{"id":"W4406400197","doi":"10.5194/gmd-18-161-2025","title":"Climate model downscaling in central Asia: a dynamical and a neural network approach","year":2025,"lang":"en","type":"article","venue":"Geoscientific model development","topic":"Climate variability and models","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Downscaling; Climatology; Coupled model intercomparison project; Environmental science; Precipitation; GCM transcription factors; Climate model; Climate change; Representative Concentration Pathways; General Circulation Model; Meteorology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001123204,0.0002443015,0.0002666421,0.00009818376,0.0003821585,0.0001273122,0.0002956869,0.0001297645,0.00004162908],"category_scores_gemma":[0.00002002584,0.0002328934,0.00005072503,0.0005279893,0.0002313077,0.0002121163,0.0008499956,0.0002391945,0.00001309908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003966507,"about_ca_system_score_gemma":0.00008447054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006811092,"about_ca_topic_score_gemma":0.0003014809,"domain_scores_codex":[0.9970773,0.00005532917,0.0005272217,0.0009520148,0.0003550562,0.001033076],"domain_scores_gemma":[0.9994026,0.00002877942,0.00005731097,0.0003335676,0.000009351372,0.0001684108],"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":[0.00002946797,0.0001693715,0.01040763,0.00004305499,0.000004428511,0.000001879319,0.0009127426,0.9816864,0.0002646358,0.002190423,0.0003152855,0.003974682],"study_design_scores_gemma":[0.0003729026,0.000003258283,0.01077673,0.00003665305,0.000009266357,0.000002594866,0.00005574794,0.9843469,0.00001840681,0.003961637,0.0001789258,0.0002369989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7602836,0.00002938976,0.2317225,0.0001849273,0.0002113608,0.0004408379,0.00001693025,0.00005777871,0.007052627],"genre_scores_gemma":[0.9160019,0.00001909245,0.08248985,0.0002105715,0.00000643201,0.00009014367,0.00005437883,0.00001137638,0.001116256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1557182,"threshold_uncertainty_score":0.9497119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01557512780977308,"score_gpt":0.2228928416145151,"score_spread":0.207317713804742,"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."}}