{"id":"W3092916815","doi":"10.2197/ipsjjip.28.919","title":"Mad Science is Provably Hard: Puzzles in Hearthstone's Boomsday Lab are NP-hard","year":2020,"lang":"en","type":"article","venue":"Journal of Information Processing","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Generalization; Computational complexity theory; Theoretical computer science; Algorithm; Mathematics","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":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001166592,0.0001286428,0.0002256051,0.000456211,0.0002166477,0.001098339,0.001105677,0.00005189284,0.00001704626],"category_scores_gemma":[0.0007009027,0.0001093879,0.00006088333,0.001530543,0.0001568699,0.01558928,0.00017178,0.0003456371,0.00009375354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001150105,"about_ca_system_score_gemma":0.0007125975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005805758,"about_ca_topic_score_gemma":0.000001779686,"domain_scores_codex":[0.9976277,0.00002777735,0.0010072,0.0001404575,0.0009002177,0.0002965838],"domain_scores_gemma":[0.9976616,0.0000336815,0.001068618,0.0001564862,0.0008994332,0.0001802119],"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":[0.00009603604,0.00009705741,0.01314747,0.0004353591,0.00001510069,0.00004695355,0.09215307,0.007674983,0.007935011,0.003017515,0.006013236,0.8693682],"study_design_scores_gemma":[0.0008626555,0.0005520968,0.02366341,0.001608046,0.00001778503,0.0005505992,0.01013893,0.6327752,0.265399,0.00628999,0.05719298,0.0009493699],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.287962,0.0004859818,0.6661177,0.04209147,0.000661209,0.0002924466,0.000003157446,0.0001176777,0.002268311],"genre_scores_gemma":[0.9298088,0.00002436407,0.06370971,0.006320256,0.0001028776,0.000002457891,2.407286e-7,0.000005079969,0.00002623965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8684188,"threshold_uncertainty_score":0.9999386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03635320821608718,"score_gpt":0.2868326374416269,"score_spread":0.2504794292255397,"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."}}