{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E7UPRO3KQ37MJULMUXZOH4S523","short_pith_number":"pith:E7UPRO3K","schema_version":"1.0","canonical_sha256":"27e8f8bb6a86fec4d16ca5f2e3f25dd6c8212cde1d498627781e5b4b368bbd0d","source":{"kind":"arxiv","id":"2108.00462","version":1},"attestation_state":"computed","paper":{"title":"Explainable Deep Few-shot Anomaly Detection with Deviation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Choubo Ding, Chunhua Shen, Guansong Pang","submitted_at":"2021-08-01T14:33:17Z","abstract_excerpt":"Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train "},"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":"2108.00462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-01T14:33:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fdb1f9b0c7f35cd6d7546ca566ffa26588cc759ff6c1fb791b7095b9f44098c","abstract_canon_sha256":"1d31bf18b3e0ab8d2fafdd0653afeb102053ef2774a726f7ddda39024a87d07e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:23.487976Z","signature_b64":"vXYo2zhukxEJ0Uifq75fdFTZS7BiVLMG4RNHNUYJk/rSlwi93nWOXoLTyIZ2eG5TyOmzW2a6KNnUigG3yYVPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27e8f8bb6a86fec4d16ca5f2e3f25dd6c8212cde1d498627781e5b4b368bbd0d","last_reissued_at":"2026-07-05T03:02:23.487544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:23.487544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Deep Few-shot Anomaly Detection with Deviation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Choubo Ding, Chunhua Shen, Guansong Pang","submitted_at":"2021-08-01T14:33:17Z","abstract_excerpt":"Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00462","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/2108.00462/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":"2108.00462","created_at":"2026-07-05T03:02:23.487602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00462v1","created_at":"2026-07-05T03:02:23.487602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00462","created_at":"2026-07-05T03:02:23.487602+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7UPRO3KQ37M","created_at":"2026-07-05T03:02:23.487602+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7UPRO3KQ37MJULM","created_at":"2026-07-05T03:02:23.487602+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7UPRO3K","created_at":"2026-07-05T03:02:23.487602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02252","citing_title":"ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23231","citing_title":"Beyond Normal References: Discriminative Few-Shot Anomaly Detection","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20981","citing_title":"Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02438","citing_title":"Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02438","citing_title":"Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02439","citing_title":"Anomaly-Preference Image Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02438","citing_title":"Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523","json":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523.json","graph_json":"https://pith.science/api/pith-number/E7UPRO3KQ37MJULMUXZOH4S523/graph.json","events_json":"https://pith.science/api/pith-number/E7UPRO3KQ37MJULMUXZOH4S523/events.json","paper":"https://pith.science/paper/E7UPRO3K"},"agent_actions":{"view_html":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523","download_json":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523.json","view_paper":"https://pith.science/paper/E7UPRO3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00462&json=true","fetch_graph":"https://pith.science/api/pith-number/E7UPRO3KQ37MJULMUXZOH4S523/graph.json","fetch_events":"https://pith.science/api/pith-number/E7UPRO3KQ37MJULMUXZOH4S523/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523/action/storage_attestation","attest_author":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523/action/author_attestation","sign_citation":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523/action/citation_signature","submit_replication":"https://pith.science/pith/E7UPRO3KQ37MJULMUXZOH4S523/action/replication_record"}},"created_at":"2026-07-05T03:02:23.487602+00:00","updated_at":"2026-07-05T03:02:23.487602+00:00"}