{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L4W37KAGYCVLNM74OZIMPI7MB4","short_pith_number":"pith:L4W37KAG","schema_version":"1.0","canonical_sha256":"5f2dbfa806c0aab6b3fc7650c7a3ec0f25c51e0ceb60e7d4505ca5af33583892","source":{"kind":"arxiv","id":"2504.04283","version":1},"attestation_state":"computed","paper":{"title":"CATS: Mitigating Correlation Shift for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanghang Tong, Tianxin Wei, Xiao Lin, Yuzhong Chen, Zhichen Zeng, Zhining Liu","submitted_at":"2025-04-05T21:08:47Z","abstract_excerpt":"Unsupervised Domain Adaptation (UDA) leverages labeled source data to train models for unlabeled target data. Given the prevalence of multivariate time series (MTS) data across various domains, the UDA task for MTS classification has emerged as a critical challenge. However, for MTS data, correlations between variables often vary across domains, whereas most existing UDA works for MTS classification have overlooked this essential characteristic. To bridge this gap, we introduce a novel domain shift, {\\em correlation shift}, measuring domain differences in multivariate correlation. To mitigate "},"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":"2504.04283","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-05T21:08:47Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f26f46b62760b4d8798b346db836d7a845d798227bd7a4a2427546d02f27e3dc","abstract_canon_sha256":"c0db50c5e3a2a6319b15310e6718ca5ce17cbf67c4af727c4b5dea793d3d2ab3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:21.848491Z","signature_b64":"vAA9Odz+fGP6TBhIAFHoeTBwK7s2315qRZYlQGuqJPngMPYlCXRHosmpmM9PR7NxaiqOfPqc8pyROvOmKHvUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f2dbfa806c0aab6b3fc7650c7a3ec0f25c51e0ceb60e7d4505ca5af33583892","last_reissued_at":"2026-07-05T10:45:21.847913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:21.847913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CATS: Mitigating Correlation Shift for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanghang Tong, Tianxin Wei, Xiao Lin, Yuzhong Chen, Zhichen Zeng, Zhining Liu","submitted_at":"2025-04-05T21:08:47Z","abstract_excerpt":"Unsupervised Domain Adaptation (UDA) leverages labeled source data to train models for unlabeled target data. Given the prevalence of multivariate time series (MTS) data across various domains, the UDA task for MTS classification has emerged as a critical challenge. However, for MTS data, correlations between variables often vary across domains, whereas most existing UDA works for MTS classification have overlooked this essential characteristic. To bridge this gap, we introduce a novel domain shift, {\\em correlation shift}, measuring domain differences in multivariate correlation. To mitigate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04283","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/2504.04283/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":"2504.04283","created_at":"2026-07-05T10:45:21.847981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04283v1","created_at":"2026-07-05T10:45:21.847981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04283","created_at":"2026-07-05T10:45:21.847981+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4W37KAGYCVL","created_at":"2026-07-05T10:45:21.847981+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4W37KAGYCVLNM74","created_at":"2026-07-05T10:45:21.847981+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4W37KAG","created_at":"2026-07-05T10:45:21.847981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22043","citing_title":"CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20858","citing_title":"Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4","json":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4.json","graph_json":"https://pith.science/api/pith-number/L4W37KAGYCVLNM74OZIMPI7MB4/graph.json","events_json":"https://pith.science/api/pith-number/L4W37KAGYCVLNM74OZIMPI7MB4/events.json","paper":"https://pith.science/paper/L4W37KAG"},"agent_actions":{"view_html":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4","download_json":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4.json","view_paper":"https://pith.science/paper/L4W37KAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04283&json=true","fetch_graph":"https://pith.science/api/pith-number/L4W37KAGYCVLNM74OZIMPI7MB4/graph.json","fetch_events":"https://pith.science/api/pith-number/L4W37KAGYCVLNM74OZIMPI7MB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4/action/storage_attestation","attest_author":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4/action/author_attestation","sign_citation":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4/action/citation_signature","submit_replication":"https://pith.science/pith/L4W37KAGYCVLNM74OZIMPI7MB4/action/replication_record"}},"created_at":"2026-07-05T10:45:21.847981+00:00","updated_at":"2026-07-05T10:45:21.847981+00:00"}