{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L36LBIZNS6PGTT3PITZUZVL37P","short_pith_number":"pith:L36LBIZN","schema_version":"1.0","canonical_sha256":"5efcb0a32d979e69cf6f44f34cd57bfbf5ee7801d9966c4d4491b34a0161d9b5","source":{"kind":"arxiv","id":"2202.03299","version":2},"attestation_state":"computed","paper":{"title":"Training OOD Detectors in their Natural Habitats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Julia Nakhleh, Julian Katz-Samuels, Robert Nowak, Yixuan Li","submitted_at":"2022-02-07T15:38:39Z","abstract_excerpt":"Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data, which naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. O"},"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":"2202.03299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T15:38:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fad89959442286fb15f66540270e7e46eaef0930de2d21fcbc4fa5e9d760c61e","abstract_canon_sha256":"96e367864c08ef2f2011a81272a7315bb84736cc1a4f83679c79eef29c8fb499"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:58.856634Z","signature_b64":"KNvk+V2hpqfU4lHTcbM2s4f+T1qWH6AyNaF+aoYxiMBsdgapwAX0gv4QPGJvha4Ihx5tA27FNbNwg63PAtDeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5efcb0a32d979e69cf6f44f34cd57bfbf5ee7801d9966c4d4491b34a0161d9b5","last_reissued_at":"2026-07-05T04:35:58.856148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:58.856148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training OOD Detectors in their Natural Habitats","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Julia Nakhleh, Julian Katz-Samuels, Robert Nowak, Yixuan Li","submitted_at":"2022-02-07T15:38:39Z","abstract_excerpt":"Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild. Recent methods use auxiliary outlier data to regularize the model for improved OOD detection. However, these approaches make a strong distributional assumption that the auxiliary outlier data is completely separable from the in-distribution (ID) data. In this paper, we propose a novel framework that leverages wild mixture data, which naturally consists of both ID and OOD samples. Such wild data is abundant and arises freely upon deploying a machine learning classifier in their natural habitats. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03299","kind":"arxiv","version":2},"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/2202.03299/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":"2202.03299","created_at":"2026-07-05T04:35:58.856202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03299v2","created_at":"2026-07-05T04:35:58.856202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03299","created_at":"2026-07-05T04:35:58.856202+00:00"},{"alias_kind":"pith_short_12","alias_value":"L36LBIZNS6PG","created_at":"2026-07-05T04:35:58.856202+00:00"},{"alias_kind":"pith_short_16","alias_value":"L36LBIZNS6PGTT3P","created_at":"2026-07-05T04:35:58.856202+00:00"},{"alias_kind":"pith_short_8","alias_value":"L36LBIZN","created_at":"2026-07-05T04:35:58.856202+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/L36LBIZNS6PGTT3PITZUZVL37P","json":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P.json","graph_json":"https://pith.science/api/pith-number/L36LBIZNS6PGTT3PITZUZVL37P/graph.json","events_json":"https://pith.science/api/pith-number/L36LBIZNS6PGTT3PITZUZVL37P/events.json","paper":"https://pith.science/paper/L36LBIZN"},"agent_actions":{"view_html":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P","download_json":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P.json","view_paper":"https://pith.science/paper/L36LBIZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03299&json=true","fetch_graph":"https://pith.science/api/pith-number/L36LBIZNS6PGTT3PITZUZVL37P/graph.json","fetch_events":"https://pith.science/api/pith-number/L36LBIZNS6PGTT3PITZUZVL37P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P/action/storage_attestation","attest_author":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P/action/author_attestation","sign_citation":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P/action/citation_signature","submit_replication":"https://pith.science/pith/L36LBIZNS6PGTT3PITZUZVL37P/action/replication_record"}},"created_at":"2026-07-05T04:35:58.856202+00:00","updated_at":"2026-07-05T04:35:58.856202+00:00"}