{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:34GSLIUFFAO4V7MGIVX2VHHKNX","short_pith_number":"pith:34GSLIUF","canonical_record":{"source":{"id":"2605.13761","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:41:14Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"398dcb4548ca70cf8574cbea280ce802c16205c11feba37724d6215672d15ca4","abstract_canon_sha256":"24118dd2ff4b83272ee6eea5e7d222e6a4cdb606ddd015f2ccde2c7a4e92b0ec"},"schema_version":"1.0"},"canonical_sha256":"df0d25a285281dcafd86456faa9cea6de740cad95510151cd524b994da35d04d","source":{"kind":"arxiv","id":"2605.13761","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13761","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13761v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13761","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"34GSLIUFFAO4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"34GSLIUFFAO4V7MG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"34GSLIUF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:34GSLIUFFAO4V7MGIVX2VHHKNX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13761","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:41:14Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"398dcb4548ca70cf8574cbea280ce802c16205c11feba37724d6215672d15ca4","abstract_canon_sha256":"24118dd2ff4b83272ee6eea5e7d222e6a4cdb606ddd015f2ccde2c7a4e92b0ec"},"schema_version":"1.0"},"canonical_sha256":"df0d25a285281dcafd86456faa9cea6de740cad95510151cd524b994da35d04d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.172343Z","signature_b64":"jmeKQIW0UBAk3HH9m1l1WI224NhHsmFfP2wO2AUB25zp6aOeTBOA5zQIfg6fI1BaJwVv5hQRzq+pTHxwqp+9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df0d25a285281dcafd86456faa9cea6de740cad95510151cd524b994da35d04d","last_reissued_at":"2026-05-18T02:44:16.171734Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.171734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13761","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydODF8OmkJuGY3yzLODwMC86B1QP4VQ3VgJNwgThBRj05O8oO7jPvjiIFZ8V0B2rDn6C7A11lPjqdMGSx34jBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:51:32.532923Z"},"content_sha256":"62a2fee1087a5f303d42457112646832841668ac84ca7537dd1acbdc36d13152","schema_version":"1.0","event_id":"sha256:62a2fee1087a5f303d42457112646832841668ac84ca7537dd1acbdc36d13152"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:34GSLIUFFAO4V7MGIVX2VHHKNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds.","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Eugene Yan, Jeremy Feinstein, Omar Sallam, Peng Chen, Phillip Si, Yuan Qiu, Ziang He","submitted_at":"2026-05-13T16:41:14Z","abstract_excerpt":"AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-dimensional shallow water equation (SWE) solvers still require $\\sim 55$ minutes per $96$-hour run on a $\\sim 4.2$-million-active-cell metropolitan basin (the Des~Plaines River basin at $30\\,\\mathrm{m}$ resolution), making such workloads prohibitive at native resolution. We present the Conditional Latent Dynamics Network (CLDNet): a low-dimensional latent neural ODE driven by rainfall, paired with a coordinate-based decoder conditioned on static "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CLDNet produces a full 96-hour basin-wide forecast in ~29 seconds -- a ~115× speedup -- while reaching a critical success index of ≈86% at the 0.5 m inundation threshold and roughly halving the relative RMSE of an unconditional baseline on the Des Plaines case study.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The latent neural ODE dynamics, trained on simulator output, continue to generalize accurately to unseen rainfall patterns and to the full range of terrain features without accumulating errors over the 96-hour horizon.