{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A62637546VBGORUXFBD5MX2B32","short_pith_number":"pith:A6263754","schema_version":"1.0","canonical_sha256":"07b5edffbcf5426746972847d65f41deaeefc7e312cde4667a2555a7969ac1bf","source":{"kind":"arxiv","id":"2605.14597","version":1},"attestation_state":"computed","paper":{"title":"VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A two-stage model fuses radar and satellite data to first capture broad precipitation motion then add fine details via diffusion.","cross_cats":["cs.CE","cs.MM"],"primary_cat":"cs.CV","authors_text":"Boyu Liu, Chunlei Shi, Dan Niu, Hao Li, Hongbin Wang, Yanlan Yang, Yongchao Feng, Yufeng Zhu, Zengliang Zang","submitted_at":"2026-05-14T09:05:30Z","abstract_excerpt":"Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of precipitation systems. Existing methods predominantly rely on single-source radar data to build either deterministic or probabilistic models for extrapolation. However, the single deterministic model suffers from blurring due to MSE convergence. The single probabilistic model, typically represented by diffusion models, can generate fine details but suffers from spurious artifacts that compromise accuracy and computational inefficiency. To addre"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:05:30Z","cross_cats_sorted":["cs.CE","cs.MM"],"title_canon_sha256":"ab04eaf81b84d8c50d075c683e3ac29468b8c43b75c40bb3ac199bdfa1dc0a68","abstract_canon_sha256":"6ffe7d3af9d72957ed6746869adcf4aa552fddfbd474d278f39aeb12422f2891"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.295097Z","signature_b64":"/ayRV5paaZFI7T4S0lDHneX3j9arI8goa9APFDB/Aq0TSOiNxyyRP3oL5g3PPQK/K03/3mGc4/t5OZaPzy9xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b5edffbcf5426746972847d65f41deaeefc7e312cde4667a2555a7969ac1bf","last_reissued_at":"2026-05-17T23:39:04.294462Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.294462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A two-stage model fuses radar and satellite data to first capture broad precipitation motion then add fine details via diffusion.","cross_cats":["cs.CE","cs.MM"],"primary_cat":"cs.CV","authors_text":"Boyu Liu, Chunlei Shi, Dan Niu, Hao Li, Hongbin Wang, Yanlan Yang, Yongchao Feng, Yufeng Zhu, Zengliang Zang","submitted_at":"2026-05-14T09:05:30Z","abstract_excerpt":"Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of precipitation systems. Existing methods predominantly rely on single-source radar data to build either deterministic or probabilistic models for extrapolation. However, the single deterministic model suffers from blurring due to MSE convergence. The single probabilistic model, typically represented by diffusion models, can generate fine details but suffers from spurious artifacts that compromise accuracy and computational inefficiency. To addre"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on Jiangsu SWAN datasets demonstrate the improvements of our method over state-of-the-art methods, particularly in short-term forecasts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the coarse-stage multi-source Vision Mamba prediction accurately captures global precipitation dynamics so the residual diffusion stage can reliably add fine details without introducing new artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A two-stage model fuses radar and satellite data to first capture broad precipitation motion then add fine details via diffusion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fc3824e143e47494a384fa14b380710ef1b993b14d634a4cea9f2af8a321a807"},"source":{"id":"2605.14597","kind":"arxiv","version":1},"verdict":{"id":"16cab33c-0e5f-4d10-8f2b-75e948cbd91c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:04:52.179228Z","strongest_claim":"Experiments on Jiangsu SWAN datasets demonstrate the improvements of our method over state-of-the-art methods, particularly in short-term forecasts.","one_line_summary":"VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the coarse-stage multi-source Vision Mamba prediction accurately captures global precipitation dynamics so the residual diffusion stage can reliably add fine details without introducing new artifacts.","pith_extraction_headline":"A two-stage model fuses radar and satellite data to first capture broad precipitation motion then add fine details via diffusion."},"references":{"count":76,"sample":[{"doi":"","year":null,"title":"Tilmann, G. and Adrian, E. R. Weather forecasting with ensemble methods. Science","work_id":"971ab286-981e-4b8a-a4be-b8df21e97068","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Machine learning tapped to improve climate forecasts","work_id":"6768068d-f9da-4109-aa3f-7933550695db","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Juanzhen, S. and Ming, X. and James, W. W. and Zawadzki, I. and Ballard, S. P. and Onvlee-Hooimeyer, J. and Pinto, J. Use of NWP for nowcasting convective precipitation: Recent progress and challenges","work_id":"d0e7b137-55a1-4837-a633-9b7ce9a6d20e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Tolstykh, M. A. and Frolov, A. V. Some current problems in numerical weather prediction. Izvestiya Atmospheric and Oceanic Physics","work_id":"897e5edc-bd34-4baf-9694-7c9aff0bcd25","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Wang-chun, W. and Wai-kin, W. Operational application of optical flow techniques to radar-based rainfall nowcasting. Atmosphere","work_id":"db935bef-f6ca-40e6-a107-1f14b6969cc4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":76,"snapshot_sha256":"c76fca0edebf67e10041d9e10a6725c829036366da078c7a571f6a5213b4bb28","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7e9af91a2e0184159b8a6655eaa8ebc90b00aa97e49027111311232c5b928d41"},"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":"2605.14597","created_at":"2026-05-17T23:39:04.294566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14597v1","created_at":"2026-05-17T23:39:04.294566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14597","created_at":"2026-05-17T23:39:04.294566+00:00"},{"alias_kind":"pith_short_12","alias_value":"A62637546VBG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"A62637546VBGORUX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6263754","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32","json":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32.json","graph_json":"https://pith.science/api/pith-number/A62637546VBGORUXFBD5MX2B32/graph.json","events_json":"https://pith.science/api/pith-number/A62637546VBGORUXFBD5MX2B32/events.json","paper":"https://pith.science/paper/A6263754"},"agent_actions":{"view_html":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32","download_json":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32.json","view_paper":"https://pith.science/paper/A6263754","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14597&json=true","fetch_graph":"https://pith.science/api/pith-number/A62637546VBGORUXFBD5MX2B32/graph.json","fetch_events":"https://pith.science/api/pith-number/A62637546VBGORUXFBD5MX2B32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32/action/storage_attestation","attest_author":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32/action/author_attestation","sign_citation":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32/action/citation_signature","submit_replication":"https://pith.science/pith/A62637546VBGORUXFBD5MX2B32/action/replication_record"}},"created_at":"2026-05-17T23:39:04.294566+00:00","updated_at":"2026-05-17T23:39:04.294566+00:00"}