{"id":"W4385570299","doi":"10.18653/v1/2023.acl-srw.17","title":"The Turing Quest: Can Transformers Make Good NPCs?","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scripting language; Computer science; Software deployment; Variety (cybernetics); Pipeline (software); Human–computer interaction; Turing; Transformer; Artificial intelligence; Programming language; Software engineering; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.002106224,0.0008492501,0.000441974,0.0005237403,0.0007366149,0.002674902,0.001349333,0.00105651,0.005702078],"category_scores_gemma":[0.02209454,0.0005490878,0.0008279234,0.0003092088,0.003126508,0.006430454,0.002014437,0.001491711,0.002489927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006384097,"about_ca_system_score_gemma":0.0009958053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002116676,"about_ca_topic_score_gemma":0.003142068,"domain_scores_codex":[0.9980757,0.0007731084,0.0001009487,0.0003729387,0.0005338461,0.0001434542],"domain_scores_gemma":[0.9923891,0.00424715,0.0003602348,0.001891202,0.0008090895,0.0003032297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00080001,0.0002145293,0.01204141,0.001080118,0.00008281129,0.001631183,0.005457262,0.09644619,0.03634505,0.532323,0.01662285,0.2969556],"study_design_scores_gemma":[0.00008059593,0.000375948,0.001145088,0.0001677561,0.00007075012,0.001217442,0.001559891,0.5308075,0.05351122,0.3506465,0.06032672,0.00009063684],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08643745,0.0002560002,0.8824565,0.0009798527,0.0001449872,0.0002216795,0.0004658741,0.007794798,0.02124281],"genre_scores_gemma":[0.7029496,0.0002041701,0.2878901,0.0003730651,0.00002792579,0.0001197229,0.0006608586,0.001773028,0.006001538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005702078,"threshold_uncertainty_score":0.01907533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02977536689391685,"score_gpt":0.2817394542453059,"score_spread":0.251964087351389,"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."}}