{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GHJDR2SWE3NXFEYJMIYFQPMHNL","short_pith_number":"pith:GHJDR2SW","schema_version":"1.0","canonical_sha256":"31d238ea5626db7293096230583d876ae3ea39df3866cf74bc764e70d33aa0dd","source":{"kind":"arxiv","id":"2503.14076","version":1},"attestation_state":"computed","paper":{"title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Jiangxuan Long, Zhao Song","submitted_at":"2025-03-18T09:53:48Z","abstract_excerpt":"Recent studies suggest utilizing generative models instead of traditional auto-regressive algorithms for time series forecasting (TSF) tasks. These non-auto-regressive approaches involving different generative methods, including GAN, Diffusion, and Flow Matching for time series, have empirically demonstrated high-quality generation capability and accuracy. However, we still lack an appropriate understanding of how it processes approximation and generalization. This paper presents the first theoretical framework from the perspective of flow-based generative models to relieve the knowledge of li"},"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":"2503.14076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T09:53:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea1fde1791edc059cf68967b27ba17f27c69b926c3e358fa0848e490cce02756","abstract_canon_sha256":"700af8f86a7e6ec0b38a9873e6033e5695fd2287873b893500c4b7a6fb36f08f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:54.638730Z","signature_b64":"TUhKMmxJ4/sdLFPy8uXLFjF9VEQxe53dEdaKl+1F1RnhtrfHtHAx9AvvrMsjsn1AAi1BrpFDV2bF+DdX2It+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d238ea5626db7293096230583d876ae3ea39df3866cf74bc764e70d33aa0dd","last_reissued_at":"2026-07-05T10:33:54.638210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:54.638210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Jiangxuan Long, Zhao Song","submitted_at":"2025-03-18T09:53:48Z","abstract_excerpt":"Recent studies suggest utilizing generative models instead of traditional auto-regressive algorithms for time series forecasting (TSF) tasks. These non-auto-regressive approaches involving different generative methods, including GAN, Diffusion, and Flow Matching for time series, have empirically demonstrated high-quality generation capability and accuracy. However, we still lack an appropriate understanding of how it processes approximation and generalization. This paper presents the first theoretical framework from the perspective of flow-based generative models to relieve the knowledge of li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14076","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/2503.14076/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":"2503.14076","created_at":"2026-07-05T10:33:54.638282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14076v1","created_at":"2026-07-05T10:33:54.638282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14076","created_at":"2026-07-05T10:33:54.638282+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHJDR2SWE3NX","created_at":"2026-07-05T10:33:54.638282+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHJDR2SWE3NXFEYJ","created_at":"2026-07-05T10:33:54.638282+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHJDR2SW","created_at":"2026-07-05T10:33:54.638282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18107","citing_title":"T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL","json":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL.json","graph_json":"https://pith.science/api/pith-number/GHJDR2SWE3NXFEYJMIYFQPMHNL/graph.json","events_json":"https://pith.science/api/pith-number/GHJDR2SWE3NXFEYJMIYFQPMHNL/events.json","paper":"https://pith.science/paper/GHJDR2SW"},"agent_actions":{"view_html":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL","download_json":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL.json","view_paper":"https://pith.science/paper/GHJDR2SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14076&json=true","fetch_graph":"https://pith.science/api/pith-number/GHJDR2SWE3NXFEYJMIYFQPMHNL/graph.json","fetch_events":"https://pith.science/api/pith-number/GHJDR2SWE3NXFEYJMIYFQPMHNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL/action/storage_attestation","attest_author":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL/action/author_attestation","sign_citation":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL/action/citation_signature","submit_replication":"https://pith.science/pith/GHJDR2SWE3NXFEYJMIYFQPMHNL/action/replication_record"}},"created_at":"2026-07-05T10:33:54.638282+00:00","updated_at":"2026-07-05T10:33:54.638282+00:00"}