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CLDNet is a conditional latent dynamics network surrogate for the shallow water equations that delivers 115x faster 96-hour flood forecasts on irregular metropolitan basins while maintaining usable accuracy against gauge data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ba150dfbbd1296ea3154d433f588e06416968c93dbd5e28e2a752b0e687d20b9"},"source":{"id":"2605.13761","kind":"arxiv","version":1},"verdict":{"id":"57e7a769-b33c-4673-9db8-8f6d1339eb25","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:30:21.135774Z","strongest_claim":"CLDNet produces a full 96-hour basin-wide forecast in ~29 seconds -- a ~115× speedup -- while reaching a critical success index of ≈86% at the 0.5 m inundation threshold and roughly halving the relative RMSE of an unconditional baseline on the Des Plaines case study.","one_line_summary":"CLDNet is a conditional latent dynamics network surrogate for the shallow water equations that delivers 115x faster 96-hour flood forecasts on irregular metropolitan basins while maintaining usable accuracy against gauge data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The latent neural ODE dynamics, trained on simulator output, continue to generalize accurately to unseen rainfall patterns and to the full range of terrain features without accumulating errors over the 96-hour horizon.","pith_extraction_headline":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds."},"references":{"count":41,"sample":[{"doi":"10.1038/s41467-022-30727-4","year":2022,"title":"J. Rentschler, M. Salhab, B. A. Jafino, Flood exposure and poverty in 188 countries, Nature Commu- nications 13 (1) (2022) 3527.doi:10.1038/s41467-022-30727-4","work_id":"34ad86ad-5c51-4ecf-aa8c-83f5eb3cb2e9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1038/s41586-021-03695-w","year":2021,"title":"B. Tellman, J. A. Sullivan, C. Kuhn, A. J. Kettner, C. S. Doyle, G. R. Brakenridge, T. A. Erickson, D. A. Slayback, Satellite imaging reveals increased proportion of population exposed to floods, Natu","work_id":"ab728dc8-d9a4-4c94-9b24-6046b58c35ca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.jhydrol.2010.03.027","year":2010,"title":"P. D. Bates, M. S. Horritt, T. J. Fewtrell, A simple inertial formulation of the shallow water equations for efficient two-dimensional flood inundation modelling, Journal of Hydrology 387 (1–2) (2010)","work_id":"08549c7c-e715-4662-a93d-dc708b7e1ee9","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/2016wr020055","year":2017,"title":"X. Xia, Q. Liang, X. Ming, J. Hou, An efficient and stable hydrodynamic model with novel source term discretization schemes for overland flow and flood simulations, Water resources research 53 (5) (20","work_id":"681c9f30-2839-4095-aa82-20c338b342f9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.advwatres.2018.05","year":2018,"title":"X. Xia, Q. Liang, A new efficient implicit scheme for discretising the stiff friction terms in the shallow water equations, Advances in water resources 117 (2018) 87–97.doi:10.1016/j.advwatres.2018.05","work_id":"125d36ee-c769-4b4a-9e04-3e10addbf2a6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"387de47b4382c30e0c35fc6e2def0522636d220881301cc32eee089fa6ff0ac9","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6e0ee265664a7890d1ae410df078733bde447d8c2935478ae8ccb736b5a42031"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"57e7a769-b33c-4673-9db8-8f6d1339eb25"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"imI5lcf/l8VscYlZ9ST8nfUBKCJSU6kb3yQVZGyqsGbJQ8ciTQG93VPr4NFib4HwZ8GIZO6R3Tbec7wtNAtoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:51:32.534205Z"},"content_sha256":"319b22af968aaa77e66c4e44b95b40762672f6352dcb4a88accc076c913c6f8b","schema_version":"1.0","event_id":"sha256:319b22af968aaa77e66c4e44b95b40762672f6352dcb4a88accc076c913c6f8b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:34GSLIUFFAO4V7MGIVX2VHHKNX","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.jhydrol.2024.131998.30) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"F. Yang, W. Ding, J. Zhao, L. Song, D. Yang, X. Li, Rapid urban flood inundation forecasting using a physics-informed deep learning approach, Journal of Hydrology 643 (2024) 131998.doi:10.1016/j. jhydrol.2024.131998. 30","arxiv_id":"2605.13761","detector":"doi_compliance","evidence":{"ref_index":11,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"F. Yang, W. Ding, J. Zhao, L. Song, D. Yang, X. Li, Rapid urban flood inundation forecasting using a physics-informed deep learning approach, Journal of Hydrology 643 (2024) 131998.doi:10.1016/j. jhydrol.2024.131998. 