{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SNW5CLBF6JSK5655R7ACKXVO4J","short_pith_number":"pith:SNW5CLBF","schema_version":"1.0","canonical_sha256":"936dd12c25f264aefbbd8fc0255eaee257b69cac40f4aae40a73aaa82b0b18e8","source":{"kind":"arxiv","id":"2107.07702","version":1},"attestation_state":"computed","paper":{"title":"Neural Contextual Anomaly Detection for Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris U. Carmona, Fran\\c{c}ois-Xavier Aubet, Jan Gasthaus, Valentin Flunkert","submitted_at":"2021-07-16T04:33:53Z","abstract_excerpt":"We introduce Neural Contextual Anomaly Detection (NCAD), a framework for anomaly detection on time series that scales seamlessly from the unsupervised to supervised setting, and is applicable to both univariate and multivariate time series. This is achieved by effectively combining recent developments in representation learning for multivariate time series, with techniques for deep anomaly detection originally developed for computer vision that we tailor to the time series setting. Our window-based approach facilitates learning the boundary between normal and anomalous classes by injecting gen"},"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":"2107.07702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-16T04:33:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"693f58bc90bff1078c3caada659de590df3589c1c443ec939a55392ae5255e3e","abstract_canon_sha256":"78bacd3f798d031c185e0249ce9083c64ab1effa533c4e6501ac818271f64c02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:28.477157Z","signature_b64":"Ciw4kWXCJtL2mvX7JBB7PLnXJWo0dsldbkl5JYw5PP1zMeB6SHHMk+3Mq8N8vmLhxVNtV+rAy+myb0GMoRddAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936dd12c25f264aefbbd8fc0255eaee257b69cac40f4aae40a73aaa82b0b18e8","last_reissued_at":"2026-07-05T02:58:28.476749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:28.476749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Contextual Anomaly Detection for Time Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris U. Carmona, Fran\\c{c}ois-Xavier Aubet, Jan Gasthaus, Valentin Flunkert","submitted_at":"2021-07-16T04:33:53Z","abstract_excerpt":"We introduce Neural Contextual Anomaly Detection (NCAD), a framework for anomaly detection on time series that scales seamlessly from the unsupervised to supervised setting, and is applicable to both univariate and multivariate time series. This is achieved by effectively combining recent developments in representation learning for multivariate time series, with techniques for deep anomaly detection originally developed for computer vision that we tailor to the time series setting. Our window-based approach facilitates learning the boundary between normal and anomalous classes by injecting gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07702","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/2107.07702/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":"2107.07702","created_at":"2026-07-05T02:58:28.476806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07702v1","created_at":"2026-07-05T02:58:28.476806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07702","created_at":"2026-07-05T02:58:28.476806+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNW5CLBF6JSK","created_at":"2026-07-05T02:58:28.476806+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNW5CLBF6JSK5655","created_at":"2026-07-05T02:58:28.476806+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNW5CLBF","created_at":"2026-07-05T02:58:28.476806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2403.07815","citing_title":"Chronos: Learning the Language of Time Series","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09685","citing_title":"Learning Unified Representations of Normalcy for Time Series Anomaly Detection","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J","json":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J.json","graph_json":"https://pith.science/api/pith-number/SNW5CLBF6JSK5655R7ACKXVO4J/graph.json","events_json":"https://pith.science/api/pith-number/SNW5CLBF6JSK5655R7ACKXVO4J/events.json","paper":"https://pith.science/paper/SNW5CLBF"},"agent_actions":{"view_html":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J","download_json":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J.json","view_paper":"https://pith.science/paper/SNW5CLBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07702&json=true","fetch_graph":"https://pith.science/api/pith-number/SNW5CLBF6JSK5655R7ACKXVO4J/graph.json","fetch_events":"https://pith.science/api/pith-number/SNW5CLBF6JSK5655R7ACKXVO4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J/action/storage_attestation","attest_author":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J/action/author_attestation","sign_citation":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J/action/citation_signature","submit_replication":"https://pith.science/pith/SNW5CLBF6JSK5655R7ACKXVO4J/action/replication_record"}},"created_at":"2026-07-05T02:58:28.476806+00:00","updated_at":"2026-07-05T02:58:28.476806+00:00"}