{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FK2RKBBYVZUMSB2MVEK3FOUR3U","short_pith_number":"pith:FK2RKBBY","schema_version":"1.0","canonical_sha256":"2ab5150438ae68c9074ca915b2ba91dd26c065ff66e680984aaeb6ed86732833","source":{"kind":"arxiv","id":"2605.08856","version":2},"attestation_state":"computed","paper":{"title":"Controlling Transient Amplification Improves Long-horizon Rollouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Non-normal and non-commuting Jacobians along rollout trajectories cause transient error amplification and long-horizon drift even in asymptotically stable systems.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adeel Pervez, Francesco Locatello","submitted_at":"2026-05-09T10:10:30Z","abstract_excerpt":"Autoregressive neural simulators now match classical solvers on short-horizon prediction of physical systems, yet their accuracy degrades rapidly when rolled out over long horizons. In this work, we identify transient amplification of perturbations around rollout trajectories as a structural mechanism driving rollout error. Using a linearization analysis we show that when the Jacobians along an autoregressive trajectory are non-normal and non-commuting, the model amplifies errors transiently, resulting in model rollout drift even when the overall system is asymptotically stable. Building on 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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.08856","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T10:10:30Z","cross_cats_sorted":[],"title_canon_sha256":"03db4647a4caf3d713ac4708a8abadde9e18a50646889debcbcbf7f3d1ad5a2d","abstract_canon_sha256":"4122739a2724eb2707243a1d70603b8bf4b7c7fb7659711fb4ee3cb2fab6ed29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:41.641954Z","signature_b64":"ot1auNTlgsbP3lzRkVdSux7ylxHch6wkxzePMCVxipKo3yXvjTKvcT2f8mZ9892OB4j0/97cDqIjdt/HdpuwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ab5150438ae68c9074ca915b2ba91dd26c065ff66e680984aaeb6ed86732833","last_reissued_at":"2026-05-20T00:00:41.641197Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:41.641197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Transient Amplification Improves Long-horizon Rollouts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Non-normal and non-commuting Jacobians along rollout trajectories cause transient error amplification and long-horizon drift even in asymptotically stable systems.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adeel Pervez, Francesco Locatello","submitted_at":"2026-05-09T10:10:30Z","abstract_excerpt":"Autoregressive neural simulators now match classical solvers on short-horizon prediction of physical systems, yet their accuracy degrades rapidly when rolled out over long horizons. In this work, we identify transient amplification of perturbations around rollout trajectories as a structural mechanism driving rollout error. Using a linearization analysis we show that when the Jacobians along an autoregressive trajectory are non-normal and non-commuting, the model amplifies errors transiently, resulting in model rollout drift even when the overall system is asymptotically stable. Building on th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When Jacobians along an autoregressive trajectory are non-normal and non-commuting, the model amplifies errors transiently, resulting in rollout drift even when the overall system is asymptotically stable; commutativity regularization reduces this amplification and enables successful long-horizon rollouts over thousands of steps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The linearization analysis around rollout trajectories captures the dominant source of long-horizon error, and the two proposed penalties can be tuned to reduce normality defect and commutator norm without introducing new instabilities or degrading short-horizon accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Non-normal and non-commuting Jacobians along rollout trajectories cause transient error amplification and long-horizon drift even in asymptotically stable systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"15393305ba45e6f2631f8b1d1c74647f45c44093ae117fc75608d75b15049aac"},"source":{"id":"2605.08856","kind":"arxiv","version":2},"verdict":{"id":"31b79906-79d3-46f3-865d-5b6666e992be","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:39:39.855830Z","strongest_claim":"When Jacobians along an autoregressive trajectory are non-normal and non-commuting, the model amplifies errors transiently, resulting in rollout drift even when the overall system is asymptotically