{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IBYLZWFJLXZBYRZG7TKCNRHHWL","short_pith_number":"pith:IBYLZWFJ","schema_version":"1.0","canonical_sha256":"4070bcd8a95df21c4726fcd426c4e7b2dd57ddd1aade5293bb2ed764de3cf851","source":{"kind":"arxiv","id":"2307.11494","version":3},"attestation_state":"computed","paper":{"title":"Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Fatir Ansari, Hao Wang, Jasper Zschiegner, Marcel Kollovieh, Michael Bohlke-Schneider, Yuyang Wang","submitted_at":"2023-07-21T10:56:36Z","abstract_excerpt":"Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks. In this work, we explore the potential of task-agnostic, unconditional diffusion models for several time series applications. We propose TSDiff, an unconditionally-trained diffusion model for time series. Our proposed self-guidance mechanism enables conditioning TSDiff for downstream tasks during inference, without requiring auxili"},"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":"2307.11494","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T10:56:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f8564eee498a3345615371e9b3c51ef727c47a5d73ffd2b46686e309bd9d5a00","abstract_canon_sha256":"5de381afecc374f7da49b4a315fc1b0c09daf79b7a297acf30a48885b2d18003"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:15.878018Z","signature_b64":"ztgIhN+3dfuMubsFY4XwjA7KZj/zOPnjADH5glkVRiC8vUZVRC1d89ywNB3mCFxC9kikv3zWhEwR3ciE3WRxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4070bcd8a95df21c4726fcd426c4e7b2dd57ddd1aade5293bb2ed764de3cf851","last_reissued_at":"2026-07-05T07:15:15.877511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:15.877511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdul Fatir Ansari, Hao Wang, Jasper Zschiegner, Marcel Kollovieh, Michael Bohlke-Schneider, Yuyang Wang","submitted_at":"2023-07-21T10:56:36Z","abstract_excerpt":"Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks. In this work, we explore the potential of task-agnostic, unconditional diffusion models for several time series applications. We propose TSDiff, an unconditionally-trained diffusion model for time series. Our proposed self-guidance mechanism enables conditioning TSDiff for downstream tasks during inference, without requiring auxili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11494","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/2307.11494/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":"2307.11494","created_at":"2026-07-05T07:15:15.877575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11494v3","created_at":"2026-07-05T07:15:15.877575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11494","created_at":"2026-07-05T07:15:15.877575+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBYLZWFJLXZB","created_at":"2026-07-05T07:15:15.877575+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBYLZWFJLXZBYRZG","created_at":"2026-07-05T07:15:15.877575+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBYLZWFJ","created_at":"2026-07-05T07:15:15.877575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08302","citing_title":"HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL","json":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL.json","graph_json":"https://pith.science/api/pith-number/IBYLZWFJLXZBYRZG7TKCNRHHWL/graph.json","events_json":"https://pith.science/api/pith-number/IBYLZWFJLXZBYRZG7TKCNRHHWL/events.json","paper":"https://pith.science/paper/IBYLZWFJ"},"agent_actions":{"view_html":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL","download_json":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL.json","view_paper":"https://pith.science/paper/IBYLZWFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11494&json=true","fetch_graph":"https://pith.science/api/pith-number/IBYLZWFJLXZBYRZG7TKCNRHHWL/graph.json","fetch_events":"https://pith.science/api/pith-number/IBYLZWFJLXZBYRZG7TKCNRHHWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL/action/storage_attestation","attest_author":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL/action/author_attestation","sign_citation":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL/action/citation_signature","submit_replication":"https://pith.science/pith/IBYLZWFJLXZBYRZG7TKCNRHHWL/action/replication_record"}},"created_at":"2026-07-05T07:15:15.877575+00:00","updated_at":"2026-07-05T07:15:15.877575+00:00"}