{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HJYN7ORNZJ4DQISBT2XOT5I242","short_pith_number":"pith:HJYN7ORN","schema_version":"1.0","canonical_sha256":"3a70dfba2dca783822419eaee9f51ae6a893eb0704feb8ebf9e89b80f269c9ef","source":{"kind":"arxiv","id":"2402.02653","version":1},"attestation_state":"computed","paper":{"title":"Learning with Mixture of Prototypes for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Gong, Haodong Lu, Jason Xue, Kristen Moore, Lina Yao, Shuo Wang","submitted_at":"2024-02-05T00:52:50Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection methods have emerged with enhanced deep representation learning. They identify unseen OOD samples by measuring their distances from ID class centroids or prototypes. However, existing approaches learn the representation relying on oversimplified data assumptions, e.g, modeling ID data of each class with one centroid class prototype or using loss functions not d"},"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":"2402.02653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T00:52:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fb1081c42cb830666fb2a2f707354ce2a1879cb0d05ec05a0b0394325652c087","abstract_canon_sha256":"041e05740b6db51e21fdf216fd41d3ee3e1e143d414aafcc649bb1f7e94a39fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:16.786454Z","signature_b64":"yRN4DDzu3fJTg7MFaC1KZTKX4JXDADIEhunFFaBEXYGlA4IiEzHPxE640l7dAmdO86nLF0uAr8/tqt7qY1aaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a70dfba2dca783822419eaee9f51ae6a893eb0704feb8ebf9e89b80f269c9ef","last_reissued_at":"2026-07-05T07:41:16.785996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:16.785996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Mixture of Prototypes for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Gong, Haodong Lu, Jason Xue, Kristen Moore, Lina Yao, Shuo Wang","submitted_at":"2024-02-05T00:52:50Z","abstract_excerpt":"Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection methods have emerged with enhanced deep representation learning. They identify unseen OOD samples by measuring their distances from ID class centroids or prototypes. However, existing approaches learn the representation relying on oversimplified data assumptions, e.g, modeling ID data of each class with one centroid class prototype or using loss functions not d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02653","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/2402.02653/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":"2402.02653","created_at":"2026-07-05T07:41:16.786050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02653v1","created_at":"2026-07-05T07:41:16.786050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02653","created_at":"2026-07-05T07:41:16.786050+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJYN7ORNZJ4D","created_at":"2026-07-05T07:41:16.786050+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJYN7ORNZJ4DQISB","created_at":"2026-07-05T07:41:16.786050+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJYN7ORN","created_at":"2026-07-05T07:41:16.786050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17352","citing_title":"MM++: Unsupervised Scale-Invariant Multilayer OOD Detection via Top-K Gated Feature Fusion","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02252","citing_title":"ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31155","citing_title":"Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20728","citing_title":"Early High-Frequency Injection for Geometry-Sensitive OOD Detection","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242","json":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242.json","graph_json":"https://pith.science/api/pith-number/HJYN7ORNZJ4DQISBT2XOT5I242/graph.json","events_json":"https://pith.science/api/pith-number/HJYN7ORNZJ4DQISBT2XOT5I242/events.json","paper":"https://pith.science/paper/HJYN7ORN"},"agent_actions":{"view_html":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242","download_json":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242.json","view_paper":"https://pith.science/paper/HJYN7ORN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02653&json=true","fetch_graph":"https://pith.science/api/pith-number/HJYN7ORNZJ4DQISBT2XOT5I242/graph.json","fetch_events":"https://pith.science/api/pith-number/HJYN7ORNZJ4DQISBT2XOT5I242/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242/action/storage_attestation","attest_author":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242/action/author_attestation","sign_citation":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242/action/citation_signature","submit_replication":"https://pith.science/pith/HJYN7ORNZJ4DQISBT2XOT5I242/action/replication_record"}},"created_at":"2026-07-05T07:41:16.786050+00:00","updated_at":"2026-07-05T07:41:16.786050+00:00"}