stable; commutativity regularization reduces this amplification and enables successful long-horizon rollouts over thousands of steps.","one_line_summary":"Commutativity regularization mitigates transient error amplification in autoregressive neural simulators by penalizing non-normality and non-commutativity of Jacobians, yielding stable long-horizon rollouts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The linearization analysis around rollout trajectories captures the dominant source of long-horizon error, and the two proposed penalties can be tuned to reduce normality defect and commutator norm without introducing new instabilities or degrading short-horizon accuracy.","pith_extraction_headline":"Non-normal and non-commuting Jacobians along rollout trajectories cause transient error amplification and long-horizon drift even in asymptotically stable systems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08856/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:44.975825Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:21.685923Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:42:26.659571Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"62e724dfd9d71b526be8f3ae2d60fb0d9691bf74262f34d8447e717e47833f94"},"references":{"count":21,"sample":[{"doi":"","year":1999,"title":"URLhttps://openreview.net/forum?id=MKP1g8wU0P. H. Hersbach, B. Bell, P. Berrisford, S. Hirahara, A. Horányi, J. Muñoz-Sabater, J. Nicolas, C. Peubey, R. Radu, D. Schepers, A. Simmons, C. Soci, S. Abda","work_id":"84276261-9515-4224-b79a-231761f749d7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/qj.3803","year":null,"title":"URLhttps://rmets.onlinelibrary","work_id":"e8d7a404-9f91-4f76-95f8-6949c6500cfa","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.neunet.2026.108641","year":2026,"title":"15 Controlling Transient Amplification Improves Long-horizon Rollouts doi: https://doi.org/10.1016/j.neunet.2026.108641","work_id":"21318679-1824-4bf5-8e62-8abbb66d018f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1007/bf01957346","year":null,"title":"doi: 10.1007/BF01957346. R. Lam, A. Sanchez-Gonzalez, M. Willson, P. Wirnsberger, M. Fortunato, F. Alet, S. Ravuri, T. Ewalds, Z. Eaton-Rosen, W. Hu, A. Merose, S. Hoyer, G. Holland, O. Vinyals, J. St","work_id":"0f97b4ea-82af-417b-aebb-f0f4d4fc3d14","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1126/science.adi2336","year":null,"title":"Learning skillful medium-range global weather forecasting","work_id":"5d68d02c-56fb-4a90-8d79-a0aff0e3d717","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"b51a01197a0979b06c3c87e294bcb62d87b4ac64ccef4a203b6d9da454b33ed7","internal_anchors":2},"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":"2605.08856","created_at":"2026-05-20T00:00:41.641301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08856v2","created_at":"2026-05-20T00:00:41.641301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08856","created_at":"2026-05-20T00:00:41.641301+00:00"},{"alias_kind":"pith_short_12","alias_value":"FK2RKBBYVZUM","created_at":"2026-05-20T00:00:41.641301+00:00"},{"alias_kind":"pith_short_16","alias_value":"FK2RKBBYVZUMSB2M","created_at":"2026-05-20T00:00:41.641301+00:00"},{"alias_kind":"pith_short_8","alias_value":"FK2RKBBY","created_at":"2026-05-20T00:00:41.641301+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/FK2RKBBYVZUMSB2MVEK3FOUR3U","json":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U.json","graph_json":"https://pith.science/api/pith-number/FK2RKBBYVZUMSB2MVEK3FOUR3U/graph.json","events_json":"https://pith.science/api/pith-number/FK2RKBBYVZUMSB2MVEK3FOUR3U/events.json","paper":"https://pith.science/paper/FK2RKBBY"},"agent_actions":{"view_html":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U","download_json":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U.json","view_paper":"https://pith.science/paper/FK2RKBBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08856&json=true","fetch_graph":"https://pith.science/api/pith-number/FK2RKBBYVZUMSB2MVEK3FOUR3U/graph.json","fetch_events":"https://pith.science/api/pith-number/FK2RKBBYVZUMSB2MVEK3FOUR3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U/action/storage_attestation","attest_author":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U/action/author_attestation","sign_citation":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U/action/citation_signature","submit_replication":"https://pith.science/pith/FK2RKBBYVZUMSB2MVEK3FOUR3U/action/replication_record"}},"created_at":"2026-05-20T00:00:41.641301+00:00","updated_at":"2026-05-20T00:00:41.641301+00:00"}