{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SDTYH3A33VTZVYLSMGA3XRPE5D","short_pith_number":"pith:SDTYH3A3","schema_version":"1.0","canonical_sha256":"90e783ec1bdd679ae1726181bbc5e4e8f4dfd9f84ad9a8383d6ac9ea3f62bb0b","source":{"kind":"arxiv","id":"2503.10468","version":1},"attestation_state":"computed","paper":{"title":"OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hengyu Liu, Lin Zhu, Nanyang Ye, Qinying Gu, Yifeng Yang, Zewen Sun","submitted_at":"2025-03-13T15:41:56Z","abstract_excerpt":"Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically maintains and updates an OOD dictionary without fine-tuning. Our approach leverages a priority queue-based dictionary that accumulates representative OOD features during testing, combined with an informative inlier sampling strategy for in-distribution (ID) samples. To ensure stable performance during early testing, we propose a dual OOD stabilization mechan"},"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":"2503.10468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T15:41:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d34302f871c1b2eb988d815785fd45c32d8a8c8ba135a6c575af8d761d10907","abstract_canon_sha256":"b42ada6898965d11c312ccb150a4725d9fed60efbface4808dbd74d2bb5534f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:45.985065Z","signature_b64":"Aoh5ZAtxGyBIzU+sYKRxe+Y4OUau0SU3JkD+XjYOh4WI3VqcJT3Bo5e5AG491DX12hUQyNFyFizc10VIQ/6ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e783ec1bdd679ae1726181bbc5e4e8f4dfd9f84ad9a8383d6ac9ea3f62bb0b","last_reissued_at":"2026-07-05T10:30:45.984382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:45.984382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hengyu Liu, Lin Zhu, Nanyang Ye, Qinying Gu, Yifeng Yang, Zewen Sun","submitted_at":"2025-03-13T15:41:56Z","abstract_excerpt":"Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically maintains and updates an OOD dictionary without fine-tuning. Our approach leverages a priority queue-based dictionary that accumulates representative OOD features during testing, combined with an informative inlier sampling strategy for in-distribution (ID) samples. To ensure stable performance during early testing, we propose a dual OOD stabilization mechan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10468","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/2503.10468/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":"2503.10468","created_at":"2026-07-05T10:30:45.984460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10468v1","created_at":"2026-07-05T10:30:45.984460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10468","created_at":"2026-07-05T10:30:45.984460+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDTYH3A33VTZ","created_at":"2026-07-05T10:30:45.984460+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDTYH3A33VTZVYLS","created_at":"2026-07-05T10:30:45.984460+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDTYH3A3","created_at":"2026-07-05T10:30:45.984460+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/SDTYH3A33VTZVYLSMGA3XRPE5D","json":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D.json","graph_json":"https://pith.science/api/pith-number/SDTYH3A33VTZVYLSMGA3XRPE5D/graph.json","events_json":"https://pith.science/api/pith-number/SDTYH3A33VTZVYLSMGA3XRPE5D/events.json","paper":"https://pith.science/paper/SDTYH3A3"},"agent_actions":{"view_html":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D","download_json":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D.json","view_paper":"https://pith.science/paper/SDTYH3A3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10468&json=true","fetch_graph":"https://pith.science/api/pith-number/SDTYH3A33VTZVYLSMGA3XRPE5D/graph.json","fetch_events":"https://pith.science/api/pith-number/SDTYH3A33VTZVYLSMGA3XRPE5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D/action/storage_attestation","attest_author":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D/action/author_attestation","sign_citation":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D/action/citation_signature","submit_replication":"https://pith.science/pith/SDTYH3A33VTZVYLSMGA3XRPE5D/action/replication_record"}},"created_at":"2026-07-05T10:30:45.984460+00:00","updated_at":"2026-07-05T10:30:45.984460+00:00"}