{"id":"W4391116695","doi":"10.1609/aaaiss.v2i1.27650","title":"Multi-Variable Hard Physical Constraints for Climate Model Downscaling","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Climate variability and models","field":"Environmental Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Agencia Estatal de Investigación","keywords":"Downscaling; Variable (mathematics); Climate model; Climate change; Scale (ratio); GCM transcription factors; Computer science; Scope (computer science); Climatology; Environmental science; General Circulation Model; Econometrics; Mathematics; Geography; Geology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003077505,0.0009462315,0.001092213,0.0004804669,0.0008026268,0.001841266,0.002040093,0.001429383,0.003474094],"category_scores_gemma":[0.01966419,0.0007094266,0.0009051916,0.0007489981,0.001707494,0.00326367,0.003491326,0.004830249,0.0002857099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121077,"about_ca_system_score_gemma":0.001545847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003877866,"about_ca_topic_score_gemma":0.005749903,"domain_scores_codex":[0.9985772,0.0005272985,0.00008287358,0.0003137208,0.000356755,0.0001421052],"domain_scores_gemma":[0.9926078,0.004969657,0.0007297212,0.000888836,0.0004469845,0.0003569561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005152125,0.00003480886,0.001073944,0.0000818274,0.00004225624,0.0001317551,0.00006991104,0.8836725,0.0007732902,0.09385646,0.002771456,0.01744024],"study_design_scores_gemma":[0.00001110379,0.000009049772,0.0001944954,0.00001482142,0.000004225034,0.00001521295,0.00001405886,0.9049217,0.0002539927,0.0933083,0.001245652,0.00000743386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02747992,0.0006079535,0.9656118,0.001551959,0.0001291779,0.00005625674,0.000358517,0.00021848,0.003985837],"genre_scores_gemma":[0.6243883,0.0008114421,0.3678137,0.0009748073,0.0003983636,0.000462741,0.001169088,0.000416124,0.003565394],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003877866,"threshold_uncertainty_score":0.01627558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0194022782809089,"score_gpt":0.2465382461274216,"score_spread":0.2271359678465127,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}