{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LY3R7264EDWHALA54KLFHMIDID","short_pith_number":"pith:LY3R7264","schema_version":"1.0","canonical_sha256":"5e371febdc20ec702c1de29653b10340d2701b75bafd6cd0c18c8c83576f36c1","source":{"kind":"arxiv","id":"2402.01295","version":4},"attestation_state":"computed","paper":{"title":"ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Kang Chen, Lei Bai, Tao Han, Wanghan Xu, Wanli Ouyang","submitted_at":"2024-02-02T10:34:13Z","abstract_excerpt":"Data-driven weather forecast based on machine learning (ML) has experienced rapid development and demonstrated superior performance in the global medium-range forecast compared to traditional physics-based dynamical models. However, most of these ML models struggle with accurately predicting extreme weather, which is related to training loss and the uncertainty of weather systems. Through mathematical analysis, we prove that the use of symmetric losses, such as the Mean Squared Error (MSE), leads to biased predictions and underestimation of extreme values. To address this issue, we introduce E"},"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":"2402.01295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T10:34:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7eea1c6fd90b2e24b08ab1507241c026de77ff8a7b56d723e001bbf52722849e","abstract_canon_sha256":"96e54fe93d529f9da0e54770a34feaa7a76422f65d1242b261e900314a587448"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:03.316389Z","signature_b64":"gnQqzsxaTbevGNBix2j54GZCTEd5EpWLxmR0XKR9snIyB7r9d086+K7UySa1dt0Cnns4OUoKYj925cJtZTF+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e371febdc20ec702c1de29653b10340d2701b75bafd6cd0c18c8c83576f36c1","last_reissued_at":"2026-07-05T08:56:03.315937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:03.315937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hao Chen, Kang Chen, Lei Bai, Tao Han, Wanghan Xu, Wanli Ouyang","submitted_at":"2024-02-02T10:34:13Z","abstract_excerpt":"Data-driven weather forecast based on machine learning (ML) has experienced rapid development and demonstrated superior performance in the global medium-range forecast compared to traditional physics-based dynamical models. However, most of these ML models struggle with accurately predicting extreme weather, which is related to training loss and the uncertainty of weather systems. Through mathematical analysis, we prove that the use of symmetric losses, such as the Mean Squared Error (MSE), leads to biased predictions and underestimation of extreme values. To address this issue, we introduce E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01295","kind":"arxiv","version":4},"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/2402.01295/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":"2402.01295","created_at":"2026-07-05T08:56:03.315998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01295v4","created_at":"2026-07-05T08:56:03.315998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01295","created_at":"2026-07-05T08:56:03.315998+00:00"},{"alias_kind":"pith_short_12","alias_value":"LY3R7264EDWH","created_at":"2026-07-05T08:56:03.315998+00:00"},{"alias_kind":"pith_short_16","alias_value":"LY3R7264EDWHALA5","created_at":"2026-07-05T08:56:03.315998+00:00"},{"alias_kind":"pith_short_8","alias_value":"LY3R7264","created_at":"2026-07-05T08:56:03.315998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24945","citing_title":"RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07928","citing_title":"Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID","json":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID.json","graph_json":"https://pith.science/api/pith-number/LY3R7264EDWHALA54KLFHMIDID/graph.json","events_json":"https://pith.science/api/pith-number/LY3R7264EDWHALA54KLFHMIDID/events.json","paper":"https://pith.science/paper/LY3R7264"},"agent_actions":{"view_html":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID","download_json":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID.json","view_paper":"https://pith.science/paper/LY3R7264","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01295&json=true","fetch_graph":"https://pith.science/api/pith-number/LY3R7264EDWHALA54KLFHMIDID/graph.json","fetch_events":"https://pith.science/api/pith-number/LY3R7264EDWHALA54KLFHMIDID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID/action/storage_attestation","attest_author":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID/action/author_attestation","sign_citation":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID/action/citation_signature","submit_replication":"https://pith.science/pith/LY3R7264EDWHALA54KLFHMIDID/action/replication_record"}},"created_at":"2026-07-05T08:56:03.315998+00:00","updated_at":"2026-07-05T08:56:03.315998+00:00"}