{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FIXTSGBXHKBMM7YNF2DXXWICBS","short_pith_number":"pith:FIXTSGBX","schema_version":"1.0","canonical_sha256":"2a2f3918373a82c67f0d2e877bd9020c85f4985828528b5211c38df3ab6b3097","source":{"kind":"arxiv","id":"2202.07586","version":2},"attestation_state":"computed","paper":{"title":"Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cristian Challu, Laurent Callot, Peihong Jiang, Ying Nian Wu","submitted_at":"2022-02-15T17:19:44Z","abstract_excerpt":"Multivariate time series anomaly detection has become an active area of research in recent years, with Deep Learning models outperforming previous approaches on benchmark datasets. Among reconstruction-based models, most previous work has focused on Variational Autoencoders and Generative Adversarial Networks. This work presents DGHL, a new family of generative models for time series anomaly detection, trained by maximizing the observed likelihood by posterior sampling and alternating back-propagation. A top-down Convolution Network maps a novel hierarchical latent space to time series windows"},"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":"2202.07586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-15T17:19:44Z","cross_cats_sorted":[],"title_canon_sha256":"d61cb11608cadf9c92b8814abaff3c28508305b6cf476af1c3eda3c782d04773","abstract_canon_sha256":"36cafa325d02fcfc350c1ef8fdc9b9d5400f5df2d5782c584df5712c6308af29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:04.767619Z","signature_b64":"GmKJ7Y5SYo6CvLGAPgyb2kdEJpGckGm65cFfVbDezF9na+ckobar0LMvuYx4ikZslZq57jOs7+5C40TQ7L2NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2f3918373a82c67f0d2e877bd9020c85f4985828528b5211c38df3ab6b3097","last_reissued_at":"2026-07-05T04:00:04.767216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:04.767216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cristian Challu, Laurent Callot, Peihong Jiang, Ying Nian Wu","submitted_at":"2022-02-15T17:19:44Z","abstract_excerpt":"Multivariate time series anomaly detection has become an active area of research in recent years, with Deep Learning models outperforming previous approaches on benchmark datasets. Among reconstruction-based models, most previous work has focused on Variational Autoencoders and Generative Adversarial Networks. This work presents DGHL, a new family of generative models for time series anomaly detection, trained by maximizing the observed likelihood by posterior sampling and alternating back-propagation. A top-down Convolution Network maps a novel hierarchical latent space to time series windows"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07586","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/2202.07586/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":"2202.07586","created_at":"2026-07-05T04:00:04.767272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07586v2","created_at":"2026-07-05T04:00:04.767272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07586","created_at":"2026-07-05T04:00:04.767272+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIXTSGBXHKBM","created_at":"2026-07-05T04:00:04.767272+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIXTSGBXHKBMM7YN","created_at":"2026-07-05T04:00:04.767272+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIXTSGBX","created_at":"2026-07-05T04:00:04.767272+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/FIXTSGBXHKBMM7YNF2DXXWICBS","json":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS.json","graph_json":"https://pith.science/api/pith-number/FIXTSGBXHKBMM7YNF2DXXWICBS/graph.json","events_json":"https://pith.science/api/pith-number/FIXTSGBXHKBMM7YNF2DXXWICBS/events.json","paper":"https://pith.science/paper/FIXTSGBX"},"agent_actions":{"view_html":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS","download_json":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS.json","view_paper":"https://pith.science/paper/FIXTSGBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07586&json=true","fetch_graph":"https://pith.science/api/pith-number/FIXTSGBXHKBMM7YNF2DXXWICBS/graph.json","fetch_events":"https://pith.science/api/pith-number/FIXTSGBXHKBMM7YNF2DXXWICBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS/action/storage_attestation","attest_author":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS/action/author_attestation","sign_citation":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS/action/citation_signature","submit_replication":"https://pith.science/pith/FIXTSGBXHKBMM7YNF2DXXWICBS/action/replication_record"}},"created_at":"2026-07-05T04:00:04.767272+00:00","updated_at":"2026-07-05T04:00:04.767272+00:00"}