{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PHX7IDJTM3QRK2JOIJC3ENPCPJ","short_pith_number":"pith:PHX7IDJT","schema_version":"1.0","canonical_sha256":"79eff40d3366e115692e4245b235e27a4cbc519615401ac0ab25fff2ededab04","source":{"kind":"arxiv","id":"2204.06507","version":3},"attestation_state":"computed","paper":{"title":"Out-of-Distribution Detection with Deep Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiaojin Zhu, Yifei Ming, Yixuan Li, Yiyou Sun","submitted_at":"2022-04-13T16:45:21Z","abstract_excerpt":"Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samples are detected as OOD if they are relatively far away from in-distribution (ID) data. However, prior methods impose a strong distributional assumption of the underlying feature space, which may not always hold. In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature. Unlike prior works, our method does not impose any 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":"2204.06507","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T16:45:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"827ba91c73597bfe12b74ad66ea9217b89bb65b7abf1c0e9a0432e358c3b6078","abstract_canon_sha256":"98a2d4f5ca02f25e32848376e80c742ecb645f0a283cfdd0be6be2d73d7767f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:30.405177Z","signature_b64":"FSvk49GIOAGnAw6Z5jMdlZFXSPXwbVMX1adJOhG3ibe46OpmkhYP/Jbe+e1G3y/3gS8+yUOKHvU0rnYDyGgjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79eff40d3366e115692e4245b235e27a4cbc519615401ac0ab25fff2ededab04","last_reissued_at":"2026-07-05T05:23:30.404681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:30.404681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out-of-Distribution Detection with Deep Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiaojin Zhu, Yifei Ming, Yixuan Li, Yiyou Sun","submitted_at":"2022-04-13T16:45:21Z","abstract_excerpt":"Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samples are detected as OOD if they are relatively far away from in-distribution (ID) data. However, prior methods impose a strong distributional assumption of the underlying feature space, which may not always hold. In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature. Unlike prior works, our method does not impose any d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06507","kind":"arxiv","version":3},"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/2204.06507/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":"2204.06507","created_at":"2026-07-05T05:23:30.404748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.06507v3","created_at":"2026-07-05T05:23:30.404748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06507","created_at":"2026-07-05T05:23:30.404748+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHX7IDJTM3QR","created_at":"2026-07-05T05:23:30.404748+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHX7IDJTM3QRK2JO","created_at":"2026-07-05T05:23:30.404748+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHX7IDJT","created_at":"2026-07-05T05:23:30.404748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11920","citing_title":"Domain Restriction via Multi SAE Layer Transitions","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ","json":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ.json","graph_json":"https://pith.science/api/pith-number/PHX7IDJTM3QRK2JOIJC3ENPCPJ/graph.json","events_json":"https://pith.science/api/pith-number/PHX7IDJTM3QRK2JOIJC3ENPCPJ/events.json","paper":"https://pith.science/paper/PHX7IDJT"},"agent_actions":{"view_html":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ","download_json":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ.json","view_paper":"https://pith.science/paper/PHX7IDJT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.06507&json=true","fetch_graph":"https://pith.science/api/pith-number/PHX7IDJTM3QRK2JOIJC3ENPCPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PHX7IDJTM3QRK2JOIJC3ENPCPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ/action/storage_attestation","attest_author":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ/action/author_attestation","sign_citation":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ/action/citation_signature","submit_replication":"https://pith.science/pith/PHX7IDJTM3QRK2JOIJC3ENPCPJ/action/replication_record"}},"created_at":"2026-07-05T05:23:30.404748+00:00","updated_at":"2026-07-05T05:23:30.404748+00:00"}