{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OBPRHKH4G5DNQPJQBO3LPY7NCN","short_pith_number":"pith:OBPRHKH4","schema_version":"1.0","canonical_sha256":"705f13a8fc3746d83d300bb6b7e3ed1348c23574e296f0f624ac6a59c92426eb","source":{"kind":"arxiv","id":"2509.02341","version":1},"attestation_state":"computed","paper":{"title":"RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chih-Yu Lai, Duane S. Boning, Yu-Chien Ning","submitted_at":"2025-09-02T14:06:29Z","abstract_excerpt":"Probabilistic Time Series Forecasting (PTSF) plays a critical role in domains requiring accurate and uncertainty-aware predictions for decision-making. However, existing methods offer suboptimal distribution modeling and suffer from a mismatch between training and evaluation metrics. Surprisingly, we found that augmenting a strong point estimator with a zero-mean Gaussian, whose standard deviation matches its training error, can yield state-of-the-art performance in PTSF. In this work, we propose RDIT, a plug-and-play framework that combines point estimation and residual-based conditional diff"},"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":"2509.02341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T14:06:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3149fe13454fa6f951c5cb9b8ba53242adf81ba17d5c9782a3673a9bf77312a4","abstract_canon_sha256":"a65efa2cd422ea7bc6775bdd35e1741ee6452a85bfbb1b0340971d8549d84c8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:36.624742Z","signature_b64":"L7HTPme4SP495XQDRQxCsWBe9ho11Y6gmor6Gb9V/fVAfA5DMvyEarXeue2SBbABC7OHxXMhBsKaRGdVQrQHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"705f13a8fc3746d83d300bb6b7e3ed1348c23574e296f0f624ac6a59c92426eb","last_reissued_at":"2026-07-05T12:03:36.624214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:36.624214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chih-Yu Lai, Duane S. Boning, Yu-Chien Ning","submitted_at":"2025-09-02T14:06:29Z","abstract_excerpt":"Probabilistic Time Series Forecasting (PTSF) plays a critical role in domains requiring accurate and uncertainty-aware predictions for decision-making. However, existing methods offer suboptimal distribution modeling and suffer from a mismatch between training and evaluation metrics. Surprisingly, we found that augmenting a strong point estimator with a zero-mean Gaussian, whose standard deviation matches its training error, can yield state-of-the-art performance in PTSF. In this work, we propose RDIT, a plug-and-play framework that combines point estimation and residual-based conditional diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02341","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/2509.02341/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":"2509.02341","created_at":"2026-07-05T12:03:36.624280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02341v1","created_at":"2026-07-05T12:03:36.624280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02341","created_at":"2026-07-05T12:03:36.624280+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBPRHKH4G5DN","created_at":"2026-07-05T12:03:36.624280+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBPRHKH4G5DNQPJQ","created_at":"2026-07-05T12:03:36.624280+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBPRHKH4","created_at":"2026-07-05T12:03:36.624280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30821","citing_title":"Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN","json":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN.json","graph_json":"https://pith.science/api/pith-number/OBPRHKH4G5DNQPJQBO3LPY7NCN/graph.json","events_json":"https://pith.science/api/pith-number/OBPRHKH4G5DNQPJQBO3LPY7NCN/events.json","paper":"https://pith.science/paper/OBPRHKH4"},"agent_actions":{"view_html":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN","download_json":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN.json","view_paper":"https://pith.science/paper/OBPRHKH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02341&json=true","fetch_graph":"https://pith.science/api/pith-number/OBPRHKH4G5DNQPJQBO3LPY7NCN/graph.json","fetch_events":"https://pith.science/api/pith-number/OBPRHKH4G5DNQPJQBO3LPY7NCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN/action/storage_attestation","attest_author":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN/action/author_attestation","sign_citation":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN/action/citation_signature","submit_replication":"https://pith.science/pith/OBPRHKH4G5DNQPJQBO3LPY7NCN/action/replication_record"}},"created_at":"2026-07-05T12:03:36.624280+00:00","updated_at":"2026-07-05T12:03:36.624280+00:00"}