{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003865047,0.00009307113,0.00007132121,0.00005587745,0.0003191291,0.0002527738,0.0009359872,0.00003430103,0.00001578816],"category_scores_gemma":[0.00003774198,0.00006060481,0.00005978804,0.0005482393,0.0000780594,0.0001556524,0.0001138166,0.0001092544,0.000511242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000299074,"about_ca_system_score_gemma":0.00005340192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002977324,"about_ca_topic_score_gemma":0.002323587,"domain_scores_codex":[0.998902,0.00003159122,0.0001869122,0.0002363328,0.000249922,0.0003932396],"domain_scores_gemma":[0.9992964,0.0002165352,0.00002484937,0.0003564864,0.00003471665,0.00007104369],"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":[0.000001868042,0.000009203042,0.0004328817,0.00000431025,0.00001358149,0.00001890039,0.002822126,0.0003062554,0.0006114098,0.3384839,0.001727899,0.6555676],"study_design_scores_gemma":[0.0001398937,0.0001933289,0.006355209,0.00005195886,0.00001205711,0.00003574349,0.004927611,0.2996701,0.2869015,0.1169149,0.2838964,0.0009012528],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1121194,0.0001858939,0.5975744,0.0652065,0.003558161,0.0006554602,0.000003927896,0.003383842,0.2173125],"genre_scores_gemma":[0.9899467,0.0000890974,0.001525762,0.00037779,0.00007241072,0.00002059891,5.308205e-7,0.000009349345,0.007957712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8778273,"threshold_uncertainty_score":0.6571152,"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."}}