{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BP5HCYWU77AYGNFRHSFJN3HYFF","short_pith_number":"pith:BP5HCYWU","schema_version":"1.0","canonical_sha256":"0bfa7162d4ffc18334b13c8a96ecf82961674897fdb7ce2eae05371788d1e0c4","source":{"kind":"arxiv","id":"2306.10125","version":4},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP","stat.AP"],"primary_cat":"cs.LG","authors_text":"Chaoli Zhang, Dongjin Song, Guansong Pang, James Zhang, Kexin Zhang, Ming Jin, Qingsong Wen, Rongyao Cai, Shirui Pan, Yong Liu, Yuxuan Liang","submitted_at":"2023-06-16T18:23:10Z","abstract_excerpt":"Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we firs"},"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":"2306.10125","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-16T18:23:10Z","cross_cats_sorted":["cs.AI","eess.SP","stat.AP"],"title_canon_sha256":"1097de206e0c5fa3c85d6d42c48e806a7438a4d228df605607f049c5a6df3c4d","abstract_canon_sha256":"a07cb052f3816eaa6a72f194139ab7722ec7d007c1010eb44ad78de32f193fe9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:37.655833Z","signature_b64":"9MWczGH1FyluYkZQtiC8JavzK7GTue3aafdJvFTb9nfknh1Xenre001dunBp3sz/cZyx3CXH1GaFQIPQdfluAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bfa7162d4ffc18334b13c8a96ecf82961674897fdb7ce2eae05371788d1e0c4","last_reissued_at":"2026-07-05T08:05:37.655382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:37.655382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.SP","stat.AP"],"primary_cat":"cs.LG","authors_text":"Chaoli Zhang, Dongjin Song, Guansong Pang, James Zhang, Kexin Zhang, Ming Jin, Qingsong Wen, Rongyao Cai, Shirui Pan, Yong Liu, Yuxuan Liang","submitted_at":"2023-06-16T18:23:10Z","abstract_excerpt":"Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10125","kind":"arxiv","version":4},"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/2306.10125/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":"2306.10125","created_at":"2026-07-05T08:05:37.655440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10125v4","created_at":"2026-07-05T08:05:37.655440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10125","created_at":"2026-07-05T08:05:37.655440+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP5HCYWU77AY","created_at":"2026-07-05T08:05:37.655440+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP5HCYWU77AYGNFR","created_at":"2026-07-05T08:05:37.655440+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP5HCYWU","created_at":"2026-07-05T08:05:37.655440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.05963","citing_title":"Next-Latent Prediction Transformers Learn Compact World Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03717","citing_title":"Universal Time-Series Representation Learning: A Survey","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01728","citing_title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF","json":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF.json","graph_json":"https://pith.science/api/pith-number/BP5HCYWU77AYGNFRHSFJN3HYFF/graph.json","events_json":"https://pith.science/api/pith-number/BP5HCYWU77AYGNFRHSFJN3HYFF/events.json","paper":"https://pith.science/paper/BP5HCYWU"},"agent_actions":{"view_html":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF","download_json":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF.json","view_paper":"https://pith.science/paper/BP5HCYWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10125&json=true","fetch_graph":"https://pith.science/api/pith-number/BP5HCYWU77AYGNFRHSFJN3HYFF/graph.json","fetch_events":"https://pith.science/api/pith-number/BP5HCYWU77AYGNFRHSFJN3HYFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF/action/storage_attestation","attest_author":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF/action/author_attestation","sign_citation":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF/action/citation_signature","submit_replication":"https://pith.science/pith/BP5HCYWU77AYGNFRHSFJN3HYFF/action/replication_record"}},"created_at":"2026-07-05T08:05:37.655440+00:00","updated_at":"2026-07-05T08:05:37.655440+00:00"}