{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZFXZO6DWQUYNL7ZIY6GIXINEQ4","short_pith_number":"pith:ZFXZO6DW","schema_version":"1.0","canonical_sha256":"c96f9778768530d5ff28c78c8ba1a48731e5e132f6b53bceb26e8434c9f562ce","source":{"kind":"arxiv","id":"2509.03816","version":1},"attestation_state":"computed","paper":{"title":"Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Aditi Sheshadri, Aman Gupta, Johannes Schmude, Manil Maskey, Rahul Ramachandran, Sujit Roy, Vishal Gaur, Wei Ji Leong","submitted_at":"2025-09-04T02:05:54Z","abstract_excerpt":"Global climate models parameterize a range of atmospheric-oceanic processes like gravity waves, clouds, moist convection, and turbulence that cannot be sufficiently resolved. These subgrid-scale closures for unresolved processes are a leading source of model uncertainty. Here, we present a new approach to developing machine learning parameterizations of small-scale climate processes by fine-tuning a pre-trained AI foundation model (FM). FMs are largely unexplored in climate research. A pre-trained encoder-decoder from a 2.3 billion parameter FM (NASA and IBM Research's Prithvi WxC) -- which co"},"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":"2509.03816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"physics.ao-ph","submitted_at":"2025-09-04T02:05:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53142d4d57269f9ab2cd902eedc751b8735e9dad7c3c3ea9acb9f3d59756cef6","abstract_canon_sha256":"01a8b248bc6e08ad03e87a2d31fa273e803417937439531c9199b7a03f9913fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:47.045544Z","signature_b64":"76udHMKDKIFUL2xl9t8Y8pGHwnKVejoERq+m8Br/TfmNL9wHAKW/t+rqBP4trNub9YZgKf0QiixzFq5zElfQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c96f9778768530d5ff28c78c8ba1a48731e5e132f6b53bceb26e8434c9f562ce","last_reissued_at":"2026-07-05T12:04:47.045035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:47.045035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finetuning AI Foundation Models to Develop Subgrid-Scale Parameterizations: A Case Study on Atmospheric Gravity Waves","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.ao-ph","authors_text":"Aditi Sheshadri, Aman Gupta, Johannes Schmude, Manil Maskey, Rahul Ramachandran, Sujit Roy, Vishal Gaur, Wei Ji Leong","submitted_at":"2025-09-04T02:05:54Z","abstract_excerpt":"Global climate models parameterize a range of atmospheric-oceanic processes like gravity waves, clouds, moist convection, and turbulence that cannot be sufficiently resolved. These subgrid-scale closures for unresolved processes are a leading source of model uncertainty. Here, we present a new approach to developing machine learning parameterizations of small-scale climate processes by fine-tuning a pre-trained AI foundation model (FM). FMs are largely unexplored in climate research. A pre-trained encoder-decoder from a 2.3 billion parameter FM (NASA and IBM Research's Prithvi WxC) -- which co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03816","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/2509.03816/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":"2509.03816","created_at":"2026-07-05T12:04:47.045094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03816v1","created_at":"2026-07-05T12:04:47.045094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03816","created_at":"2026-07-05T12:04:47.045094+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFXZO6DWQUYN","created_at":"2026-07-05T12:04:47.045094+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFXZO6DWQUYNL7ZI","created_at":"2026-07-05T12:04:47.045094+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFXZO6DW","created_at":"2026-07-05T12:04:47.045094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05052","citing_title":"Interpretable Neural Networks to Predict Momentum Fluxes of Orographic Gravity Waves","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4","json":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4.json","graph_json":"https://pith.science/api/pith-number/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/graph.json","events_json":"https://pith.science/api/pith-number/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/events.json","paper":"https://pith.science/paper/ZFXZO6DW"},"agent_actions":{"view_html":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4","download_json":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4.json","view_paper":"https://pith.science/paper/ZFXZO6DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03816&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/action/storage_attestation","attest_author":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/action/author_attestation","sign_citation":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/action/citation_signature","submit_replication":"https://pith.science/pith/ZFXZO6DWQUYNL7ZIY6GIXINEQ4/action/replication_record"}},"created_at":"2026-07-05T12:04:47.045094+00:00","updated_at":"2026-07-05T12:04:47.045094+00:00"}