{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004671443,0.0001099523,0.0001547694,0.0007809892,0.001839834,0.0003759616,0.0007289133,0.0001307756,0.0001725505],"category_scores_gemma":[0.005674917,0.0001102161,0.00001733656,0.004952569,0.0006689367,0.001025906,0.000369342,0.0003983371,0.00006627232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001151609,"about_ca_system_score_gemma":0.00008242688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001726726,"about_ca_topic_score_gemma":0.0007895424,"domain_scores_codex":[0.9979518,0.0003063785,0.0001793861,0.000456328,0.0006626705,0.0004434088],"domain_scores_gemma":[0.9988757,0.00008787287,0.00007447384,0.0002722986,0.0004595022,0.0002301866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001443725,0.00004194433,0.03924217,0.00001740265,0.000002615038,0.000002376192,0.08762445,0.00007664566,0.008486382,0.02076211,0.00006298628,0.8436665],"study_design_scores_gemma":[0.0007322219,0.0009080422,0.02589827,0.00008048883,0.00006414065,0.00001123852,0.1085151,0.7148858,0.00029518,0.002100824,0.145695,0.0008137809],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9047955,0.000262859,0.0001992613,0.086357,0.0000746824,0.0005427137,0.000008761339,0.0005945651,0.007164627],"genre_scores_gemma":[0.9956629,0.001278163,0.001595842,0.00123125,0.0001277305,0.00005399872,0.00002560477,0.00001100228,0.00001355988],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8428527,"threshold_uncertainty_score":0.9994596,"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."}}