{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24F4T3V2GKLPCOWSGXAKUO7JFZ","short_pith_number":"pith:24F4T3V2","schema_version":"1.0","canonical_sha256":"d70bc9eeba3296f13ad235c0aa3be92e74bd03bd00d05785ad5a2811673f01bf","source":{"kind":"arxiv","id":"2408.01581","version":3},"attestation_state":"computed","paper":{"title":"Huge Ensembles Part II: Properties of a Huge Ensemble of Hindcasts Generated with Spherical Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Ankur Mahesh, Boris Bonev, David Pruitt, Jared Willard, Joshua North, Karthik Kashinath, Mark Risser, Michael Pritchard, Noah Brenowitz, Peter Harrington, Shashank Subramanian, Thorsten Kurth, Travis OBrien, William Collins, Yair Cohen","submitted_at":"2024-08-02T21:31:34Z","abstract_excerpt":"In Part I, we created an ensemble based on Spherical Fourier Neural Operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires orders of magnitude fewer computational resources. Here in Part II, we generate a huge ensemble (HENS), with 7,424 members initialized each day of summer 2023. We enumerate the technical requirement"},"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":"2408.01581","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T21:31:34Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"03f88781d6463e05e4050b5afe0bda6652a98b47737e7829e30eb20d132aa7d5","abstract_canon_sha256":"3c219e2111cf47eed90db3f8446d12a6d75260026be02fa27b37507e2b71c7ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:38.155491Z","signature_b64":"r3DrVgF3tde6CnvEQ9lyJW6U5D7KbogmSReQTMV/KHRQpAElBfjdMY4UzJrYw3x+4b8TnZNokiqUAs3L/qYQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d70bc9eeba3296f13ad235c0aa3be92e74bd03bd00d05785ad5a2811673f01bf","last_reissued_at":"2026-07-05T10:43:38.154894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:38.154894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Huge Ensembles Part II: Properties of a Huge Ensemble of Hindcasts Generated with Spherical Fourier Neural Operators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Ankur Mahesh, Boris Bonev, David Pruitt, Jared Willard, Joshua North, Karthik Kashinath, Mark Risser, Michael Pritchard, Noah Brenowitz, Peter Harrington, Shashank Subramanian, Thorsten Kurth, Travis OBrien, William Collins, Yair Cohen","submitted_at":"2024-08-02T21:31:34Z","abstract_excerpt":"In Part I, we created an ensemble based on Spherical Fourier Neural Operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires orders of magnitude fewer computational resources. Here in Part II, we generate a huge ensemble (HENS), with 7,424 members initialized each day of summer 2023. We enumerate the technical requirement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01581","kind":"arxiv","version":3},"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/2408.01581/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":"2408.01581","created_at":"2026-07-05T10:43:38.154955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01581v3","created_at":"2026-07-05T10:43:38.154955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01581","created_at":"2026-07-05T10:43:38.154955+00:00"},{"alias_kind":"pith_short_12","alias_value":"24F4T3V2GKLP","created_at":"2026-07-05T10:43:38.154955+00:00"},{"alias_kind":"pith_short_16","alias_value":"24F4T3V2GKLPCOWS","created_at":"2026-07-05T10:43:38.154955+00:00"},{"alias_kind":"pith_short_8","alias_value":"24F4T3V2","created_at":"2026-07-05T10:43:38.154955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19642","citing_title":"Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ","json":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ.json","graph_json":"https://pith.science/api/pith-number/24F4T3V2GKLPCOWSGXAKUO7JFZ/graph.json","events_json":"https://pith.science/api/pith-number/24F4T3V2GKLPCOWSGXAKUO7JFZ/events.json","paper":"https://pith.science/paper/24F4T3V2"},"agent_actions":{"view_html":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ","download_json":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ.json","view_paper":"https://pith.science/paper/24F4T3V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01581&json=true","fetch_graph":"https://pith.science/api/pith-number/24F4T3V2GKLPCOWSGXAKUO7JFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/24F4T3V2GKLPCOWSGXAKUO7JFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ/action/storage_attestation","attest_author":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ/action/author_attestation","sign_citation":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ/action/citation_signature","submit_replication":"https://pith.science/pith/24F4T3V2GKLPCOWSGXAKUO7JFZ/action/replication_record"}},"created_at":"2026-07-05T10:43:38.154955+00:00","updated_at":"2026-07-05T10:43:38.154955+00:00"}