{"id":"W3186993943","doi":"10.1145/3472538.3472602","title":"Generating Lode Runner Levels by Learning Player Paths with LSTMs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Path (computing); Controllability; Lode; Artificial intelligence; Coherence (philosophical gambling strategy); Video game; Machine learning; Human–computer interaction; Multimedia; Programming language","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004450505,0.0004248626,0.0004196856,0.0000893931,0.0002634056,0.001439793,0.001507055,0.0003024809,0.0003985713],"category_scores_gemma":[0.0001338996,0.0003479205,0.0001204113,0.0002131275,0.00008110115,0.0004332271,0.002416998,0.001263625,0.0001356649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009546282,"about_ca_system_score_gemma":0.0003501265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004635801,"about_ca_topic_score_gemma":0.0001671061,"domain_scores_codex":[0.9969023,0.0001917414,0.0005025403,0.001251579,0.0006186917,0.0005331097],"domain_scores_gemma":[0.9980102,0.0001784121,0.000281872,0.001053606,0.0003278915,0.0001480001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008281725,0.000183656,0.002938448,0.0001171923,0.0002391093,0.000338142,0.0127054,0.7364703,0.03880963,0.00859051,0.005946365,0.1936529],"study_design_scores_gemma":[0.00005338039,0.00007854661,0.00007364908,0.0002068486,0.00001575568,0.00003126306,0.0008316089,0.8762957,0.1177572,0.000825922,0.002922019,0.0009080889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1058727,0.0003935854,0.8876451,0.0006320644,0.0006430053,0.0001927549,0.000003269801,0.0004033376,0.004214176],"genre_scores_gemma":[0.7220954,0.00002587325,0.2709324,0.0006696181,0.0002199912,0.00005012298,0.0000209272,0.0000420473,0.00594358],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6167126,"threshold_uncertainty_score":0.9998973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04382845345099001,"score_gpt":0.2825260387895651,"score_spread":0.238697585338575,"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."}}