{"paper":{"title":"An Attention-Based Stochastic Simulator for Multisite Extremes to Evaluate Nonstationary, Cascading Flood Risk","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An attention-based framework simulates multisite flood events that are coherent in space and time and linked to climate variability.","cross_cats":["physics.ao-ph","physics.data-an"],"primary_cat":"physics.geo-ph","authors_text":"Adam Nayak, Pierre Gentine, Upmanu Lall","submitted_at":"2025-09-17T16:46:56Z","abstract_excerpt":"Flood risk is correlated in space and time, challenging insurance systems that rely on diversification across assets. Financial instruments governing flood coverage are typically structured as 1 to 5-year contracts, exposing portfolios to climate-driven risk at interannual-to-decadal scales. Yet existing tools address climate risk either through seasonal forecasts extending only months or multidecadal projections misaligned with fiscal horizons, leaving a critical gap in actionable flood risk simulation. We introduce a multisite flood simulation framework combining attention-based analog retri"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The multisite flood simulation framework produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability, yielding physically interpretable flood clusters for portfolio-scale loss simulation and plausible out-of-sample flood risk catalogs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That attention-based analog retrieval combined with stochastic multivariate sequence generation can accurately reproduce nonstationary spatial-temporal flood dependencies across sites without post-hoc tuning or missing key drivers, as implied by the framework's ability to link clusters to large-scale climate drivers via wavelet analysis.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Presents an attention-based stochastic simulator for generating spatiotemporally coherent multisite flood sequences conditioned on interannual climate variability to support portfolio-scale flood risk assessment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An attention-based framework simulates multisite flood events that are coherent in space and time and linked to climate variability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3f669b9199ed13686858d8251988262c6bc47cf72e2b351e3c3b589802154985"},"source":{"id":"2509.14162","kind":"arxiv","version":3},"verdict":{"id":"7a61d3cd-1436-4636-bdf1-aece786d5f38","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T16:06:07.556023Z","strongest_claim":"The multisite flood simulation framework produces spatiotemporally coherent flood portfolios conditioned on interannual climate variability, yielding physically interpretable flood clusters for portfolio-scale loss simulation and plausible out-of-sample flood risk catalogs.","one_line_summary":"Presents an attention-based stochastic simulator for generating spatiotemporally coherent multisite flood sequences conditioned on interannual climate variability to support portfolio-scale flood risk assessment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That attention-based analog retrieval combined with stochastic multivariate sequence generation can accurately reproduce nonstationary spatial-temporal flood dependencies across sites without post-hoc tuning or missing key drivers, as implied by the framework's ability to link clusters to large-scale climate drivers via wavelet analysis.","pith_extraction_headline":"An attention-based framework simulates multisite flood events that are coherent in space and time and linked to climate variability."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.14162/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":1,"snapshot_sha256":"dd5edce12e6fcf10ee30129f735d2d966f7a17390504371a74683007f0062896"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}