{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JB5XB7ROXKVPCEYZFV6EWERRQM","short_pith_number":"pith:JB5XB7RO","schema_version":"1.0","canonical_sha256":"487b70fe2ebaaaf113192d7c4b1231830420e53b672eb68f579c83aa907a0d64","source":{"kind":"arxiv","id":"2503.23953","version":1},"attestation_state":"computed","paper":{"title":"Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ao-ph","authors_text":"Adam A. Scaife, Chris Kent, Doug Smith, Nick J. Dunstone, Oliver Watt-Meyer, Steven C. Hardiman, Tom Dunstan","submitted_at":"2025-03-31T11:11:16Z","abstract_excerpt":"Machine learning weather models trained on observed atmospheric conditions can outperform conventional physics-based models at short- to medium-range (1-14 day) forecast timescales. Here we take the machine learning weather model ACE2, trained to predict 6-hourly steps in atmospheric evolution and which can remain stable over long forecast periods, and assess it from a seasonal forecasting perspective. Applying persisted sea surface temperature (SST) and sea-ice anomalies centred on 1st November each year, we initialise a lagged ensemble of winter predictions covering 1993/1994 to 2015/2016. O"},"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":"2503.23953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"physics.ao-ph","submitted_at":"2025-03-31T11:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"5a5bad7a47c0df050d4d3f99c51492113132fb377bbdbacd3f1cb2ed8349e23c","abstract_canon_sha256":"230e810e72f8ceea101df9fda35630ed8147493a33ae8392ca921f88b4fdf123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:02.428528Z","signature_b64":"rRTJO7INZbXsX3S/2FmdpT7MEezIYhZk/KIEZOy9VhDCNwCTs/CP8WknzvguHWAbOBbMjb4aEj9lHUzOpoGmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"487b70fe2ebaaaf113192d7c4b1231830420e53b672eb68f579c83aa907a0d64","last_reissued_at":"2026-07-05T10:42:02.427985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:02.427985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skilful global seasonal predictions from a machine learning weather model trained on reanalysis data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ao-ph","authors_text":"Adam A. Scaife, Chris Kent, Doug Smith, Nick J. Dunstone, Oliver Watt-Meyer, Steven C. Hardiman, Tom Dunstan","submitted_at":"2025-03-31T11:11:16Z","abstract_excerpt":"Machine learning weather models trained on observed atmospheric conditions can outperform conventional physics-based models at short- to medium-range (1-14 day) forecast timescales. Here we take the machine learning weather model ACE2, trained to predict 6-hourly steps in atmospheric evolution and which can remain stable over long forecast periods, and assess it from a seasonal forecasting perspective. Applying persisted sea surface temperature (SST) and sea-ice anomalies centred on 1st November each year, we initialise a lagged ensemble of winter predictions covering 1993/1994 to 2015/2016. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23953","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/2503.23953/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":"2503.23953","created_at":"2026-07-05T10:42:02.428043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23953v1","created_at":"2026-07-05T10:42:02.428043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23953","created_at":"2026-07-05T10:42:02.428043+00:00"},{"alias_kind":"pith_short_12","alias_value":"JB5XB7ROXKVP","created_at":"2026-07-05T10:42:02.428043+00:00"},{"alias_kind":"pith_short_16","alias_value":"JB5XB7ROXKVPCEYZ","created_at":"2026-07-05T10:42:02.428043+00:00"},{"alias_kind":"pith_short_8","alias_value":"JB5XB7RO","created_at":"2026-07-05T10:42:02.428043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02061","citing_title":"LUCIE-3D: A three-dimensional climate emulator for forced responses","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM","json":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM.json","graph_json":"https://pith.science/api/pith-number/JB5XB7ROXKVPCEYZFV6EWERRQM/graph.json","events_json":"https://pith.science/api/pith-number/JB5XB7ROXKVPCEYZFV6EWERRQM/events.json","paper":"https://pith.science/paper/JB5XB7RO"},"agent_actions":{"view_html":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM","download_json":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM.json","view_paper":"https://pith.science/paper/JB5XB7RO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23953&json=true","fetch_graph":"https://pith.science/api/pith-number/JB5XB7ROXKVPCEYZFV6EWERRQM/graph.json","fetch_events":"https://pith.science/api/pith-number/JB5XB7ROXKVPCEYZFV6EWERRQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM/action/storage_attestation","attest_author":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM/action/author_attestation","sign_citation":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM/action/citation_signature","submit_replication":"https://pith.science/pith/JB5XB7ROXKVPCEYZFV6EWERRQM/action/replication_record"}},"created_at":"2026-07-05T10:42:02.428043+00:00","updated_at":"2026-07-05T10:42:02.428043+00:00"}