{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RODOZSWCGL5BZJRWTN4RWAXJKK","short_pith_number":"pith:RODOZSWC","schema_version":"1.0","canonical_sha256":"8b86eccac232fa1ca6369b791b02e952b5ff77b5e25dbe2c9309a5ca4445e3fd","source":{"kind":"arxiv","id":"2408.14587","version":2},"attestation_state":"computed","paper":{"title":"Efficient fine-tuning of 37-level GraphCast with the Canadian global deterministic analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Christopher Subich","submitted_at":"2024-08-26T19:16:08Z","abstract_excerpt":"This work describes a process for efficiently fine-tuning the GraphCast data-driven forecast model to simulate another analysis system, here the Global Deterministic Prediction System (GDPS) of Environment and Climate Change Canada (ECCC). Using two years of training data (July 2019 -- December 2021) and 37 GPU-days of computation to tune the 37-level, quarter-degree version of GraphCast, the resulting model significantly outperforms both the unmodified GraphCast and operational forecast, showing significant forecast skill in the troposphere over lead times from 1 to 10 days. This fine-tuning "},"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":"2408.14587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-26T19:16:08Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"ecf7fd1d33e18776601a7823e248e8a8e598aa69f2e2263f6dddcd73f6be096d","abstract_canon_sha256":"05e731c0395fcc448915e67e0f086f9730f2f2f2c001e1d0cbf0ae8c7eadc387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:00.367565Z","signature_b64":"cQPwDW43g6Z8a9zbfJNbaxCsMYb1J6J//rpBkmQXKPNsGGenl/+kklx8a6gg50zd5Cjme8TFVnoDrlgH/srOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b86eccac232fa1ca6369b791b02e952b5ff77b5e25dbe2c9309a5ca4445e3fd","last_reissued_at":"2026-07-05T11:52:00.367101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:00.367101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient fine-tuning of 37-level GraphCast with the Canadian global deterministic analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Christopher Subich","submitted_at":"2024-08-26T19:16:08Z","abstract_excerpt":"This work describes a process for efficiently fine-tuning the GraphCast data-driven forecast model to simulate another analysis system, here the Global Deterministic Prediction System (GDPS) of Environment and Climate Change Canada (ECCC). Using two years of training data (July 2019 -- December 2021) and 37 GPU-days of computation to tune the 37-level, quarter-degree version of GraphCast, the resulting model significantly outperforms both the unmodified GraphCast and operational forecast, showing significant forecast skill in the troposphere over lead times from 1 to 10 days. This fine-tuning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14587","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/2408.14587/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":"2408.14587","created_at":"2026-07-05T11:52:00.367158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14587v2","created_at":"2026-07-05T11:52:00.367158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14587","created_at":"2026-07-05T11:52:00.367158+00:00"},{"alias_kind":"pith_short_12","alias_value":"RODOZSWCGL5B","created_at":"2026-07-05T11:52:00.367158+00:00"},{"alias_kind":"pith_short_16","alias_value":"RODOZSWCGL5BZJRW","created_at":"2026-07-05T11:52:00.367158+00:00"},{"alias_kind":"pith_short_8","alias_value":"RODOZSWC","created_at":"2026-07-05T11:52:00.367158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19374","citing_title":"Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK","json":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK.json","graph_json":"https://pith.science/api/pith-number/RODOZSWCGL5BZJRWTN4RWAXJKK/graph.json","events_json":"https://pith.science/api/pith-number/RODOZSWCGL5BZJRWTN4RWAXJKK/events.json","paper":"https://pith.science/paper/RODOZSWC"},"agent_actions":{"view_html":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK","download_json":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK.json","view_paper":"https://pith.science/paper/RODOZSWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14587&json=true","fetch_graph":"https://pith.science/api/pith-number/RODOZSWCGL5BZJRWTN4RWAXJKK/graph.json","fetch_events":"https://pith.science/api/pith-number/RODOZSWCGL5BZJRWTN4RWAXJKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK/action/storage_attestation","attest_author":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK/action/author_attestation","sign_citation":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK/action/citation_signature","submit_replication":"https://pith.science/pith/RODOZSWCGL5BZJRWTN4RWAXJKK/action/replication_record"}},"created_at":"2026-07-05T11:52:00.367158+00:00","updated_at":"2026-07-05T11:52:00.367158+00:00"}