{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ML3SROPLGN7DVH7GIDTN5Y7BDZ","short_pith_number":"pith:ML3SROPL","schema_version":"1.0","canonical_sha256":"62f728b9eb337e3a9fe640e6dee3e11e7c0d9a300073c809a14eeeb5666189bf","source":{"kind":"arxiv","id":"2302.07849","version":4},"attestation_state":"computed","paper":{"title":"Zero-Shot Anomaly Detection via Batch Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Maja Rudolph, Marius Kloft, Padhraic Smyth, Stephan Mandt","submitted_at":"2023-02-15T18:34:15Z","abstract_excerpt":"Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the \"new normal,\" has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch n"},"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":"2302.07849","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-15T18:34:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3f130e41b12490dfe5bb818406abcb69e1d8fe8d1aa5c5a3d0fe0db170f8ed46","abstract_canon_sha256":"8d72f7e3ad6d7afcc4c7029de607973f57de8d1166cb0b51d39aa11755623150"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:22.755869Z","signature_b64":"CiQLUmktNxxhKa+nBDU5GmHI8b4mneAOoXdrjhwb4WWQECwt6C+K0h8SBg6rG52gNDNN5eNLvs6bEWTC2UcqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f728b9eb337e3a9fe640e6dee3e11e7c0d9a300073c809a14eeeb5666189bf","last_reissued_at":"2026-07-05T07:10:22.755361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:22.755361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Anomaly Detection via Batch Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aodong Li, Chen Qiu, Maja Rudolph, Marius Kloft, Padhraic Smyth, Stephan Mandt","submitted_at":"2023-02-15T18:34:15Z","abstract_excerpt":"Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is available for the \"new normal,\" has led to the development of zero-shot AD techniques. In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD. Our approach trains off-the-shelf deep anomaly detectors (such as deep SVDD) to adapt to a set of inter-related training data distributions in combination with batch n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07849","kind":"arxiv","version":4},"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/2302.07849/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":"2302.07849","created_at":"2026-07-05T07:10:22.755423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07849v4","created_at":"2026-07-05T07:10:22.755423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07849","created_at":"2026-07-05T07:10:22.755423+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML3SROPLGN7D","created_at":"2026-07-05T07:10:22.755423+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML3SROPLGN7DVH7G","created_at":"2026-07-05T07:10:22.755423+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML3SROPL","created_at":"2026-07-05T07:10:22.755423+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/ML3SROPLGN7DVH7GIDTN5Y7BDZ","json":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ.json","graph_json":"https://pith.science/api/pith-number/ML3SROPLGN7DVH7GIDTN5Y7BDZ/graph.json","events_json":"https://pith.science/api/pith-number/ML3SROPLGN7DVH7GIDTN5Y7BDZ/events.json","paper":"https://pith.science/paper/ML3SROPL"},"agent_actions":{"view_html":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ","download_json":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ.json","view_paper":"https://pith.science/paper/ML3SROPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07849&json=true","fetch_graph":"https://pith.science/api/pith-number/ML3SROPLGN7DVH7GIDTN5Y7BDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ML3SROPLGN7DVH7GIDTN5Y7BDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ/action/storage_attestation","attest_author":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ/action/author_attestation","sign_citation":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ/action/citation_signature","submit_replication":"https://pith.science/pith/ML3SROPLGN7DVH7GIDTN5Y7BDZ/action/replication_record"}},"created_at":"2026-07-05T07:10:22.755423+00:00","updated_at":"2026-07-05T07:10:22.755423+00:00"}