{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MEG2UGJYHKVDOVN7QEJNKMN65Q","short_pith_number":"pith:MEG2UGJY","schema_version":"1.0","canonical_sha256":"610daa19383aaa3755bf8112d531beec0fd3c8f65255f0524702b608da5b7a8b","source":{"kind":"arxiv","id":"2311.03303","version":1},"attestation_state":"computed","paper":{"title":"TS-Diffusion: Generating Highly Complex Time Series with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yangming Li","submitted_at":"2023-11-06T17:52:08Z","abstract_excerpt":"While current generative models have achieved promising performances in time-series synthesis, they either make strong assumptions on the data format (e.g., regularities) or rely on pre-processing approaches (e.g., interpolations) to simplify the raw data. In this work, we consider a class of time series with three common bad properties, including sampling irregularities, missingness, and large feature-temporal dimensions, and introduce a general model, TS-Diffusion, to process such complex time series. Our model consists of three parts under the framework of point process. The first part is a"},"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":"2311.03303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T17:52:08Z","cross_cats_sorted":[],"title_canon_sha256":"1d2dc72435b8c7839dd6cf29ab0c0c12da1def7e2b0a72b834c0a34a05e115d9","abstract_canon_sha256":"22e4cd5e9e3aed4d8c557b0389db6243e8e0bbcc95df5b814544c618ecace25c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:39.512224Z","signature_b64":"HuByKpUfIj+Rip35luRxnmccSciHcpKouTD7jKNCKN4FRH8CKYYlWk8cYRdXnmktbUYIxegPQoTF4JmmAl3DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"610daa19383aaa3755bf8112d531beec0fd3c8f65255f0524702b608da5b7a8b","last_reissued_at":"2026-07-05T07:09:39.511736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:39.511736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TS-Diffusion: Generating Highly Complex Time Series with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yangming Li","submitted_at":"2023-11-06T17:52:08Z","abstract_excerpt":"While current generative models have achieved promising performances in time-series synthesis, they either make strong assumptions on the data format (e.g., regularities) or rely on pre-processing approaches (e.g., interpolations) to simplify the raw data. In this work, we consider a class of time series with three common bad properties, including sampling irregularities, missingness, and large feature-temporal dimensions, and introduce a general model, TS-Diffusion, to process such complex time series. Our model consists of three parts under the framework of point process. The first part is a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03303","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/2311.03303/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":"2311.03303","created_at":"2026-07-05T07:09:39.511801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03303v1","created_at":"2026-07-05T07:09:39.511801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03303","created_at":"2026-07-05T07:09:39.511801+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEG2UGJYHKVD","created_at":"2026-07-05T07:09:39.511801+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEG2UGJYHKVDOVN7","created_at":"2026-07-05T07:09:39.511801+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEG2UGJY","created_at":"2026-07-05T07:09:39.511801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13428","citing_title":"SynEHRgy: Synthesizing Mixed-Type Structured Electronic Health Records using Decoder-Only Transformers","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q","json":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q.json","graph_json":"https://pith.science/api/pith-number/MEG2UGJYHKVDOVN7QEJNKMN65Q/graph.json","events_json":"https://pith.science/api/pith-number/MEG2UGJYHKVDOVN7QEJNKMN65Q/events.json","paper":"https://pith.science/paper/MEG2UGJY"},"agent_actions":{"view_html":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q","download_json":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q.json","view_paper":"https://pith.science/paper/MEG2UGJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03303&json=true","fetch_graph":"https://pith.science/api/pith-number/MEG2UGJYHKVDOVN7QEJNKMN65Q/graph.json","fetch_events":"https://pith.science/api/pith-number/MEG2UGJYHKVDOVN7QEJNKMN65Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q/action/storage_attestation","attest_author":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q/action/author_attestation","sign_citation":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q/action/citation_signature","submit_replication":"https://pith.science/pith/MEG2UGJYHKVDOVN7QEJNKMN65Q/action/replication_record"}},"created_at":"2026-07-05T07:09:39.511801+00:00","updated_at":"2026-07-05T07:09:39.511801+00:00"}