30","reconstructed_doi":"10.1016/j.jhydrol.2024.131998.30"},"severity":"advisory","ref_index":11,"audited_at":"2026-05-19T06:15:58.386877Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.jhydrol.2024.131998.30","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"ea0f7eadc71c8cd8f164e22fc4fb3f5c984f53d8659b6977cfbf3956e5f42eb5","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":104,"payload_sha256":"2b80b4ed0a62492daff6a6f157da4e246dc62ee857f2eeb275f92955c2d0aac4","signature_b64":"7MykZyUMrFHp+CYmzgP5YSvOque/djd5X1XYAQaGXi8hGn9aOuxuVcMr0wpv3kZ8/yKN2eXnJmmRnMgL7ygtBQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T06:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rfp/y7JVtgddHT7eUKEFhUhi4uB4Ug0Te8nbZDX+AM7IAsPDUHOJGpaUubS02baeOUBmbzttwHlgDEWLUsJqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:51:32.535800Z"},"content_sha256":"79f91dc97102e5708538294edb132070a99314467ec92101964a0d9c3d78e8c2","schema_version":"1.0","event_id":"sha256:79f91dc97102e5708538294edb132070a99314467ec92101964a0d9c3d78e8c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/bundle.json","state_url":"https://pith.science/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T03:51:32Z","links":{"resolver":"https://pith.science/pith/34GSLIUFFAO4V7MGIVX2VHHKNX","bundle":"https://pith.science/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/bundle.json","state":"https://pith.science/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/34GSLIUFFAO4V7MGIVX2VHHKNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:34GSLIUFFAO4V7MGIVX2VHHKNX","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"24118dd2ff4b83272ee6eea5e7d222e6a4cdb606ddd015f2ccde2c7a4e92b0ec","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:41:14Z","title_canon_sha256":"398dcb4548ca70cf8574cbea280ce802c16205c11feba37724d6215672d15ca4"},"schema_version":"1.0","source":{"id":"2605.13761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13761","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13761v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13761","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"34GSLIUFFAO4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"34GSLIUFFAO4V7MG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"34GSLIUF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:319b22af968aaa77e66c4e44b95b40762672f6352dcb4a88accc076c913c6f8b","target":"graph","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CLDNet produces a full 96-hour basin-wide forecast in ~29 seconds -- a ~115× speedup -- while reaching a critical success index of ≈86% at the 0.5 m inundation threshold and roughly halving the relative RMSE of an unconditional baseline on the Des Plaines case study."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The latent neural ODE dynamics, trained on simulator output, continue to generalize accurately to unseen rainfall patterns and to the full range of terrain features without accumulating errors over the 96-hour horizon."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CLDNet is a conditional latent dynamics network surrogate for the shallow water equations that delivers 115x faster 96-hour flood forecasts on irregular metropolitan basins while maintaining usable accuracy against gauge data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds."}],"snapshot_sha256":"ba150dfbbd1296ea3154d433f588e06416968c93dbd5e28e2a752b0e687d20b9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6e0ee265664a7890d1ae410df078733bde447d8c2935478ae8ccb736b5a42031"},"paper":{"abstract_excerpt":"AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-dimensional shallow water equation (SWE) solvers still require $\\sim 55$ minutes per $96$-hour run on a $\\sim 4.2$-million-active-cell metropolitan basin (the Des~Plaines River basin at $30\\,\\mathrm{m}$ resolution), making such workloads prohibitive at native resolution. We present the Conditional Latent Dynamics Network (CLDNet): a low-dimensional latent neural ODE driven by rainfall, paired with a coordinate-based decoder conditioned on static ","authors_text":"Eugene Yan, Jeremy Feinstein, Omar Sallam, Peng Chen, Phillip Si, Yuan Qiu, Ziang He","cross_cats":["cs.CE"],"headline":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:41:14Z","title":"Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations"},"references":{"count":41,"internal_anchors":2,"resolved_work":41,"sample":[{"cited_arxiv_id":"","doi":"10.1038/s41467-022-30727-4","is_internal_anchor":false,"ref_index":1,"title":"J. Rentschler, M. Salhab, B. A. Jafino, Flood exposure and poverty in 188 countries, Nature Commu- nications 13 (1) (2022) 