{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3HX7Q54SCJUVYHKY6VESK3CYVK","short_pith_number":"pith:3HX7Q54S","schema_version":"1.0","canonical_sha256":"d9eff8779212695c1d58f549256c58aa8a9fa506aea241d13c1fccce9976bea8","source":{"kind":"arxiv","id":"2605.13197","version":1},"attestation_state":"computed","paper":{"title":"McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"McCast corrects latent drift in autoregressive precipitation models using a memory bank to produce coherent long-horizon forecasts.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lintao Wang, Mengwei He, Patrick Filippi, Penghui Wen, Thomas Francis Bishop, Yu Luo, Zhiyong Wang","submitted_at":"2026-05-13T08:51:24Z","abstract_excerpt":"Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. However, such an approach accumulates errors over long rollouts, causing forecasts to drift away from physically plausible evolution trajectories. Although various studies have attempted to alleviate this problem by improving step-wise prediction accuracy, they largely neglect the global temporal evolution of meteorological systems and lack mechanisms to actively correct drift during rollouts. To address this issue, we propose McCast, a memory-guided"},"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":false},"canonical_record":{"source":{"id":"2605.13197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:51:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8228a6864765d70c3d63aec7cb10f686e9e2a296bb02e940815d8edec0a0f4e8","abstract_canon_sha256":"e6aafeb8e75b21198796d7f45088af5442361d0180302fa9fba0b9502b3a2502"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:48.711293Z","signature_b64":"CKZdlPafK4aXhgma33bQGdkXcDbG6DVe2HkKxLCP2/33SRrGqmXfR7TIrOGN92a8K15b8RhiQYBsx/t5vNaDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9eff8779212695c1d58f549256c58aa8a9fa506aea241d13c1fccce9976bea8","last_reissued_at":"2026-05-18T03:08:48.710655Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:48.710655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"McCast: Memory-Guided Latent Drift Correction for Long-Horizon Precipitation Nowcasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"McCast corrects latent drift in autoregressive precipitation models using a memory bank to produce coherent long-horizon forecasts.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Lintao Wang, Mengwei He, Patrick Filippi, Penghui Wen, Thomas Francis Bishop, Yu Luo, Zhiyong Wang","submitted_at":"2026-05-13T08:51:24Z","abstract_excerpt":"Existing precipitation nowcasting methods typically adopt an autoregressive formulation, where future states are predicted from previous outputs. However, such an approach accumulates errors over long rollouts, causing forecasts to drift away from physically plausible evolution trajectories. Although various studies have attempted to alleviate this problem by improving step-wise prediction accuracy, they largely neglect the global temporal evolution of meteorological systems and lack mechanisms to actively correct drift during rollouts. To address this issue, we propose McCast, a memory-guided"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By explicitly correcting latent evolution, instead of improving step-wise prediction accuracy only, McCast produces more temporally coherent and reliable long-horizon forecasts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a temporally organized memory bank can reliably estimate and apply drift corrections to latent states without introducing new inconsistencies or requiring domain-specific tuning that is not captured in the abstract description.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"McCast uses a Drift-Corrective Memory Bank to actively correct latent drift in autoregressive precipitation nowcasting for more coherent long-horizon forecasts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"McCast corrects latent drift in autoregressive precipitation models using a memory bank to produce coherent long-horizon forecasts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9f09f82582a7d8eaf03a5edcca1b203cb8969c4c1b2c6d6468f0b9efcde451ab"},"source":{"id":"2605.13197","kind":"arxiv","version":1},"verdict":{"id":"abd4f514-851b-45b3-b4f5-d00fe7e1536f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:32:09.629144Z","strongest_claim":"By explicitly correcting latent evolution, instead of improving step-wise prediction accuracy only, McCast produces more temporally coherent and reliable long-horizon forecasts.","one_line_summary":"McCast uses a Drift-Corrective Memory Bank to actively correct latent drift in autoregressive precipitation nowcasting for more coherent long-horizon forecasts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a temporally organized memory bank can reliably estimate and apply drift corrections to latent states without introducing new inconsistencies or requiring domain-specific tuning that is not captured in the abstract description.","pith_extraction_headline":"McCast corrects latent drift in autoregressive precipitation models using a memory bank to produce coherent long-horizon forecasts."},"references":{"count":37,"sample":[{"doi":"","year":2021,"title":"Skilful pre- cipitation nowcasting using deep generative models of radar.Nature, 597(7878):672–677, 2021","work_id":"2a732139-bfb5-44f9-ab1c-3aa53c508cb7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Skilful nowcasting of extreme precipitation with nowcastnet.Nature, 619 (7970):526–532, 2023","work_id":"17271ea2-f8fe-4881-a5f7-1e94471ceff7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Diffcast: A unified framework via residual diffusion for precipitation nowcasting","work_id":"1217d1d6-70dd-46d3-8f01-720106ef98b1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"AlphaPre: Amplitude-phase disentanglement model for precipitation nowcasting","work_id":"ad06e325-4008-46d5-9cce-730571b52181","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"CasCast: Skillful high-resolution precipitation nowcasting via cascaded modelling","work_id":"9d17f4ec-4a2c-4d99-a13a-c8b5ae6c262b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"7b0fc0eccd980bd437ee49d70281cadfff8aab9a1f3ce47b923d6ecc79f9570a","internal_anchors":1},"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":"2605.13197","created_at":"2026-05-18T03:08:48.710764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13197v1","created_at":"2026-05-18T03:08:48.710764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13197","created_at":"2026-05-18T03:08:48.710764+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HX7Q54SCJUV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HX7Q54SCJUVYHKY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HX7Q54S","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23478","citing_title":"PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK","json":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK.json","graph_json":"https://pith.science/api/pith-number/3HX7Q54SCJUVYHKY6VESK3CYVK/graph.json","events_json":"https://pith.science/api/pith-number/3HX7Q54SCJUVYHKY6VESK3CYVK/events.json","paper":"https://pith.science/paper/3HX7Q54S"},"agent_actions":{"view_html":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK","download_json":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK.json","view_paper":"https://pith.science/paper/3HX7Q54S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13197&json=true","fetch_graph":"https://pith.science/api/pith-number/3HX7Q54SCJUVYHKY6VESK3CYVK/graph.json","fetch_events":"https://pith.science/api/pith-number/3HX7Q54SCJUVYHKY6VESK3CYVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK/action/storage_attestation","attest_author":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK/action/author_attestation","sign_citation":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK/action/citation_signature","submit_replication":"https://pith.science/pith/3HX7Q54SCJUVYHKY6VESK3CYVK/action/replication_record"}},"created_at":"2026-05-18T03:08:48.710764+00:00","updated_at":"2026-05-18T03:08:48.710764+00:00"}