{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WAM34TSDDUP5NOJVWTNKE45QG5","short_pith_number":"pith:WAM34TSD","schema_version":"1.0","canonical_sha256":"b019be4e431d1fd6b935b4daa273b03753dbad8113befd17e07088971ee64f6e","source":{"kind":"arxiv","id":"2205.14297","version":2},"attestation_state":"computed","paper":{"title":"Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Efstratios Gavves, Hossein Mirzaei, Mohammad Hossein Rohban, Mohammadreza Salehi, Mohammad Sabokrou, Sajjad Shahabi","submitted_at":"2022-05-28T02:02:53Z","abstract_excerpt":"We aim for image-based novelty detection. Despite considerable progress, existing models either fail or face a dramatic drop under the so-called \"near-distribution\" setting, where the differences between normal and anomalous samples are subtle. We first demonstrate existing methods experience up to 20% decrease in performance in the near-distribution setting. Next, we propose to exploit a score-based generative model to produce synthetic near-distribution anomalous data. Our model is then fine-tuned to distinguish such data from the normal samples. We provide a quantitative as well as qualitat"},"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":"2205.14297","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T02:02:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"91ff4f8e995feafa8894d8fe94350b98e8c1b5737068b895a0969d81b7f18886","abstract_canon_sha256":"d9618df167af1dd16a674dc9ff79cad929876cbe1ed9365055cc706552c70a8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:11.871413Z","signature_b64":"EqbPxgW3VnPvyxrhU47aNxC7lTe2/emGd+ACoj7N+R07CsJbg19l9a46ky4WMdcQH+LSRt2VosVeOn2r2z+/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b019be4e431d1fd6b935b4daa273b03753dbad8113befd17e07088971ee64f6e","last_reissued_at":"2026-07-05T05:20:11.870933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:11.870933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fake It Till You Make It: Towards Accurate Near-Distribution Novelty Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Efstratios Gavves, Hossein Mirzaei, Mohammad Hossein Rohban, Mohammadreza Salehi, Mohammad Sabokrou, Sajjad Shahabi","submitted_at":"2022-05-28T02:02:53Z","abstract_excerpt":"We aim for image-based novelty detection. Despite considerable progress, existing models either fail or face a dramatic drop under the so-called \"near-distribution\" setting, where the differences between normal and anomalous samples are subtle. We first demonstrate existing methods experience up to 20% decrease in performance in the near-distribution setting. Next, we propose to exploit a score-based generative model to produce synthetic near-distribution anomalous data. Our model is then fine-tuned to distinguish such data from the normal samples. We provide a quantitative as well as qualitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14297","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/2205.14297/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":"2205.14297","created_at":"2026-07-05T05:20:11.870991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14297v2","created_at":"2026-07-05T05:20:11.870991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14297","created_at":"2026-07-05T05:20:11.870991+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAM34TSDDUP5","created_at":"2026-07-05T05:20:11.870991+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAM34TSDDUP5NOJV","created_at":"2026-07-05T05:20:11.870991+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAM34TSD","created_at":"2026-07-05T05:20:11.870991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16971","citing_title":"RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples","ref_index":62,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5","json":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5.json","graph_json":"https://pith.science/api/pith-number/WAM34TSDDUP5NOJVWTNKE45QG5/graph.json","events_json":"https://pith.science/api/pith-number/WAM34TSDDUP5NOJVWTNKE45QG5/events.json","paper":"https://pith.science/paper/WAM34TSD"},"agent_actions":{"view_html":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5","download_json":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5.json","view_paper":"https://pith.science/paper/WAM34TSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14297&json=true","fetch_graph":"https://pith.science/api/pith-number/WAM34TSDDUP5NOJVWTNKE45QG5/graph.json","fetch_events":"https://pith.science/api/pith-number/WAM34TSDDUP5NOJVWTNKE45QG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5/action/storage_attestation","attest_author":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5/action/author_attestation","sign_citation":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5/action/citation_signature","submit_replication":"https://pith.science/pith/WAM34TSDDUP5NOJVWTNKE45QG5/action/replication_record"}},"created_at":"2026-07-05T05:20:11.870991+00:00","updated_at":"2026-07-05T05:20:11.870991+00:00"}