{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CZWOASSNRCZQBZNTYZ6V44R4SO","short_pith_number":"pith:CZWOASSN","schema_version":"1.0","canonical_sha256":"166ce04a4d88b300e5b3c67d5e723c93a2fe602bd6e21339455d62ceb28351df","source":{"kind":"arxiv","id":"2602.22962","version":2},"attestation_state":"computed","paper":{"title":"Scaling Laws of Global Weather Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandru Calotoiu, Langwen Huang, Torsten Hoefler, Yuejiang Yu","submitted_at":"2026-02-26T12:57:38Z","abstract_excerpt":"Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance (validation loss) and three key factors: model size ($N$), dataset size ($D$), and compute budget ($C$). Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior: increasing the training dataset by 10x reduces validation loss by up to 3.2x. GraphCast demonstrates the highest parameter efficiency, yet suffers from limited hardwar"},"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":"2602.22962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T12:57:38Z","cross_cats_sorted":[],"title_canon_sha256":"40e6b013aa27b3ecc9c03d4b7677476c298e490a6602d0f8d05074a32131866e","abstract_canon_sha256":"da6dce424a8120b54a50cebcc611e9eb40cea5ea19850d252e28d2bc5a5dcdce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:34.485894Z","signature_b64":"+kykAPzjPStGDf2LZpGrkgk4+hkqvxJeQlR4mutOqY+5H6YYIxBWq2jQbh4CmBthrg2len3DGp6BTIWfVuaxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"166ce04a4d88b300e5b3c67d5e723c93a2fe602bd6e21339455d62ceb28351df","last_reissued_at":"2026-06-11T01:10:34.485246Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:34.485246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Laws of Global Weather Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandru Calotoiu, Langwen Huang, Torsten Hoefler, Yuejiang Yu","submitted_at":"2026-02-26T12:57:38Z","abstract_excerpt":"Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance (validation loss) and three key factors: model size ($N$), dataset size ($D$), and compute budget ($C$). Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior: increasing the training dataset by 10x reduces validation loss by up to 3.2x. GraphCast demonstrates the highest parameter efficiency, yet suffers from limited hardwar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22962","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/2602.22962/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":"2602.22962","created_at":"2026-06-11T01:10:34.485341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22962v2","created_at":"2026-06-11T01:10:34.485341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22962","created_at":"2026-06-11T01:10:34.485341+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZWOASSNRCZQ","created_at":"2026-06-11T01:10:34.485341+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZWOASSNRCZQBZNT","created_at":"2026-06-11T01:10:34.485341+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZWOASSN","created_at":"2026-06-11T01:10:34.485341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.00850","citing_title":"Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO","json":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO.json","graph_json":"https://pith.science/api/pith-number/CZWOASSNRCZQBZNTYZ6V44R4SO/graph.json","events_json":"https://pith.science/api/pith-number/CZWOASSNRCZQBZNTYZ6V44R4SO/events.json","paper":"https://pith.science/paper/CZWOASSN"},"agent_actions":{"view_html":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO","download_json":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO.json","view_paper":"https://pith.science/paper/CZWOASSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22962&json=true","fetch_graph":"https://pith.science/api/pith-number/CZWOASSNRCZQBZNTYZ6V44R4SO/graph.json","fetch_events":"https://pith.science/api/pith-number/CZWOASSNRCZQBZNTYZ6V44R4SO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO/action/storage_attestation","attest_author":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO/action/author_attestation","sign_citation":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO/action/citation_signature","submit_replication":"https://pith.science/pith/CZWOASSNRCZQBZNTYZ6V44R4SO/action/replication_record"}},"created_at":"2026-06-11T01:10:34.485341+00:00","updated_at":"2026-06-11T01:10:34.485341+00:00"}