{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZT2E3EQDYUFA5WIHSQ7S26OX5L","short_pith_number":"pith:ZT2E3EQD","schema_version":"1.0","canonical_sha256":"ccf44d9203c50a0ed907943f2d79d7eaca0be0fc7a36f97f3f78529b9f3c9feb","source":{"kind":"arxiv","id":"2605.24945","version":1},"attestation_state":"computed","paper":{"title":"RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Fenghua Ling, Hao Chen, Lei Bai, Ruize Li, Song Guo, Tao Han, Wei Zhang, Zhibin Wen","submitted_at":"2026-05-24T08:46:17Z","abstract_excerpt":"Accurate evaluation of weather forecasting models is critical for their reliable deployment in real-world applications. However, existing benchmarks predominantly rely on reanalysis products such as ERA5, which are generated through delayed data assimilation and do not reflect the constraints of real-time operational forecasting, thereby resulting in a systematic mismatch between benchmark performance and real-world forecasting. In this work, we introduce RealBench, a next-generation benchmark for AI weather forecasting that emphasizes realistic evaluation under operational conditions. RealBen"},"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":"2605.24945","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T08:46:17Z","cross_cats_sorted":["cs.AI","physics.ao-ph"],"title_canon_sha256":"bee403d44f134c69a6d0d873c0893f2cab9b350d79bd7a30b57150d98eb9b3cb","abstract_canon_sha256":"83e510e2b99f0a87d4b5b14861163756c75cd3fb138b5ec80d5305459b60e5c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:07.048551Z","signature_b64":"Chy5AcVEv7Kuc+Ng0N30jtouXLWK1A7RogD0FaIwVk5HCiI0n4VqPdoUkyLwj3tKSsaZhTAlAO+yHzEz6tG8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccf44d9203c50a0ed907943f2d79d7eaca0be0fc7a36f97f3f78529b9f3c9feb","last_reissued_at":"2026-05-26T01:04:07.047966Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:07.047966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Fenghua Ling, Hao Chen, Lei Bai, Ruize Li, Song Guo, Tao Han, Wei Zhang, Zhibin Wen","submitted_at":"2026-05-24T08:46:17Z","abstract_excerpt":"Accurate evaluation of weather forecasting models is critical for their reliable deployment in real-world applications. However, existing benchmarks predominantly rely on reanalysis products such as ERA5, which are generated through delayed data assimilation and do not reflect the constraints of real-time operational forecasting, thereby resulting in a systematic mismatch between benchmark performance and real-world forecasting. In this work, we introduce RealBench, a next-generation benchmark for AI weather forecasting that emphasizes realistic evaluation under operational conditions. RealBen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24945","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/2605.24945/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":"2605.24945","created_at":"2026-05-26T01:04:07.048075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24945v1","created_at":"2026-05-26T01:04:07.048075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24945","created_at":"2026-05-26T01:04:07.048075+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZT2E3EQDYUFA","created_at":"2026-05-26T01:04:07.048075+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZT2E3EQDYUFA5WIH","created_at":"2026-05-26T01:04:07.048075+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZT2E3EQD","created_at":"2026-05-26T01:04:07.048075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L","json":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L.json","graph_json":"https://pith.science/api/pith-number/ZT2E3EQDYUFA5WIHSQ7S26OX5L/graph.json","events_json":"https://pith.science/api/pith-number/ZT2E3EQDYUFA5WIHSQ7S26OX5L/events.json","paper":"https://pith.science/paper/ZT2E3EQD"},"agent_actions":{"view_html":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L","download_json":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L.json","view_paper":"https://pith.science/paper/ZT2E3EQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24945&json=true","fetch_graph":"https://pith.science/api/pith-number/ZT2E3EQDYUFA5WIHSQ7S26OX5L/graph.json","fetch_events":"https://pith.science/api/pith-number/ZT2E3EQDYUFA5WIHSQ7S26OX5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L/action/storage_attestation","attest_author":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L/action/author_attestation","sign_citation":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L/action/citation_signature","submit_replication":"https://pith.science/pith/ZT2E3EQDYUFA5WIHSQ7S26OX5L/action/replication_record"}},"created_at":"2026-05-26T01:04:07.048075+00:00","updated_at":"2026-05-26T01:04:07.048075+00:00"}