{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AN4ZKG5LA5SAOV4FFNKN5HYM6U","short_pith_number":"pith:AN4ZKG5L","schema_version":"1.0","canonical_sha256":"0379951bab07640757852b54de9f0cf53464abaadf25c004f3c72d7bd529d202","source":{"kind":"arxiv","id":"2411.07506","version":3},"attestation_state":"computed","paper":{"title":"FlowTS: Time Series Generation via Rectified Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huatian Zhang, Jiheng Zhang, Lirong Wu, Sheng Wang, Stan Z. Li, Tianlong Chen, Xiao Wang, Yang Hu, Zezhen Ding, Ziyun Li","submitted_at":"2024-11-12T03:03:23Z","abstract_excerpt":"Diffusion-based models have significant achievements in time series generation but suffer from inefficient computation: solving high-dimensional ODEs/SDEs via iterative numerical solvers demands hundreds to thousands of drift function evaluations per sample, incurring prohibitive costs. To resolve this, we propose FlowTS, an ODE-based model that leverages rectified flow with straight-line transport in probability space. By learning geodesic paths between distributions, FlowTS achieves computational efficiency through exact linear trajectory simulation, accelerating training and generation whil"},"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":"2411.07506","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T03:03:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9359e6a6c940983d5ffde407a8ea55cb94cd56affe816f97516b49ad53735705","abstract_canon_sha256":"18e4d3523124e5f32fc72e8f52272a300709f51224904d6e463ed8317bea3b83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:28.584610Z","signature_b64":"XgCJm0chdvgODoPKMsUnFquAZam61vIR/xCFVPt7zUnXZ7omUupdVn3wmeDMKUfLIATtlSrBOcHe0JX7hS9vCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0379951bab07640757852b54de9f0cf53464abaadf25c004f3c72d7bd529d202","last_reissued_at":"2026-07-05T10:11:28.584125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:28.584125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowTS: Time Series Generation via Rectified Flow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huatian Zhang, Jiheng Zhang, Lirong Wu, Sheng Wang, Stan Z. Li, Tianlong Chen, Xiao Wang, Yang Hu, Zezhen Ding, Ziyun Li","submitted_at":"2024-11-12T03:03:23Z","abstract_excerpt":"Diffusion-based models have significant achievements in time series generation but suffer from inefficient computation: solving high-dimensional ODEs/SDEs via iterative numerical solvers demands hundreds to thousands of drift function evaluations per sample, incurring prohibitive costs. To resolve this, we propose FlowTS, an ODE-based model that leverages rectified flow with straight-line transport in probability space. By learning geodesic paths between distributions, FlowTS achieves computational efficiency through exact linear trajectory simulation, accelerating training and generation whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07506","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/2411.07506/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":"2411.07506","created_at":"2026-07-05T10:11:28.584183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07506v3","created_at":"2026-07-05T10:11:28.584183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07506","created_at":"2026-07-05T10:11:28.584183+00:00"},{"alias_kind":"pith_short_12","alias_value":"AN4ZKG5LA5SA","created_at":"2026-07-05T10:11:28.584183+00:00"},{"alias_kind":"pith_short_16","alias_value":"AN4ZKG5LA5SAOV4F","created_at":"2026-07-05T10:11:28.584183+00:00"},{"alias_kind":"pith_short_8","alias_value":"AN4ZKG5L","created_at":"2026-07-05T10:11:28.584183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03455","citing_title":"WavTTS: Towards High-Quality Zero-Shot TTS via Direct Raw Waveform Modeling","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07605","citing_title":"SRT: Super-Resolution for Time Series via Disentangled Rectified Flow","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11547","citing_title":"Sharpen Your Flow: Sharpness-Aware Sampling for Flow Matching","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U","json":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U.json","graph_json":"https://pith.science/api/pith-number/AN4ZKG5LA5SAOV4FFNKN5HYM6U/graph.json","events_json":"https://pith.science/api/pith-number/AN4ZKG5LA5SAOV4FFNKN5HYM6U/events.json","paper":"https://pith.science/paper/AN4ZKG5L"},"agent_actions":{"view_html":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U","download_json":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U.json","view_paper":"https://pith.science/paper/AN4ZKG5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07506&json=true","fetch_graph":"https://pith.science/api/pith-number/AN4ZKG5LA5SAOV4FFNKN5HYM6U/graph.json","fetch_events":"https://pith.science/api/pith-number/AN4ZKG5LA5SAOV4FFNKN5HYM6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U/action/storage_attestation","attest_author":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U/action/author_attestation","sign_citation":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U/action/citation_signature","submit_replication":"https://pith.science/pith/AN4ZKG5LA5SAOV4FFNKN5HYM6U/action/replication_record"}},"created_at":"2026-07-05T10:11:28.584183+00:00","updated_at":"2026-07-05T10:11:28.584183+00:00"}