{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3IMDOLFPK4EDRWHPEUDR5JGBJO","short_pith_number":"pith:3IMDOLFP","schema_version":"1.0","canonical_sha256":"da18372caf570838d8ef25071ea4c14b98767c03d830063ce4403a9926f87e55","source":{"kind":"arxiv","id":"2605.30184","version":1},"attestation_state":"computed","paper":{"title":"Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Benedikt Soja, Fanny Lehmann, Firat Ozdemir, Sebastian Schemm, Siddhartha Mishra, Torsten Hoefler, Yun Cheng","submitted_at":"2026-05-28T16:29:33Z","abstract_excerpt":"While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined \"instabilities\" when rolled out over longer horizons. This work addresses the lack of a formal taxonomy by categorizing these failures into three distinct regimes: blow-up, drift, and loss of seasonality, through year-long rollouts of nine state-of-the-art AI weather models. Our analysis reveals that stability hinges on the treatment of small spatio-temporal scales: unstable models amplify high-frequency energy, while stable models act as denoisers when noise is added to th"},"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":"2605.30184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:29:33Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"358749697fcaa398c137633b6599b74c058b37cc5ad5c305870b0d86ad95522c","abstract_canon_sha256":"e70a617ef031495982496ae5e9d77bce7c7a257bc97a1915469b9a0b21109cfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:12.202532Z","signature_b64":"sZyocATCNb3YMnsvA9UtxUaZVR1JEQ9ut43S+7IZl/ffNPwx5TgCx4kX3/Y0TugA09G6MrsBRxGbX17taR8kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da18372caf570838d8ef25071ea4c14b98767c03d830063ce4403a9926f87e55","last_reissued_at":"2026-05-29T02:06:12.202144Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:12.202144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Benedikt Soja, Fanny Lehmann, Firat Ozdemir, Sebastian Schemm, Siddhartha Mishra, Torsten Hoefler, Yun Cheng","submitted_at":"2026-05-28T16:29:33Z","abstract_excerpt":"While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined \"instabilities\" when rolled out over longer horizons. This work addresses the lack of a formal taxonomy by categorizing these failures into three distinct regimes: blow-up, drift, and loss of seasonality, through year-long rollouts of nine state-of-the-art AI weather models. Our analysis reveals that stability hinges on the treatment of small spatio-temporal scales: unstable models amplify high-frequency energy, while stable models act as denoisers when noise is added to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30184","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/2605.30184/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":"2605.30184","created_at":"2026-05-29T02:06:12.202199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30184v1","created_at":"2026-05-29T02:06:12.202199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30184","created_at":"2026-05-29T02:06:12.202199+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IMDOLFPK4ED","created_at":"2026-05-29T02:06:12.202199+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IMDOLFPK4EDRWHP","created_at":"2026-05-29T02:06:12.202199+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IMDOLFP","created_at":"2026-05-29T02:06:12.202199+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/3IMDOLFPK4EDRWHPEUDR5JGBJO","json":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO.json","graph_json":"https://pith.science/api/pith-number/3IMDOLFPK4EDRWHPEUDR5JGBJO/graph.json","events_json":"https://pith.science/api/pith-number/3IMDOLFPK4EDRWHPEUDR5JGBJO/events.json","paper":"https://pith.science/paper/3IMDOLFP"},"agent_actions":{"view_html":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO","download_json":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO.json","view_paper":"https://pith.science/paper/3IMDOLFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30184&json=true","fetch_graph":"https://pith.science/api/pith-number/3IMDOLFPK4EDRWHPEUDR5JGBJO/graph.json","fetch_events":"https://pith.science/api/pith-number/3IMDOLFPK4EDRWHPEUDR5JGBJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO/action/storage_attestation","attest_author":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO/action/author_attestation","sign_citation":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO/action/citation_signature","submit_replication":"https://pith.science/pith/3IMDOLFPK4EDRWHPEUDR5JGBJO/action/replication_record"}},"created_at":"2026-05-29T02:06:12.202199+00:00","updated_at":"2026-05-29T02:06:12.202199+00:00"}