{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZOAW47DUY24V5FO3OG6PLFRAVG","short_pith_number":"pith:ZOAW47DU","schema_version":"1.0","canonical_sha256":"cb816e7c74c6b95e95db71bcf59620a992b6f4589ff3fdaf872c649e271c0b07","source":{"kind":"arxiv","id":"2605.17493","version":1},"attestation_state":"computed","paper":{"title":"Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Minjong Cheon","submitted_at":"2026-05-17T15:04:15Z","abstract_excerpt":"Deep learning weather prediction models achieve remarkable predictive skill yet remain largely opaque: we know little about how they represent physical climate phenomena internally. Mechanistic interpretability through Sparse Autoencoders (SAEs) offers a principled route to decomposing these representations, but existing SAEs assume strictly linear feature superposition - a constraint ill-suited for the highly nonlinear atmospheric dynamics encoded in modern transformers. We introduce KAN-SAE, a sparse autoencoder whose encoder replaces the standard ReLU with learnable per-feature B-spline act"},"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":"2605.17493","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T15:04:15Z","cross_cats_sorted":["cs.AI","cs.CV","physics.ao-ph"],"title_canon_sha256":"e5f5d11be565693cc9a49b6f89cb5c18005aa121a2556095995ab8af05e20ae7","abstract_canon_sha256":"f440e394c99e0a6f63b6fc99c099eaa2c90ebdc85f0f2f1e20bebbd717226f41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:42.043757Z","signature_b64":"nHSQWqMwBxI+W7mtkSGejQj/188YSpLpPKGGyX3wHUjTx0rkwil4J9qWj5iTQYT+rzNuTDcEC1j1/3MseHN0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb816e7c74c6b95e95db71bcf59620a992b6f4589ff3fdaf872c649e271c0b07","last_reissued_at":"2026-05-20T00:04:42.043088Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:42.043088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","physics.ao-ph"],"primary_cat":"cs.LG","authors_text":"Minjong Cheon","submitted_at":"2026-05-17T15:04:15Z","abstract_excerpt":"Deep learning weather prediction models achieve remarkable predictive skill yet remain largely opaque: we know little about how they represent physical climate phenomena internally. Mechanistic interpretability through Sparse Autoencoders (SAEs) offers a principled route to decomposing these representations, but existing SAEs assume strictly linear feature superposition - a constraint ill-suited for the highly nonlinear atmospheric dynamics encoded in modern transformers. We introduce KAN-SAE, a sparse autoencoder whose encoder replaces the standard ReLU with learnable per-feature B-spline act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17493","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/2605.17493/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.677422Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.641229Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7933f89894de0e64bdfdc993184cacc798debfc7f06d9d961aaa10d45fe01b8a"},"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":"2605.17493","created_at":"2026-05-20T00:04:42.043183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17493v1","created_at":"2026-05-20T00:04:42.043183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17493","created_at":"2026-05-20T00:04:42.043183+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOAW47DUY24V","created_at":"2026-05-20T00:04:42.043183+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOAW47DUY24V5FO3","created_at":"2026-05-20T00:04:42.043183+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOAW47DU","created_at":"2026-05-20T00:04:42.043183+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/ZOAW47DUY24V5FO3OG6PLFRAVG","json":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG.json","graph_json":"https://pith.science/api/pith-number/ZOAW47DUY24V5FO3OG6PLFRAVG/graph.json","events_json":"https://pith.science/api/pith-number/ZOAW47DUY24V5FO3OG6PLFRAVG/events.json","paper":"https://pith.science/paper/ZOAW47DU"},"agent_actions":{"view_html":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG","download_json":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG.json","view_paper":"https://pith.science/paper/ZOAW47DU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17493&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOAW47DUY24V5FO3OG6PLFRAVG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOAW47DUY24V5FO3OG6PLFRAVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG/action/storage_attestation","attest_author":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG/action/author_attestation","sign_citation":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG/action/citation_signature","submit_replication":"https://pith.science/pith/ZOAW47DUY24V5FO3OG6PLFRAVG/action/replication_record"}},"created_at":"2026-05-20T00:04:42.043183+00:00","updated_at":"2026-05-20T00:04:42.043183+00:00"}