{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CY7IEZC2ZTEMLS3KJONM565DJS","short_pith_number":"pith:CY7IEZC2","schema_version":"1.0","canonical_sha256":"163e82645accc8c5cb6a4b9acefba34cbe9349a3d3f031ae44d94ea0c52e83f2","source":{"kind":"arxiv","id":"2607.20778","version":1},"attestation_state":"computed","paper":{"title":"Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Ivan Higuera-Mendieta, Jason Y. Hu, Makoto M. Kelp, Patrick Obin Sturm","submitted_at":"2026-07-22T23:00:02Z","abstract_excerpt":"Weather forecasting foundation models (FMs) are increasingly fine-tuned to predict air quality, offering fast global pollution forecasts at lower computational cost than conventional chemical transport models. These FMs are typically trained on reanalysis data and generate forecasts through autoregressive rollout. They do not explicitly represent governing physical or chemical processes. Therefore, high forecast skill does not reveal whether a model has learned physical mechanisms or exploits statistical regularities in its training data. Here, we present the first study of what a FM fine-tune"},"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":"2607.20778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T23:00:02Z","cross_cats_sorted":["physics.ao-ph"],"title_canon_sha256":"63f2396bb5dc9e384b11792cebe55a2186af0e5185615cb6ce9c926fb86657f1","abstract_canon_sha256":"cf6b930b15368611a5b9698df7a3056289d068d99bd44ce1cc8694f825798601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:34.214343Z","signature_b64":"YAtlSIWCCYpLrGARy9xSi1d0tNbF585eMkLW2PXgFMxCtPh3krfpSpVqABN5vw30vqb/rEa+MzH3eyaJCua/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163e82645accc8c5cb6a4b9acefba34cbe9349a3d3f031ae44d94ea0c52e83f2","last_reissued_at":"2026-07-24T00:23:34.213384Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:34.213384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Ivan Higuera-Mendieta, Jason Y. Hu, Makoto M. Kelp, Patrick Obin Sturm","submitted_at":"2026-07-22T23:00:02Z","abstract_excerpt":"Weather forecasting foundation models (FMs) are increasingly fine-tuned to predict air quality, offering fast global pollution forecasts at lower computational cost than conventional chemical transport models. These FMs are typically trained on reanalysis data and generate forecasts through autoregressive rollout. They do not explicitly represent governing physical or chemical processes. Therefore, high forecast skill does not reveal whether a model has learned physical mechanisms or exploits statistical regularities in its training data. Here, we present the first study of what a FM fine-tune"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20778","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/2607.20778/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":"2607.20778","created_at":"2026-07-24T00:23:34.213843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20778v1","created_at":"2026-07-24T00:23:34.213843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20778","created_at":"2026-07-24T00:23:34.213843+00:00"},{"alias_kind":"pith_short_12","alias_value":"CY7IEZC2ZTEM","created_at":"2026-07-24T00:23:34.213843+00:00"},{"alias_kind":"pith_short_16","alias_value":"CY7IEZC2ZTEMLS3K","created_at":"2026-07-24T00:23:34.213843+00:00"},{"alias_kind":"pith_short_8","alias_value":"CY7IEZC2","created_at":"2026-07-24T00:23:34.213843+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/CY7IEZC2ZTEMLS3KJONM565DJS","json":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS.json","graph_json":"https://pith.science/api/pith-number/CY7IEZC2ZTEMLS3KJONM565DJS/graph.json","events_json":"https://pith.science/api/pith-number/CY7IEZC2ZTEMLS3KJONM565DJS/events.json","paper":"https://pith.science/paper/CY7IEZC2"},"agent_actions":{"view_html":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS","download_json":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS.json","view_paper":"https://pith.science/paper/CY7IEZC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20778&json=true","fetch_graph":"https://pith.science/api/pith-number/CY7IEZC2ZTEMLS3KJONM565DJS/graph.json","fetch_events":"https://pith.science/api/pith-number/CY7IEZC2ZTEMLS3KJONM565DJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS/action/storage_attestation","attest_author":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS/action/author_attestation","sign_citation":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS/action/citation_signature","submit_replication":"https://pith.science/pith/CY7IEZC2ZTEMLS3KJONM565DJS/action/replication_record"}},"created_at":"2026-07-24T00:23:34.213843+00:00","updated_at":"2026-07-24T00:23:34.213843+00:00"}