{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4HKIHTH24LPSJJA2Q2ITUZCA4A","short_pith_number":"pith:4HKIHTH2","schema_version":"1.0","canonical_sha256":"e1d483ccfae2df24a41a86913a6440e01bee50fd2e5b56f5b2494956acf6bf3c","source":{"kind":"arxiv","id":"2401.09793","version":6},"attestation_state":"computed","paper":{"title":"PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaixiang Yang, Weizheng Wang, Yiyuan Yang, Zhijie Zhong, Zhiwen Yu","submitted_at":"2024-01-18T08:26:33Z","abstract_excerpt":"Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches, which limit the models' representational capacities. Moreover, existing deep learning-based methods are not sufficiently lightweight. Addressing these issues, we present PatchAD, our novel, highly efficient multiscale patch-based MLP-Mixer architecture that utilizes contrastive learning for representation extraction and anomaly detection. With its four dist"},"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":"2401.09793","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T08:26:33Z","cross_cats_sorted":[],"title_canon_sha256":"8fe5c4adddf6963ea83ed3a91c3eba18c9a9dc782d87dc8bd6e2c345922c09c8","abstract_canon_sha256":"75a1b3331700ac76addd2956b66a7b41c778bcab2086655fd7ad11a560c1d235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:10.817944Z","signature_b64":"rSKBxTLQrfoKwN8Of2jWqXXk2BTX+Gt9BrK1psbxTMSdW9JDXnQhz1gIcsQ6adyGpTjC6uVbKDI1F/wfF9TaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d483ccfae2df24a41a86913a6440e01bee50fd2e5b56f5b2494956acf6bf3c","last_reissued_at":"2026-07-05T11:47:10.817193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:10.817193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PatchAD: A Lightweight Patch-based MLP-Mixer for Time Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaixiang Yang, Weizheng Wang, Yiyuan Yang, Zhijie Zhong, Zhiwen Yu","submitted_at":"2024-01-18T08:26:33Z","abstract_excerpt":"Time series anomaly detection is a pivotal task in data analysis, yet it poses the challenge of discerning normal and abnormal patterns in label-deficient scenarios. While prior studies have largely employed reconstruction-based approaches, which limit the models' representational capacities. Moreover, existing deep learning-based methods are not sufficiently lightweight. Addressing these issues, we present PatchAD, our novel, highly efficient multiscale patch-based MLP-Mixer architecture that utilizes contrastive learning for representation extraction and anomaly detection. With its four dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09793","kind":"arxiv","version":6},"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/2401.09793/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":"2401.09793","created_at":"2026-07-05T11:47:10.817285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09793v6","created_at":"2026-07-05T11:47:10.817285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09793","created_at":"2026-07-05T11:47:10.817285+00:00"},{"alias_kind":"pith_short_12","alias_value":"4HKIHTH24LPS","created_at":"2026-07-05T11:47:10.817285+00:00"},{"alias_kind":"pith_short_16","alias_value":"4HKIHTH24LPSJJA2","created_at":"2026-07-05T11:47:10.817285+00:00"},{"alias_kind":"pith_short_8","alias_value":"4HKIHTH2","created_at":"2026-07-05T11:47:10.817285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.15066","citing_title":"Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A","json":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A.json","graph_json":"https://pith.science/api/pith-number/4HKIHTH24LPSJJA2Q2ITUZCA4A/graph.json","events_json":"https://pith.science/api/pith-number/4HKIHTH24LPSJJA2Q2ITUZCA4A/events.json","paper":"https://pith.science/paper/4HKIHTH2"},"agent_actions":{"view_html":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A","download_json":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A.json","view_paper":"https://pith.science/paper/4HKIHTH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09793&json=true","fetch_graph":"https://pith.science/api/pith-number/4HKIHTH24LPSJJA2Q2ITUZCA4A/graph.json","fetch_events":"https://pith.science/api/pith-number/4HKIHTH24LPSJJA2Q2ITUZCA4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A/action/storage_attestation","attest_author":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A/action/author_attestation","sign_citation":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A/action/citation_signature","submit_replication":"https://pith.science/pith/4HKIHTH24LPSJJA2Q2ITUZCA4A/action/replication_record"}},"created_at":"2026-07-05T11:47:10.817285+00:00","updated_at":"2026-07-05T11:47:10.817285+00:00"}