{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MVM4X5OXRN3O33EFVJXK6V47R7","short_pith_number":"pith:MVM4X5OX","schema_version":"1.0","canonical_sha256":"6559cbf5d78b76edec85aa6eaf579f8fc29671e68ef34560442aae39b12bc832","source":{"kind":"arxiv","id":"2504.20238","version":2},"attestation_state":"computed","paper":{"title":"Atmospheric Predictability Beyond 30 Days with Machine Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Gregory J. Hakim, P. Trent Vonich","submitted_at":"2025-04-28T20:18:57Z","abstract_excerpt":"Atmospheric predictability research has long held that rapid error growth at small spatial scales imposes an intrinsic limit of roughly two weeks on deterministic weather forecast skill. We challenge this limit using GraphCast, a machine-learning weather model, by optimizing initial conditions for twice-daily forecasts spanning 2020. This approach yields an average error reduction of 86% at ten days relative to control forecasts from reanalysis initial conditions, with skill lasting beyond 30 days. Mean optimal initial-condition perturbations reveal large-scale, spatially coherent corrections "},"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":"2504.20238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"physics.ao-ph","submitted_at":"2025-04-28T20:18:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b6c5be45c5facad67693102e5c5134f41182653171cdb5732104da5a7240c3d","abstract_canon_sha256":"01589d79443d6ee2f6803f9ddb4d912b5f12ebb020ccffc8bd9fba33cda253a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:14.531310Z","signature_b64":"ZEmCyoXhbR2siejhNX5841CTYEBGpv062w5zYyXXF92OWin2os3+SNRE4VU0clWor2NUXjoY9C3h7XbLk6DHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6559cbf5d78b76edec85aa6eaf579f8fc29671e68ef34560442aae39b12bc832","last_reissued_at":"2026-06-02T01:04:14.530847Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:14.530847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Atmospheric Predictability Beyond 30 Days with Machine Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Gregory J. Hakim, P. Trent Vonich","submitted_at":"2025-04-28T20:18:57Z","abstract_excerpt":"Atmospheric predictability research has long held that rapid error growth at small spatial scales imposes an intrinsic limit of roughly two weeks on deterministic weather forecast skill. We challenge this limit using GraphCast, a machine-learning weather model, by optimizing initial conditions for twice-daily forecasts spanning 2020. This approach yields an average error reduction of 86% at ten days relative to control forecasts from reanalysis initial conditions, with skill lasting beyond 30 days. Mean optimal initial-condition perturbations reveal large-scale, spatially coherent corrections "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20238","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/2504.20238/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":"2504.20238","created_at":"2026-06-02T01:04:14.530897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20238v2","created_at":"2026-06-02T01:04:14.530897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20238","created_at":"2026-06-02T01:04:14.530897+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVM4X5OXRN3O","created_at":"2026-06-02T01:04:14.530897+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVM4X5OXRN3O33EF","created_at":"2026-06-02T01:04:14.530897+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVM4X5OX","created_at":"2026-06-02T01:04:14.530897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.19642","citing_title":"Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction","ref_index":104,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7","json":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7.json","graph_json":"https://pith.science/api/pith-number/MVM4X5OXRN3O33EFVJXK6V47R7/graph.json","events_json":"https://pith.science/api/pith-number/MVM4X5OXRN3O33EFVJXK6V47R7/events.json","paper":"https://pith.science/paper/MVM4X5OX"},"agent_actions":{"view_html":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7","download_json":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7.json","view_paper":"https://pith.science/paper/MVM4X5OX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20238&json=true","fetch_graph":"https://pith.science/api/pith-number/MVM4X5OXRN3O33EFVJXK6V47R7/graph.json","fetch_events":"https://pith.science/api/pith-number/MVM4X5OXRN3O33EFVJXK6V47R7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7/action/storage_attestation","attest_author":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7/action/author_attestation","sign_citation":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7/action/citation_signature","submit_replication":"https://pith.science/pith/MVM4X5OXRN3O33EFVJXK6V47R7/action/replication_record"}},"created_at":"2026-06-02T01:04:14.530897+00:00","updated_at":"2026-06-02T01:04:14.530897+00:00"}