{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EYUHWH5A7MXS7LNOL5FXUKS3RK","short_pith_number":"pith:EYUHWH5A","schema_version":"1.0","canonical_sha256":"26287b1fa0fb2f2fadae5f4b7a2a5b8a99f146f6cf6a64cfb417e4241212fec3","source":{"kind":"arxiv","id":"2312.04142","version":3},"attestation_state":"computed","paper":{"title":"TimeDRL: Disentangled Representation Learning for Multivariate Time-Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chiao-Tung Chan, Ching Chang, Tien-Fu Chen, Wei-Yao Wang, Wen-Chih Peng","submitted_at":"2023-12-07T08:56:44Z","abstract_excerpt":"Multivariate time-series data in numerous real-world applications (e.g., healthcare and industry) are informative but challenging due to the lack of labels and high dimensionality. Recent studies in self-supervised learning have shown their potential in learning rich representations without relying on labels, yet they fall short in learning disentangled embeddings and addressing issues of inductive bias (e.g., transformation-invariance). To tackle these challenges, we propose TimeDRL, a generic multivariate time-series representation learning framework with disentangled dual-level embeddings. "},"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":"2312.04142","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T08:56:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5cd5ce5cabd90d9a2fcdcc1654b77b3abda6e48433dc6cd114faaef31b30a9f4","abstract_canon_sha256":"619a8e923e51e88b133a99d6d15d3905e9109ecc25a1d03a13a0ab1521d4a4d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:49.790733Z","signature_b64":"nl44Hw2GlbHhMrqMUiHh506sjSvqqyxvhO2uhPzisfV3hOp3h7DFR0fKUUx7wqUdzcJv4I7qMwHfOHH44r+mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26287b1fa0fb2f2fadae5f4b7a2a5b8a99f146f6cf6a64cfb417e4241212fec3","last_reissued_at":"2026-07-05T08:44:49.790304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:49.790304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeDRL: Disentangled Representation Learning for Multivariate Time-Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chiao-Tung Chan, Ching Chang, Tien-Fu Chen, Wei-Yao Wang, Wen-Chih Peng","submitted_at":"2023-12-07T08:56:44Z","abstract_excerpt":"Multivariate time-series data in numerous real-world applications (e.g., healthcare and industry) are informative but challenging due to the lack of labels and high dimensionality. Recent studies in self-supervised learning have shown their potential in learning rich representations without relying on labels, yet they fall short in learning disentangled embeddings and addressing issues of inductive bias (e.g., transformation-invariance). To tackle these challenges, we propose TimeDRL, a generic multivariate time-series representation learning framework with disentangled dual-level embeddings. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04142","kind":"arxiv","version":3},"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/2312.04142/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":"2312.04142","created_at":"2026-07-05T08:44:49.790369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04142v3","created_at":"2026-07-05T08:44:49.790369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04142","created_at":"2026-07-05T08:44:49.790369+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYUHWH5A7MXS","created_at":"2026-07-05T08:44:49.790369+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYUHWH5A7MXS7LNO","created_at":"2026-07-05T08:44:49.790369+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYUHWH5A","created_at":"2026-07-05T08:44:49.790369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14828","citing_title":"eMargin: Revisiting Contrastive Learning with Margin-Based Separation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK","json":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK.json","graph_json":"https://pith.science/api/pith-number/EYUHWH5A7MXS7LNOL5FXUKS3RK/graph.json","events_json":"https://pith.science/api/pith-number/EYUHWH5A7MXS7LNOL5FXUKS3RK/events.json","paper":"https://pith.science/paper/EYUHWH5A"},"agent_actions":{"view_html":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK","download_json":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK.json","view_paper":"https://pith.science/paper/EYUHWH5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04142&json=true","fetch_graph":"https://pith.science/api/pith-number/EYUHWH5A7MXS7LNOL5FXUKS3RK/graph.json","fetch_events":"https://pith.science/api/pith-number/EYUHWH5A7MXS7LNOL5FXUKS3RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK/action/storage_attestation","attest_author":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK/action/author_attestation","sign_citation":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK/action/citation_signature","submit_replication":"https://pith.science/pith/EYUHWH5A7MXS7LNOL5FXUKS3RK/action/replication_record"}},"created_at":"2026-07-05T08:44:49.790369+00:00","updated_at":"2026-07-05T08:44:49.790369+00:00"}