{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OU5LQET3URVHN6XGR4A43GK47N","short_pith_number":"pith:OU5LQET3","schema_version":"1.0","canonical_sha256":"753ab8127ba46a76fae68f01cd995cfb4e1851542f4238d8ddd7bcd26e8851ba","source":{"kind":"arxiv","id":"2106.14112","version":1},"attestation_state":"computed","paper":{"title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chee Keong Kwoh, Cuntai Guan, Emadeldeen Eldele, Min Wu, Mohamed Ragab, Xiaoli Li, Zhenghua Chen","submitted_at":"2021-06-26T23:56:31Z","abstract_excerpt":"Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Last, to further "},"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":"2106.14112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-26T23:56:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"30f554beb7b39f08448330fae69d8eb4cf1224d60b96b245c02130c0640a9584","abstract_canon_sha256":"1d639f2ead55fedb4a520c2a88a3cb5ac0491d21ac41bf6eaf70936feea457a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:47.327655Z","signature_b64":"opbWzaYAVikGhD+fL1pu1Q0iRiD0qvUHitdAAWa+TzUyCFLT1AIqtfbCBtFxtevVME1bOdD/j4b8mKpU4eQIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753ab8127ba46a76fae68f01cd995cfb4e1851542f4238d8ddd7bcd26e8851ba","last_reissued_at":"2026-07-05T02:52:47.327159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:47.327159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chee Keong Kwoh, Cuntai Guan, Emadeldeen Eldele, Min Wu, Mohamed Ragab, Xiaoli Li, Zhenghua Chen","submitted_at":"2021-06-26T23:56:31Z","abstract_excerpt":"Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Last, to further "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14112","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/2106.14112/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":"2106.14112","created_at":"2026-07-05T02:52:47.327258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14112v1","created_at":"2026-07-05T02:52:47.327258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14112","created_at":"2026-07-05T02:52:47.327258+00:00"},{"alias_kind":"pith_short_12","alias_value":"OU5LQET3URVH","created_at":"2026-07-05T02:52:47.327258+00:00"},{"alias_kind":"pith_short_16","alias_value":"OU5LQET3URVHN6XG","created_at":"2026-07-05T02:52:47.327258+00:00"},{"alias_kind":"pith_short_8","alias_value":"OU5LQET3","created_at":"2026-07-05T02:52:47.327258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00958","citing_title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00956","citing_title":"Aionoscope: Debugging Latent-State Accessibility in Time-Series Representations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31249","citing_title":"LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space","ref_index":3,"is_internal_anchor":false},{"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22055","citing_title":"Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22379","citing_title":"Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00130","citing_title":"Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N","json":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N.json","graph_json":"https://pith.science/api/pith-number/OU5LQET3URVHN6XGR4A43GK47N/graph.json","events_json":"https://pith.science/api/pith-number/OU5LQET3URVHN6XGR4A43GK47N/events.json","paper":"https://pith.science/paper/OU5LQET3"},"agent_actions":{"view_html":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N","download_json":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N.json","view_paper":"https://pith.science/paper/OU5LQET3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14112&json=true","fetch_graph":"https://pith.science/api/pith-number/OU5LQET3URVHN6XGR4A43GK47N/graph.json","fetch_events":"https://pith.science/api/pith-number/OU5LQET3URVHN6XGR4A43GK47N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N/action/storage_attestation","attest_author":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N/action/author_attestation","sign_citation":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N/action/citation_signature","submit_replication":"https://pith.science/pith/OU5LQET3URVHN6XGR4A43GK47N/action/replication_record"}},"created_at":"2026-07-05T02:52:47.327258+00:00","updated_at":"2026-07-05T02:52:47.327258+00:00"}