{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LCR2JFDSML64FFE3RODVV5WWLE","short_pith_number":"pith:LCR2JFDS","schema_version":"1.0","canonical_sha256":"58a3a4947262fdc2949b8b875af6d6592564d3bd29c2dcc4a0aaa93eed7b77b9","source":{"kind":"arxiv","id":"2207.12201","version":2},"attestation_state":"computed","paper":{"title":"Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guansong Pang, Hongzuo Xu, Qing Liao, Songlei Jian, Yijie Wang, Yongjun Wang","submitted_at":"2022-07-25T13:43:13Z","abstract_excerpt":"Time series anomaly detection is instrumental in maintaining system availability in various domains. Current work in this research line mainly focuses on learning data normality deeply and comprehensively by devising advanced neural network structures and new reconstruction/prediction learning objectives. However, their one-class learning process can be misled by latent anomalies in training data (i.e., anomaly contamination) under the unsupervised paradigm. Their learning process also lacks knowledge about the anomalies. Consequently, they often learn a biased, inaccurate normality boundary. "},"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":"2207.12201","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-25T13:43:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d16a5e7f63a9f2bb8959b614e019fc22a48311e556ca0d5382661090ab7c3dbf","abstract_canon_sha256":"4c90dda1bf3e1033e60575b53cad10663e1964990e6421a88fb5b43911668d7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:18.737028Z","signature_b64":"MJNyxPATduW3z9IOWEs7d/dE9rvJUfs7pUuE9CF75tq/PREsQ2Nhg57LS5WHUQzlzbZcZFMA18ZsZ0pmgFR2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a3a4947262fdc2949b8b875af6d6592564d3bd29c2dcc4a0aaa93eed7b77b9","last_reissued_at":"2026-07-05T08:11:18.736538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:18.736538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guansong Pang, Hongzuo Xu, Qing Liao, Songlei Jian, Yijie Wang, Yongjun Wang","submitted_at":"2022-07-25T13:43:13Z","abstract_excerpt":"Time series anomaly detection is instrumental in maintaining system availability in various domains. Current work in this research line mainly focuses on learning data normality deeply and comprehensively by devising advanced neural network structures and new reconstruction/prediction learning objectives. However, their one-class learning process can be misled by latent anomalies in training data (i.e., anomaly contamination) under the unsupervised paradigm. Their learning process also lacks knowledge about the anomalies. Consequently, they often learn a biased, inaccurate normality boundary. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.12201","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/2207.12201/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":"2207.12201","created_at":"2026-07-05T08:11:18.736594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.12201v2","created_at":"2026-07-05T08:11:18.736594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.12201","created_at":"2026-07-05T08:11:18.736594+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCR2JFDSML64","created_at":"2026-07-05T08:11:18.736594+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCR2JFDSML64FFE3","created_at":"2026-07-05T08:11:18.736594+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCR2JFDS","created_at":"2026-07-05T08:11:18.736594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09685","citing_title":"Learning Unified Representations of Normalcy for Time Series Anomaly Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07690","citing_title":"Fortifying Time Series: DTW-Certified Robust Anomaly Detection","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE","json":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE.json","graph_json":"https://pith.science/api/pith-number/LCR2JFDSML64FFE3RODVV5WWLE/graph.json","events_json":"https://pith.science/api/pith-number/LCR2JFDSML64FFE3RODVV5WWLE/events.json","paper":"https://pith.science/paper/LCR2JFDS"},"agent_actions":{"view_html":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE","download_json":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE.json","view_paper":"https://pith.science/paper/LCR2JFDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.12201&json=true","fetch_graph":"https://pith.science/api/pith-number/LCR2JFDSML64FFE3RODVV5WWLE/graph.json","fetch_events":"https://pith.science/api/pith-number/LCR2JFDSML64FFE3RODVV5WWLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE/action/storage_attestation","attest_author":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE/action/author_attestation","sign_citation":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE/action/citation_signature","submit_replication":"https://pith.science/pith/LCR2JFDSML64FFE3RODVV5WWLE/action/replication_record"}},"created_at":"2026-07-05T08:11:18.736594+00:00","updated_at":"2026-07-05T08:11:18.736594+00:00"}