3527.doi:10.1038/s41467-022-30727-4","work_id":"34ad86ad-5c51-4ecf-aa8c-83f5eb3cb2e9","year":2022},{"cited_arxiv_id":"","doi":"10.1038/s41586-021-03695-w","is_internal_anchor":false,"ref_index":2,"title":"B. Tellman, J. A. Sullivan, C. Kuhn, A. J. Kettner, C. S. Doyle, G. R. Brakenridge, T. A. Erickson, D. A. Slayback, Satellite imaging reveals increased proportion of population exposed to floods, Natu","work_id":"ab728dc8-d9a4-4c94-9b24-6046b58c35ca","year":2021},{"cited_arxiv_id":"","doi":"10.1016/j.jhydrol.2010.03.027","is_internal_anchor":false,"ref_index":3,"title":"P. D. Bates, M. S. Horritt, T. J. Fewtrell, A simple inertial formulation of the shallow water equations for efficient two-dimensional flood inundation modelling, Journal of Hydrology 387 (1–2) (2010)","work_id":"08549c7c-e715-4662-a93d-dc708b7e1ee9","year":2010},{"cited_arxiv_id":"","doi":"10.1002/2016wr020055","is_internal_anchor":false,"ref_index":4,"title":"X. Xia, Q. Liang, X. Ming, J. Hou, An efficient and stable hydrodynamic model with novel source term discretization schemes for overland flow and flood simulations, Water resources research 53 (5) (20","work_id":"681c9f30-2839-4095-aa82-20c338b342f9","year":2017},{"cited_arxiv_id":"","doi":"10.1016/j.advwatres.2018.05","is_internal_anchor":false,"ref_index":5,"title":"X. Xia, Q. Liang, A new efficient implicit scheme for discretising the stiff friction terms in the shallow water equations, Advances in water resources 117 (2018) 87–97.doi:10.1016/j.advwatres.2018.05","work_id":"125d36ee-c769-4b4a-9e04-3e10addbf2a6","year":2018}],"snapshot_sha256":"387de47b4382c30e0c35fc6e2def0522636d220881301cc32eee089fa6ff0ac9"},"source":{"id":"2605.13761","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:30:21.135774Z","id":"57e7a769-b33c-4673-9db8-8f6d1339eb25","model_set":{"reader":"grok-4.3"},"one_line_summary":"CLDNet is a conditional latent dynamics network surrogate for the shallow water equations that delivers 115x faster 96-hour flood forecasts on irregular metropolitan basins while maintaining usable accuracy against gauge data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CLDNet uses a rainfall-driven latent neural ODE and terrain-conditioned decoder to surrogate the shallow water equations, producing 96-hour metropolitan flood forecasts in 29 seconds.","strongest_claim":"CLDNet produces a full 96-hour basin-wide forecast in ~29 seconds -- a ~115× speedup -- while reaching a critical success index of ≈86% at the 0.5 m inundation threshold and roughly halving the relative RMSE of an unconditional baseline on the Des Plaines case study.","weakest_assumption":"The latent neural ODE dynamics, trained on simulator output, continue to generalize accurately to unseen rainfall patterns and to the full range of terrain features without accumulating errors over the 96-hour horizon."}},"verdict_id":"57e7a769-b33c-4673-9db8-8f6d1339eb25"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62a2fee1087a5f303d42457112646832841668ac84ca7537dd1acbdc36d13152","target":"record","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"24118dd2ff4b83272ee6eea5e7d222e6a4cdb606ddd015f2ccde2c7a4e92b0ec","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T16:41:14Z","title_canon_sha256":"398dcb4548ca70cf8574cbea280ce802c16205c11feba37724d6215672d15ca4"},"schema_version":"1.0","source":{"id":"2605.13761","kind":"arxiv","version":1}},"canonical_sha256":"df0d25a285281dcafd86456faa9cea6de740cad95510151cd524b994da35d04d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df0d25a285281dcafd86456faa9cea6de740cad95510151cd524b994da35d04d","first_computed_at":"2026-05-18T02:44:16.171734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.171734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jmeKQIW0UBAk3HH9m1l1WI224NhHsmFfP2wO2AUB25zp6aOeTBOA5zQIfg6fI1BaJwVv5hQRzq+pTHxwqp+9DA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.172343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62a2fee1087a5f303d42457112646832841668ac84ca7537dd1acbdc36d13152","sha256:319b22af968aaa77e66c4e44b95b40762672f6352dcb4a88accc076c913c6f8b","sha256:79f91dc97102e5708538294edb132070a99314467ec92101964a0d9c3d78e8c2"],"state_sha256":"151c3ce1fd835745d5472aeb06304de6e694a0d28f2af175af7078bc1ef3198c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J+sFDR1oVDwCLRASCCXzHUYY3gAOi/+UD3kEwxkTNajbN3cjOD5MlOKB2ZQ9wCNWm5kfd/nX4W10t2i5BqJFCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T03:51:32.540224Z","bundle_sha256":"3833333ab65622450ce1623b959f4e2066b3d4aaf02814655f54baa2cc49c5e7"}}