{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQYZWCNITECQSIJGMUGJSVPBUB","short_pith_number":"pith:UQYZWCNI","schema_version":"1.0","canonical_sha256":"a4319b09a89905092126650c9955e1a07c5cd5c612dfcdd710b56901affe0eb7","source":{"kind":"arxiv","id":"2403.01742","version":3},"attestation_state":"computed","paper":{"title":"Diffusion-TS: Interpretable Diffusion for General Time Series Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xinyu Yuan, Yan Qiao","submitted_at":"2024-03-04T05:39:23Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information from the noisy m"},"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":"2403.01742","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T05:39:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b408bac35e62558750dcfba49e4aa60ead5fe33c545a427db623dd53d88fc8cc","abstract_canon_sha256":"7f05230a0d0d87d3991b51915c6c4fbadab41ead34859b98ff0034bae2faa2ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:03.993226Z","signature_b64":"3ZCM+tLWHadA1uvqME6UwySweKpCTAViY5W6/KECkIFnpSab178wqmrCMDzlzIv+8t1DW7/irr2xcjMwmSE2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4319b09a89905092126650c9955e1a07c5cd5c612dfcdd710b56901affe0eb7","last_reissued_at":"2026-07-05T09:23:03.992749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:03.992749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-TS: Interpretable Diffusion for General Time Series Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Xinyu Yuan, Yan Qiao","submitted_at":"2024-03-04T05:39:23Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) are becoming the leading paradigm for generative models. It has recently shown breakthroughs in audio synthesis, time series imputation and forecasting. In this paper, we propose Diffusion-TS, a novel diffusion-based framework that generates multivariate time series samples of high quality by using an encoder-decoder transformer with disentangled temporal representations, in which the decomposition technique guides Diffusion-TS to capture the semantic meaning of time series while transformers mine detailed sequential information from the noisy m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01742","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/2403.01742/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":"2403.01742","created_at":"2026-07-05T09:23:03.992808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01742v3","created_at":"2026-07-05T09:23:03.992808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01742","created_at":"2026-07-05T09:23:03.992808+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQYZWCNITECQ","created_at":"2026-07-05T09:23:03.992808+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQYZWCNITECQSIJG","created_at":"2026-07-05T09:23:03.992808+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQYZWCNI","created_at":"2026-07-05T09:23:03.992808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06504","citing_title":"RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27561","citing_title":"Quantum Generative Diffusion Model for Real-World Time Series","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28867","citing_title":"PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03998","citing_title":"TGSD: Topology-Guided State-Space Diffusion Framework for EEG Spatial Super-Resolution","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27113","citing_title":"High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07605","citing_title":"SRT: Super-Resolution for Time Series via Disentangled Rectified Flow","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00708","citing_title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23402","citing_title":"Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04278","citing_title":"Non-stationary Diffusion For Probabilistic Time Series Forecasting","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14202","citing_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15067","citing_title":"EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14422","citing_title":"What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05736","citing_title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05257","citing_title":"Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20288","citing_title":"Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework","ref_index":140,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB","json":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB.json","graph_json":"https://pith.science/api/pith-number/UQYZWCNITECQSIJGMUGJSVPBUB/graph.json","events_json":"https://pith.science/api/pith-number/UQYZWCNITECQSIJGMUGJSVPBUB/events.json","paper":"https://pith.science/paper/UQYZWCNI"},"agent_actions":{"view_html":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB","download_json":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB.json","view_paper":"https://pith.science/paper/UQYZWCNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01742&json=true","fetch_graph":"https://pith.science/api/pith-number/UQYZWCNITECQSIJGMUGJSVPBUB/graph.json","fetch_events":"https://pith.science/api/pith-number/UQYZWCNITECQSIJGMUGJSVPBUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB/action/storage_attestation","attest_author":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB/action/author_attestation","sign_citation":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB/action/citation_signature","submit_replication":"https://pith.science/pith/UQYZWCNITECQSIJGMUGJSVPBUB/action/replication_record"}},"created_at":"2026-07-05T09:23:03.992808+00:00","updated_at":"2026-07-05T09:23:03.992808+00:00"}