{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6H2BOM2OFXPW7LM65RTCFRAO7","short_pith_number":"pith:W6H2BOM2","schema_version":"1.0","canonical_sha256":"b78fa0b99a716efb7d6cf76331162077de244879394e972440fcf7fae0f725ae","source":{"kind":"arxiv","id":"2404.19630","version":1},"attestation_state":"computed","paper":{"title":"Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ankur Mahesh, Jared D. Willard, Peter Harrington, Shashank Subramanian, Travis A. O'Brien, William D. Collins","submitted_at":"2024-04-30T15:30:14Z","abstract_excerpt":"The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training proced"},"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":"2404.19630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-30T15:30:14Z","cross_cats_sorted":[],"title_canon_sha256":"560ab4f8006b07b6ab399e6ddc482ba850a20a483028d9534aa156bd2d30bc88","abstract_canon_sha256":"83232eed4682259e95150ff722a6985fb144d2f6a9ac84b93dcbf5511710a9fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:54.719259Z","signature_b64":"N4Vk73OwQ/YGAJeGHaZXkUHtoTW8jhnS34EjlUHzYfDywYjiGhM/GARjmCB0IRyTX+YYFnZ6ClciHdS2F9UNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78fa0b99a716efb7d6cf76331162077de244879394e972440fcf7fae0f725ae","last_reissued_at":"2026-07-05T08:13:54.718830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:54.718830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analyzing and Exploring Training Recipes for Large-Scale Transformer-Based Weather Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ankur Mahesh, Jared D. Willard, Peter Harrington, Shashank Subramanian, Travis A. O'Brien, William D. Collins","submitted_at":"2024-04-30T15:30:14Z","abstract_excerpt":"The rapid rise of deep learning (DL) in numerical weather prediction (NWP) has led to a proliferation of models which forecast atmospheric variables with comparable or superior skill than traditional physics-based NWP. However, among these leading DL models, there is a wide variance in both the training settings and architecture used. Further, the lack of thorough ablation studies makes it hard to discern which components are most critical to success. In this work, we show that it is possible to attain high forecast skill even with relatively off-the-shelf architectures, simple training proced"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19630","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/2404.19630/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":"2404.19630","created_at":"2026-07-05T08:13:54.718885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19630v1","created_at":"2026-07-05T08:13:54.718885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19630","created_at":"2026-07-05T08:13:54.718885+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6H2BOM2OFXP","created_at":"2026-07-05T08:13:54.718885+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6H2BOM2OFXPW7LM","created_at":"2026-07-05T08:13:54.718885+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6H2BOM2","created_at":"2026-07-05T08:13:54.718885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17720","citing_title":"PEAR: Equal Area Weather Forecasting on the Sphere","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7","json":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7.json","graph_json":"https://pith.science/api/pith-number/W6H2BOM2OFXPW7LM65RTCFRAO7/graph.json","events_json":"https://pith.science/api/pith-number/W6H2BOM2OFXPW7LM65RTCFRAO7/events.json","paper":"https://pith.science/paper/W6H2BOM2"},"agent_actions":{"view_html":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7","download_json":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7.json","view_paper":"https://pith.science/paper/W6H2BOM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19630&json=true","fetch_graph":"https://pith.science/api/pith-number/W6H2BOM2OFXPW7LM65RTCFRAO7/graph.json","fetch_events":"https://pith.science/api/pith-number/W6H2BOM2OFXPW7LM65RTCFRAO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7/action/storage_attestation","attest_author":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7/action/author_attestation","sign_citation":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7/action/citation_signature","submit_replication":"https://pith.science/pith/W6H2BOM2OFXPW7LM65RTCFRAO7/action/replication_record"}},"created_at":"2026-07-05T08:13:54.718885+00:00","updated_at":"2026-07-05T08:13:54.718885+00:00"}