{"id":"W2788411626","doi":"10.1145/3167476","title":"Evaluating Computational Creativity","year":2018,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Creativity in Education and Neuroscience","field":"Psychology","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Creativity; Computer science; Computational creativity; Task (project management); Creativity technique; Cognitive science; Software; Human–computer interaction; Cognition; Data science; Artificial intelligence; Psychology; Programming language","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008170477,0.0004899643,0.00122695,0.0002877012,0.000451669,0.000149601,0.001253948,0.0002702666,0.00110329],"category_scores_gemma":[0.003914376,0.0004564343,0.0003727622,0.0009539447,0.0003380033,0.00006824283,0.000516592,0.0005663342,0.002439639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001336759,"about_ca_system_score_gemma":0.0004891598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001061041,"about_ca_topic_score_gemma":0.000007849495,"domain_scores_codex":[0.989817,0.007206162,0.0008217735,0.001105276,0.0005092932,0.0005404532],"domain_scores_gemma":[0.9880829,0.009428782,0.0008050113,0.001304927,0.000231614,0.0001467219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001051374,0.0001985147,0.0003183869,0.0006315304,0.00006531918,0.000005435949,0.0005151199,0.00001678622,7.248489e-8,0.0003164787,0.005683476,0.9922478],"study_design_scores_gemma":[0.0003112707,0.0002643735,0.009124846,0.003985126,0.0002948162,0.0002255894,0.00006798751,0.0008043156,2.215086e-7,0.000586714,0.9833598,0.0009749081],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0008149319,0.9761882,0.007468307,0.00004696355,0.005918307,0.0007767745,0.00007738711,0.0003130446,0.008396043],"genre_scores_gemma":[0.002799567,0.9599008,0.02024731,0.0004587018,0.003949017,0.0001474117,0.0009291299,0.0003200017,0.01124808],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9912729,"threshold_uncertainty_score":0.9998099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4074853096323455,"score_gpt":0.5620924236654873,"score_spread":0.1546071140331418,"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."}}