},"created_at":"2026-07-05T09:38:40.967729+00:00","updated_at":"2026-07-05T09:38:40.967729+00:00"}