{"id":"W3136819617","doi":"10.1088/2632-2153/ab7657","title":"Establishing an evaluation metric to quantify climate change image realism <sup>*</sup>","year":2020,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Climate Change Communication and Perception","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Generative grammar; Computer science; Metric (unit); Artificial intelligence; Realism; Generative model; Empathy; Deep learning; Machine learning; Classifier (UML); Data science; Psychology; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008149181,0.001412743,0.0005983753,0.002175367,0.0004136131,0.002723848,0.001145531,0.002021546,0.005576603],"category_scores_gemma":[0.04356787,0.0002706463,0.0005904878,0.0008406102,0.001512473,0.002184444,0.002075841,0.001140646,0.00166838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009483601,"about_ca_system_score_gemma":0.0005203352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002149999,"about_ca_topic_score_gemma":0.002499687,"domain_scores_codex":[0.9947799,0.002634807,0.0003494142,0.0006093212,0.001354822,0.0002717582],"domain_scores_gemma":[0.9750965,0.01574601,0.001854638,0.002483014,0.004172484,0.0006474258],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00255606,0.0005912082,0.04326372,0.00207205,0.0006727366,0.000328826,0.000861072,0.2301457,0.04631742,0.01835097,0.03750318,0.617337],"study_design_scores_gemma":[0.00007046813,0.001073911,0.02020521,0.0003443363,0.0001495714,0.0005560606,0.0004585446,0.8941031,0.06109496,0.01292332,0.008885518,0.0001350953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3451912,0.004998066,0.6034685,0.00210203,0.001507259,0.001055863,0.003390437,0.005623522,0.03266316],"genre_scores_gemma":[0.8668225,0.0004327541,0.1262718,0.0003749545,0.0001499533,0.0002406152,0.002967502,0.0006356831,0.002104226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918508,"threshold_uncertainty_score":0.0430975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3379307254520805,"score_gpt":0.4590707075245422,"score_spread":0.1211399820724617,"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."}}