{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TRLH3BBFBP7XNKZW636FJLP2N6","short_pith_number":"pith:TRLH3BBF","schema_version":"1.0","canonical_sha256":"9c567d84250bff76ab36f6fc54adfa6f8ef2d58dc2e88e2d58bc621e36336c22","source":{"kind":"arxiv","id":"2008.05369","version":1},"attestation_state":"computed","paper":{"title":"Anomaly localization by modeling perceptual features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"David Dehaene, Pierre Eline","submitted_at":"2020-08-12T15:09:13Z","abstract_excerpt":"Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often identifies images or regions that do not concur with human perception, even questioning the usability of generative models for robust anomaly detection. Here, we argue that those issues can emerge from having a simplistic model of the anomaly distribution and we propose a new VAE-based model expressing a more complex anomaly model that is also closer to human perception. This "},"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":"2008.05369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-12T15:09:13Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"2ea619052a09d80150b8681298859f9812430331ad7253d3a94ca6a41b914b4a","abstract_canon_sha256":"4b98fb93bff25077dce5edcbddfea50746423364e9debbf65460ef09e7f7576e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:46.070523Z","signature_b64":"QjGL3W+fV24x/vaNNJeM3+TixejI7ThJKHEiMyL3oYOwhDfVkQSVfH0aHi+MeIZ9pM92iaz0qNJtMMdFHF+cAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c567d84250bff76ab36f6fc54adfa6f8ef2d58dc2e88e2d58bc621e36336c22","last_reissued_at":"2026-07-05T01:26:46.070135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:46.070135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anomaly localization by modeling perceptual features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"David Dehaene, Pierre Eline","submitted_at":"2020-08-12T15:09:13Z","abstract_excerpt":"Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often identifies images or regions that do not concur with human perception, even questioning the usability of generative models for robust anomaly detection. Here, we argue that those issues can emerge from having a simplistic model of the anomaly distribution and we propose a new VAE-based model expressing a more complex anomaly model that is also closer to human perception. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.05369","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/2008.05369/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":"2008.05369","created_at":"2026-07-05T01:26:46.070190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.05369v1","created_at":"2026-07-05T01:26:46.070190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.05369","created_at":"2026-07-05T01:26:46.070190+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRLH3BBFBP7X","created_at":"2026-07-05T01:26:46.070190+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRLH3BBFBP7XNKZW","created_at":"2026-07-05T01:26:46.070190+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRLH3BBF","created_at":"2026-07-05T01:26:46.070190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06194","citing_title":"Multimodal Task Representation Memory Bank vs. Catastrophic Forgetting in Anomaly Detection","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6","json":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6.json","graph_json":"https://pith.science/api/pith-number/TRLH3BBFBP7XNKZW636FJLP2N6/graph.json","events_json":"https://pith.science/api/pith-number/TRLH3BBFBP7XNKZW636FJLP2N6/events.json","paper":"https://pith.science/paper/TRLH3BBF"},"agent_actions":{"view_html":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6","download_json":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6.json","view_paper":"https://pith.science/paper/TRLH3BBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.05369&json=true","fetch_graph":"https://pith.science/api/pith-number/TRLH3BBFBP7XNKZW636FJLP2N6/graph.json","fetch_events":"https://pith.science/api/pith-number/TRLH3BBFBP7XNKZW636FJLP2N6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6/action/storage_attestation","attest_author":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6/action/author_attestation","sign_citation":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6/action/citation_signature","submit_replication":"https://pith.science/pith/TRLH3BBFBP7XNKZW636FJLP2N6/action/replication_record"}},"created_at":"2026-07-05T01:26:46.070190+00:00","updated_at":"2026-07-05T01:26:46.070190+00:00"}