{"id":"W7064720729","doi":"","title":"On Characterizations of Large Language Models and Creativity Evaluation","year":2023,"lang":"en","type":"article","venue":"Kent Academic Repository (University of Kent)","topic":"Electromagnetic Compatibility and Measurements","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Creativity; Language model; Expression (computer science); Action (physics); On Language; Natural language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002902253,0.00006574145,0.0001225271,0.00009431594,0.00005833643,0.000002359283,0.00009355607,0.00007486995,0.00002099487],"category_scores_gemma":[0.00001908464,0.0000836829,0.00003308617,0.0001684633,0.0000323408,0.0001346046,0.00002587547,0.0001298025,0.000002667115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006006456,"about_ca_system_score_gemma":0.00001786087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002532336,"about_ca_topic_score_gemma":0.000007946775,"domain_scores_codex":[0.9993424,0.00005724518,0.0001100194,0.0001195309,0.0002609787,0.0001098453],"domain_scores_gemma":[0.9996714,0.00004310695,0.00005838934,0.000135482,0.00005068076,0.00004096336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005850232,0.0001045692,0.01269279,0.0003063769,0.0001166768,0.000006319351,0.01382932,0.01383206,0.9529675,0.0008691047,0.001589173,0.003627572],"study_design_scores_gemma":[0.001524953,0.0001950377,0.3149884,0.0002638444,0.000179049,0.000003580413,0.001701953,0.6366504,0.04305746,0.001025882,0.0001681221,0.000241315],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9970689,0.0001541294,0.0007028626,0.00004048708,0.00007492265,0.0001964726,0.00001339348,0.00008133404,0.001667457],"genre_scores_gemma":[0.9995286,0.0001457002,0.00003375416,0.000004824638,0.00001095164,6.396428e-7,0.00002532672,0.000005593064,0.0002445447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9099101,"threshold_uncertainty_score":0.341249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02420777247282885,"score_gpt":0.2413337751800886,"score_spread":0.2171260027072597,"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."}}