{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UQORXY5OFKA6RKWN76VUKXV77","short_pith_number":"pith:7UQORXY5","schema_version":"1.0","canonical_sha256":"fd20e8df1d71540f45566ffd5a2af5ffe35023de3c051b024d3e85d93a840f0a","source":{"kind":"arxiv","id":"2507.12144","version":2},"attestation_state":"computed","paper":{"title":"FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Alexander Keller, Anima Anandkumar, Ankur Mahesh, Boris Bonev, Jean Kossaifi, Karthik Kashinath, Mauro Bisson, Michael S. Pritchard, Thorsten Kurth, William D. Collins","submitted_at":"2025-07-16T11:22:18Z","abstract_excerpt":"FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. The approach is designed to respect spherical geometry and to accurately model the spatially correlated probabilistic nature of the problem, resulting in stable spectra and realistic dynamics across multiple scales. FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods, while producing forecasts 8 to 60 times faster than these approaches. In contrast to oth"},"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":"2507.12144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T11:22:18Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"f78951d53e2d265b1800bd2fb8aafd140eb60dfad6354b023598b6736710409b","abstract_canon_sha256":"552d65d42b8c4fd875b14a8801694dac16a8096761b5cac669646ef46798601e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:14.532521Z","signature_b64":"+lE3ubKJ+YxBgkcD4hZLJJSWNpAC0yrvvlno+qdykO7Empekk5Dend5CKq54mqtgdtcahyKJiIRhNX1jRbTMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd20e8df1d71540f45566ffd5a2af5ffe35023de3c051b024d3e85d93a840f0a","last_reissued_at":"2026-07-05T11:39:14.531922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:14.531922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FourCastNet 3: A geometric approach to probabilistic machine-learning weather forecasting at scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Alexander Keller, Anima Anandkumar, Ankur Mahesh, Boris Bonev, Jean Kossaifi, Karthik Kashinath, Mauro Bisson, Michael S. Pritchard, Thorsten Kurth, William D. Collins","submitted_at":"2025-07-16T11:22:18Z","abstract_excerpt":"FourCastNet 3 advances global weather modeling by implementing a scalable, geometric machine learning (ML) approach to probabilistic ensemble forecasting. The approach is designed to respect spherical geometry and to accurately model the spatially correlated probabilistic nature of the problem, resulting in stable spectra and realistic dynamics across multiple scales. FourCastNet 3 delivers forecasting accuracy that surpasses leading conventional ensemble models and rivals the best diffusion-based methods, while producing forecasts 8 to 60 times faster than these approaches. In contrast to oth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12144","kind":"arxiv","version":2},"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/2507.12144/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":"2507.12144","created_at":"2026-07-05T11:39:14.531980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12144v2","created_at":"2026-07-05T11:39:14.531980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12144","created_at":"2026-07-05T11:39:14.531980+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UQORXY5OFKA","created_at":"2026-07-05T11:39:14.531980+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UQORXY5OFKA6RKW","created_at":"2026-07-05T11:39:14.531980+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UQORXY5","created_at":"2026-07-05T11:39:14.531980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26421","citing_title":"Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27168","citing_title":"Deep learning model emulators for marine biogeochemistry forecasting from days to decades","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12997","citing_title":"Reliability of Probabilistic Emulation of Physical Systems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08871","citing_title":"Fourier Neural Operators with rank-1 lattice points and hyperbolic cross","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08563","citing_title":"Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01171","citing_title":"Decision-Aware Training for Sample-Based Generative Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15470","citing_title":"Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24782","citing_title":"The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02610","citing_title":"Samudra 2: Scaling Ocean Emulators across Resolutions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07928","citing_title":"Disentangling the effects of sea surface temperature and CO$_2$ in global machine learned weather-climate emulators","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23778","citing_title":"The physics of AI weather models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15470","citing_title":"Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2601.17636","citing_title":"HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01486","citing_title":"Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09317","citing_title":"SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13847","citing_title":"Physics constraints and response validation in discrete-time reduced-order modeling: from idealized turbulent systems to climate dynamics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16090","citing_title":"Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11111","citing_title":"ShardTensor: Domain Parallelism for Scientific Machine Learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06873","citing_title":"One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00850","citing_title":"Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06873","citing_title":"One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05068","citing_title":"Towards Scaling Law Analysis For Spatiotemporal Weather Data","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09041","citing_title":"U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01599","citing_title":"Cast3: Translating numerical weather prediction principles into data-driven forecasting","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77","json":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77.json","graph_json":"https://pith.science/api/pith-number/7UQORXY5OFKA6RKWN76VUKXV77/graph.json","events_json":"https://pith.science/api/pith-number/7UQORXY5OFKA6RKWN76VUKXV77/events.json","paper":"https://pith.science/paper/7UQORXY5"},"agent_actions":{"view_html":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77","download_json":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77.json","view_paper":"https://pith.science/paper/7UQORXY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12144&json=true","fetch_graph":"https://pith.science/api/pith-number/7UQORXY5OFKA6RKWN76VUKXV77/graph.json","fetch_events":"https://pith.science/api/pith-number/7UQORXY5OFKA6RKWN76VUKXV77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77/action/storage_attestation","attest_author":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77/action/author_attestation","sign_citation":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77/action/citation_signature","submit_replication":"https://pith.science/pith/7UQORXY5OFKA6RKWN76VUKXV77/action/replication_record"}},"created_at":"2026-07-05T11:39:14.531980+00:00","updated_at":"2026-07-05T11:39:14.531980+00:00"}