{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OZKFDEIP66Q74ETLSIQKD3ZD7U","short_pith_number":"pith:OZKFDEIP","schema_version":"1.0","canonical_sha256":"765451910ff7a1fe126b9220a1ef23fd340883e3ea471f78dc42845a0e326fc9","source":{"kind":"arxiv","id":"2505.02417","version":2},"attestation_state":"computed","paper":{"title":"T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haomin Wen, Hongyan Li, Jiawei Li, Meikang Qiu, Ming Jin, Shirui Pan, Yiji Zhao, Yunfeng Ge, Zhao Li","submitted_at":"2025-05-05T07:22:54Z","abstract_excerpt":"Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable success in Text-to-X (e.g., vision and audio data) generation, their use in time series generation remains in its nascent stages. Existing approaches face two critical limitations: (1) the lack of systematic exploration of general-proposed time series captions, which are often domain-specific and struggle with generalization; and (2) the inability to generate"},"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":"2505.02417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T07:22:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67092aefae003e8a2721e9557569f26daf83e02f9c30aa06a64d29beb7150b19","abstract_canon_sha256":"9e5c2269ffbda6ad73b44ac82350b0208f536fddb66fe09390766fd9dbc2ea02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:07.673696Z","signature_b64":"epGBXFZo/pJmKkQi7x0ZEH2fHIetyux/nGVc53Lx4dKLl2KdnKhlPgIQTCx6bWDj7P5aNEOPegPd5kOD6FLDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"765451910ff7a1fe126b9220a1ef23fd340883e3ea471f78dc42845a0e326fc9","last_reissued_at":"2026-07-05T11:00:07.673199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:07.673199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haomin Wen, Hongyan Li, Jiawei Li, Meikang Qiu, Ming Jin, Shirui Pan, Yiji Zhao, Yunfeng Ge, Zhao Li","submitted_at":"2025-05-05T07:22:54Z","abstract_excerpt":"Text-to-Time Series generation holds significant potential to address challenges such as data sparsity, imbalance, and limited availability of multimodal time series datasets across domains. While diffusion models have achieved remarkable success in Text-to-X (e.g., vision and audio data) generation, their use in time series generation remains in its nascent stages. Existing approaches face two critical limitations: (1) the lack of systematic exploration of general-proposed time series captions, which are often domain-specific and struggle with generalization; and (2) the inability to generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02417","kind":"arxiv","version":2},"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/2505.02417/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":"2505.02417","created_at":"2026-07-05T11:00:07.673258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02417v2","created_at":"2026-07-05T11:00:07.673258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02417","created_at":"2026-07-05T11:00:07.673258+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZKFDEIP66Q7","created_at":"2026-07-05T11:00:07.673258+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZKFDEIP66Q74ETL","created_at":"2026-07-05T11:00:07.673258+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZKFDEIP","created_at":"2026-07-05T11:00:07.673258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10466","citing_title":"UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28867","citing_title":"PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12451","citing_title":"Overcoming the Modality Gap in Context-Aided Forecasting","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26762","citing_title":"Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U","json":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U.json","graph_json":"https://pith.science/api/pith-number/OZKFDEIP66Q74ETLSIQKD3ZD7U/graph.json","events_json":"https://pith.science/api/pith-number/OZKFDEIP66Q74ETLSIQKD3ZD7U/events.json","paper":"https://pith.science/paper/OZKFDEIP"},"agent_actions":{"view_html":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U","download_json":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U.json","view_paper":"https://pith.science/paper/OZKFDEIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02417&json=true","fetch_graph":"https://pith.science/api/pith-number/OZKFDEIP66Q74ETLSIQKD3ZD7U/graph.json","fetch_events":"https://pith.science/api/pith-number/OZKFDEIP66Q74ETLSIQKD3ZD7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U/action/storage_attestation","attest_author":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U/action/author_attestation","sign_citation":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U/action/citation_signature","submit_replication":"https://pith.science/pith/OZKFDEIP66Q74ETLSIQKD3ZD7U/action/replication_record"}},"created_at":"2026-07-05T11:00:07.673258+00:00","updated_at":"2026-07-05T11:00:07.673258+00:00"}