{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W3WGEISOJW72ILFJQIIEN5PP4A","short_pith_number":"pith:W3WGEISO","schema_version":"1.0","canonical_sha256":"b6ec62224e4dbfa42ca9821046f5efe02b906e91b44cfcc94a3ec6f7c4b0907b","source":{"kind":"arxiv","id":"2501.19374","version":2},"attestation_state":"computed","paper":{"title":"Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Christopher Subich, Jing Yang, Leo Separovic, Syed Zahid Husain","submitted_at":"2025-01-31T18:23:45Z","abstract_excerpt":"Recent advancements in data-driven weather forecasting models have delivered deterministic models that outperform the leading operational forecast systems based on traditional, physics-based models. However, these data-driven models are typically trained with a mean squared error loss function, which causes smoothing of fine scales through a \"double penalty\" effect. We develop a simple, parameter-free modification to this loss function that avoids this problem by separating the loss attributable to decorrelation from the loss attributable to spectral amplitude errors. Fine-tuning the GraphCast"},"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":"2501.19374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T18:23:45Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"94dbdecb50000b69aa93dbb41eea348ffec9239c3d44fe7eb77c59d97894ecff","abstract_canon_sha256":"306e4dd30a8280304bdad8be6e837595e59c3803585780500ab830252029cc78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:25.123066Z","signature_b64":"/cz5tsMT0HdSQfCuTgOpGT8IvtV9qOVYuw8OoKZfEBv1h7KYoKwkfWQaM/J6m5yAQl68CmQIQfMWbf9z4a1PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6ec62224e4dbfa42ca9821046f5efe02b906e91b44cfcc94a3ec6f7c4b0907b","last_reissued_at":"2026-07-05T11:12:25.122485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:25.122485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Christopher Subich, Jing Yang, Leo Separovic, Syed Zahid Husain","submitted_at":"2025-01-31T18:23:45Z","abstract_excerpt":"Recent advancements in data-driven weather forecasting models have delivered deterministic models that outperform the leading operational forecast systems based on traditional, physics-based models. However, these data-driven models are typically trained with a mean squared error loss function, which causes smoothing of fine scales through a \"double penalty\" effect. We develop a simple, parameter-free modification to this loss function that avoids this problem by separating the loss attributable to decorrelation from the loss attributable to spectral amplitude errors. Fine-tuning the GraphCast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19374","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/2501.19374/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":"2501.19374","created_at":"2026-07-05T11:12:25.122557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19374v2","created_at":"2026-07-05T11:12:25.122557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19374","created_at":"2026-07-05T11:12:25.122557+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3WGEISOJW72","created_at":"2026-07-05T11:12:25.122557+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3WGEISOJW72ILFJ","created_at":"2026-07-05T11:12:25.122557+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3WGEISO","created_at":"2026-07-05T11:12:25.122557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10642","citing_title":"PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29172","citing_title":"CORDEX-ML-Bench: A Benchmark for Data-Driven Regional Climate Downscaling -Experiment Design and Overview","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19642","citing_title":"Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20925","citing_title":"Blending machine learning and physics-based approaches for weather and climate: a typology","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08663","citing_title":"Efficient Parameter Calibration of Numerical Weather Prediction Models via Evolutionary Sequential Transfer Optimization","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A","json":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A.json","graph_json":"https://pith.science/api/pith-number/W3WGEISOJW72ILFJQIIEN5PP4A/graph.json","events_json":"https://pith.science/api/pith-number/W3WGEISOJW72ILFJQIIEN5PP4A/events.json","paper":"https://pith.science/paper/W3WGEISO"},"agent_actions":{"view_html":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A","download_json":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A.json","view_paper":"https://pith.science/paper/W3WGEISO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19374&json=true","fetch_graph":"https://pith.science/api/pith-number/W3WGEISOJW72ILFJQIIEN5PP4A/graph.json","fetch_events":"https://pith.science/api/pith-number/W3WGEISOJW72ILFJQIIEN5PP4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A/action/storage_attestation","attest_author":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A/action/author_attestation","sign_citation":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A/action/citation_signature","submit_replication":"https://pith.science/pith/W3WGEISOJW72ILFJQIIEN5PP4A/action/replication_record"}},"created_at":"2026-07-05T11:12:25.122557+00:00","updated_at":"2026-07-05T11:12:25.122557+00:00"}