{"id":"W4306759121","doi":"10.1609/aiide.v18i1.21977","title":"FarmQuest: A Demonstration of an AI Director Video Game Test Bed","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Intuition; Computer science; Test (biology); Video game; Artificial intelligence; Operations research; Multimedia; Engineering; Psychology; Cognitive science","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":[],"consensus_categories":[],"category_scores_codex":[0.0003403596,0.0002897026,0.0003400315,0.0002063747,0.0002513949,0.0004553091,0.001507529,0.00004954961,0.00009860889],"category_scores_gemma":[0.0003996126,0.0002385265,0.0001547048,0.0004501762,0.000360601,0.00191036,0.0008523707,0.0003952709,0.00001278022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001443732,"about_ca_system_score_gemma":0.00009255787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007847646,"about_ca_topic_score_gemma":0.00001201161,"domain_scores_codex":[0.9974682,0.00003853241,0.0008192961,0.0006265739,0.0007158685,0.0003315605],"domain_scores_gemma":[0.9981408,0.0002476095,0.0006235595,0.0003219451,0.0005450939,0.0001210354],"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":[0.000486947,0.002472495,0.002782457,0.00004805368,0.00009566733,0.000003500757,0.01315515,0.0002465477,0.1153592,0.4740688,0.00009712785,0.391184],"study_design_scores_gemma":[0.00004155585,0.002102705,0.0002949921,0.0001422133,0.00001680231,0.00001851659,0.00691029,0.07000529,0.8642655,0.05560493,0.0002896567,0.0003075592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9739009,0.00002531089,0.01442788,0.003195575,0.0005133641,0.0008380167,0.00008036091,0.00008848796,0.006930127],"genre_scores_gemma":[0.9990698,0.00001488698,0.0002614383,0.0003382912,0.00003402415,0.00009828727,0.000003667834,0.00001549191,0.0001641111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7489063,"threshold_uncertainty_score":0.972683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03541465136400487,"score_gpt":0.2905972546056102,"score_spread":0.2551826032416054,"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."}}