{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04998139,0.001727297,0.002149415,0.004800447,0.001842217,0.01151025,0.003379534,0.003616905,0.005143607],"category_scores_gemma":[0.2476108,0.0007770942,0.001949745,0.004361931,0.006663803,0.01644147,0.006680278,0.00553608,0.0006350848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005169389,"about_ca_system_score_gemma":0.002254087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003352723,"about_ca_topic_score_gemma":0.003568457,"domain_scores_codex":[0.9430289,0.03853051,0.003664243,0.003460489,0.01000676,0.001309094],"domain_scores_gemma":[0.674913,0.2833971,0.009912444,0.01727618,0.0109364,0.003564997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008697259,0.0006045898,0.01251802,0.0008762731,0.0003443205,0.0003854133,0.003185828,0.1814751,0.002346661,0.5354015,0.01161063,0.2503819],"study_design_scores_gemma":[0.00006169742,0.0002487872,0.001538507,0.0002676348,0.00005948261,0.0002580977,0.0005575902,0.6134166,0.001605815,0.3779004,0.004008299,0.00007717704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0994623,0.005855577,0.8352936,0.01363711,0.0003611678,0.0007153019,0.0008958643,0.002085414,0.04169366],"genre_scores_gemma":[0.7323002,0.0009837564,0.2581847,0.001508842,0.0004355589,0.0008988994,0.001377352,0.0006758592,0.003634924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04998139,"threshold_uncertainty_score":0.2643301,"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."}}