{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XENRZ72LLDDF7OVQZZ6RZ72NKF","short_pith_number":"pith:XENRZ72L","schema_version":"1.0","canonical_sha256":"b91b1cff4b58c65fbab0ce7d1cff4d516d77b72c6a0ba3b72f56693ce4e2c27d","source":{"kind":"arxiv","id":"2301.04257","version":2},"attestation_state":"computed","paper":{"title":"ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Jaesung Hwang, Jongjin Lee, Kunwoong Kim, Yongdai Kim","submitted_at":"2023-01-11T01:02:27Z","abstract_excerpt":"The unsupervised outlier detection (UOD) problem refers to a task to identify inliers given training data which contain outliers as well as inliers, without any labeled information about inliers and outliers. It has been widely recognized that using fully-trained likelihood-based deep generative models (DGMs) often results in poor performance in distinguishing inliers from outliers. In this study, we claim that the likelihood itself could serve as powerful evidence for identifying inliers in UOD tasks, provided that DGMs are carefully under-fitted. Our approach begins with a novel observation "},"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":"2301.04257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-01-11T01:02:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"46e8384483a928248f14697f718a32132c4ed7c8341672a8eecba165428c4d0f","abstract_canon_sha256":"0a18da71ee2a6ac6161d684a9c53548df3c69b60087dbc18b712e0be36c8a7b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:08.300026Z","signature_b64":"4cLSekpOFqW4UimPB11Gyw7EsK6lkmWHjjstXtXTgY0gYpzSXb3BjF2xgTo0czVKYDFy6gC8Z6ydWDx7nXzkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91b1cff4b58c65fbab0ce7d1cff4d516d77b72c6a0ba3b72f56693ce4e2c27d","last_reissued_at":"2026-07-05T08:44:08.299603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:08.299603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ODIM: Outlier Detection via Likelihood of Under-Fitted Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dongha Kim, Jaesung Hwang, Jongjin Lee, Kunwoong Kim, Yongdai Kim","submitted_at":"2023-01-11T01:02:27Z","abstract_excerpt":"The unsupervised outlier detection (UOD) problem refers to a task to identify inliers given training data which contain outliers as well as inliers, without any labeled information about inliers and outliers. It has been widely recognized that using fully-trained likelihood-based deep generative models (DGMs) often results in poor performance in distinguishing inliers from outliers. In this study, we claim that the likelihood itself could serve as powerful evidence for identifying inliers in UOD tasks, provided that DGMs are carefully under-fitted. Our approach begins with a novel observation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04257","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/2301.04257/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":"2301.04257","created_at":"2026-07-05T08:44:08.299658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04257v2","created_at":"2026-07-05T08:44:08.299658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04257","created_at":"2026-07-05T08:44:08.299658+00:00"},{"alias_kind":"pith_short_12","alias_value":"XENRZ72LLDDF","created_at":"2026-07-05T08:44:08.299658+00:00"},{"alias_kind":"pith_short_16","alias_value":"XENRZ72LLDDF7OVQ","created_at":"2026-07-05T08:44:08.299658+00:00"},{"alias_kind":"pith_short_8","alias_value":"XENRZ72L","created_at":"2026-07-05T08:44:08.299658+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/XENRZ72LLDDF7OVQZZ6RZ72NKF","json":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF.json","graph_json":"https://pith.science/api/pith-number/XENRZ72LLDDF7OVQZZ6RZ72NKF/graph.json","events_json":"https://pith.science/api/pith-number/XENRZ72LLDDF7OVQZZ6RZ72NKF/events.json","paper":"https://pith.science/paper/XENRZ72L"},"agent_actions":{"view_html":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF","download_json":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF.json","view_paper":"https://pith.science/paper/XENRZ72L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04257&json=true","fetch_graph":"https://pith.science/api/pith-number/XENRZ72LLDDF7OVQZZ6RZ72NKF/graph.json","fetch_events":"https://pith.science/api/pith-number/XENRZ72LLDDF7OVQZZ6RZ72NKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF/action/storage_attestation","attest_author":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF/action/author_attestation","sign_citation":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF/action/citation_signature","submit_replication":"https://pith.science/pith/XENRZ72LLDDF7OVQZZ6RZ72NKF/action/replication_record"}},"created_at":"2026-07-05T08:44:08.299658+00:00","updated_at":"2026-07-05T08:44:08.299658+00:00"}