{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AMQPPDNQ5P3NYJDNC6HBACJJ7U","short_pith_number":"pith:AMQPPDNQ","schema_version":"1.0","canonical_sha256":"0320f78db0ebf6dc246d178e100929fd0d2e15252464414f59b223efd8b904ea","source":{"kind":"arxiv","id":"2102.05107","version":1},"attestation_state":"computed","paper":{"title":"Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Dale R. Durran, Jonathan A. Weyn, Nathaniel Cresswell-Clay, Rich Caruana","submitted_at":"2021-02-09T20:14:43Z","abstract_excerpt":"We present an ensemble prediction system using a Deep Learning Weather Prediction (DLWP) model that recursively predicts key atmospheric variables with six-hour time resolution. This model uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts. The approach is computationally efficient, requiring just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4{\\deg} resolution. Ensemble spread is primarily produced by randomizing the CNN training process to create a set of 32 DLWP models with slightly different learned weights. A"},"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":"2102.05107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.ao-ph","submitted_at":"2021-02-09T20:14:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5159a257ca4f08a4117d9ff348f3061ae382b323e9fe900964ba7c1d48082821","abstract_canon_sha256":"c5cd23597fe04dd6d735e4aef7e49ed19fed2915c1e483bba8d6358186ecda28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:13.261520Z","signature_b64":"WlJb+gSxV7CbNFnQ9aQ9DnrjoK6RnWmvl+vmynq3xeyobcMYHc2C2I2Tg631j6ed89wY9s4ISx6QKsEMiEaiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0320f78db0ebf6dc246d178e100929fd0d2e15252464414f59b223efd8b904ea","last_reissued_at":"2026-07-05T03:39:13.261033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:13.261033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-seasonal forecasting with a large ensemble of deep-learning weather prediction models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Dale R. Durran, Jonathan A. Weyn, Nathaniel Cresswell-Clay, Rich Caruana","submitted_at":"2021-02-09T20:14:43Z","abstract_excerpt":"We present an ensemble prediction system using a Deep Learning Weather Prediction (DLWP) model that recursively predicts key atmospheric variables with six-hour time resolution. This model uses convolutional neural networks (CNNs) on a cubed sphere grid to produce global forecasts. The approach is computationally efficient, requiring just three minutes on a single GPU to produce a 320-member set of six-week forecasts at 1.4{\\deg} resolution. Ensemble spread is primarily produced by randomizing the CNN training process to create a set of 32 DLWP models with slightly different learned weights. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.05107","kind":"arxiv","version":1},"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/2102.05107/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":"2102.05107","created_at":"2026-07-05T03:39:13.261086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.05107v1","created_at":"2026-07-05T03:39:13.261086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.05107","created_at":"2026-07-05T03:39:13.261086+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMQPPDNQ5P3N","created_at":"2026-07-05T03:39:13.261086+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMQPPDNQ5P3NYJDN","created_at":"2026-07-05T03:39:13.261086+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMQPPDNQ","created_at":"2026-07-05T03:39:13.261086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2202.11214","citing_title":"FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U","json":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U.json","graph_json":"https://pith.science/api/pith-number/AMQPPDNQ5P3NYJDNC6HBACJJ7U/graph.json","events_json":"https://pith.science/api/pith-number/AMQPPDNQ5P3NYJDNC6HBACJJ7U/events.json","paper":"https://pith.science/paper/AMQPPDNQ"},"agent_actions":{"view_html":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U","download_json":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U.json","view_paper":"https://pith.science/paper/AMQPPDNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.05107&json=true","fetch_graph":"https://pith.science/api/pith-number/AMQPPDNQ5P3NYJDNC6HBACJJ7U/graph.json","fetch_events":"https://pith.science/api/pith-number/AMQPPDNQ5P3NYJDNC6HBACJJ7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U/action/storage_attestation","attest_author":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U/action/author_attestation","sign_citation":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U/action/citation_signature","submit_replication":"https://pith.science/pith/AMQPPDNQ5P3NYJDNC6HBACJJ7U/action/replication_record"}},"created_at":"2026-07-05T03:39:13.261086+00:00","updated_at":"2026-07-05T03:39:13.261086+00:00"}