{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BGOTD7I472AHM3KCJLPTDS2QAN","short_pith_number":"pith:BGOTD7I4","schema_version":"1.0","canonical_sha256":"099d31fd1cfe80766d424adf31cb50036eb61a54222ee2e50e5512c1ebfb9082","source":{"kind":"arxiv","id":"2606.19302","version":1},"attestation_state":"computed","paper":{"title":"Optimal scenario design for climate emulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Andrei Sokolov, Christopher B. Womack, Glenn Flierl, Noelle E. Selin, Popat Salunke, Sebastian D. Eastham, Shahine Bouabid","submitted_at":"2026-06-17T17:26:22Z","abstract_excerpt":"As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training datasets themselves can be optimized to improve generalization. We introduce a method to create datasets that produce emulators capable of generalizing to new, struct"},"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":"2606.19302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.ao-ph","submitted_at":"2026-06-17T17:26:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"695694bb1dc1bd893d90b3d5d2b02b5aec0456c483eb88ee7c7e3cb05a4699cf","abstract_canon_sha256":"2f50a84d51aa8e8fa3148a68ea662c52a5f705d30a1a00f0b4eb6fa1f4834142"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:10.469940Z","signature_b64":"U4Xp2+fL7x39iLurnvEZF83BJaYyq3jbDUkrb2eKTgU4zcMeOujYOkscxEw1vACnVpTQifMEwwZlHugg1Q1bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099d31fd1cfe80766d424adf31cb50036eb61a54222ee2e50e5512c1ebfb9082","last_reissued_at":"2026-06-19T16:12:10.469553Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:10.469553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal scenario design for climate emulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Andrei Sokolov, Christopher B. Womack, Glenn Flierl, Noelle E. Selin, Popat Salunke, Sebastian D. Eastham, Shahine Bouabid","submitted_at":"2026-06-17T17:26:22Z","abstract_excerpt":"As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), we show that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. Here, we examine whether training datasets themselves can be optimized to improve generalization. We introduce a method to create datasets that produce emulators capable of generalizing to new, struct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19302","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/2606.19302/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":"2606.19302","created_at":"2026-06-19T16:12:10.469617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19302v1","created_at":"2026-06-19T16:12:10.469617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19302","created_at":"2026-06-19T16:12:10.469617+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGOTD7I472AH","created_at":"2026-06-19T16:12:10.469617+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGOTD7I472AHM3KC","created_at":"2026-06-19T16:12:10.469617+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGOTD7I4","created_at":"2026-06-19T16:12:10.469617+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/BGOTD7I472AHM3KCJLPTDS2QAN","json":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN.json","graph_json":"https://pith.science/api/pith-number/BGOTD7I472AHM3KCJLPTDS2QAN/graph.json","events_json":"https://pith.science/api/pith-number/BGOTD7I472AHM3KCJLPTDS2QAN/events.json","paper":"https://pith.science/paper/BGOTD7I4"},"agent_actions":{"view_html":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN","download_json":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN.json","view_paper":"https://pith.science/paper/BGOTD7I4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19302&json=true","fetch_graph":"https://pith.science/api/pith-number/BGOTD7I472AHM3KCJLPTDS2QAN/graph.json","fetch_events":"https://pith.science/api/pith-number/BGOTD7I472AHM3KCJLPTDS2QAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN/action/storage_attestation","attest_author":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN/action/author_attestation","sign_citation":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN/action/citation_signature","submit_replication":"https://pith.science/pith/BGOTD7I472AHM3KCJLPTDS2QAN/action/replication_record"}},"created_at":"2026-06-19T16:12:10.469617+00:00","updated_at":"2026-06-19T16:12:10.469617+00:00"}