{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008832024,0.0008334641,0.0009121964,0.0005227026,0.001449589,0.003275306,0.001550127,0.001758033,0.009170078],"category_scores_gemma":[0.01217203,0.0005252871,0.001268452,0.0006494983,0.002688318,0.005246314,0.003053499,0.005009184,0.0007613389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001860845,"about_ca_system_score_gemma":0.001173338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003628883,"about_ca_topic_score_gemma":0.004407146,"domain_scores_codex":[0.9990786,0.0003006263,0.00003440672,0.0002137105,0.0001727028,0.0001999385],"domain_scores_gemma":[0.9926479,0.005536816,0.000424082,0.0005075326,0.0002151446,0.000668549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008167612,0.0003788845,0.006159942,0.000374131,0.0001268251,0.0005373379,0.000700375,0.05300369,0.00297527,0.8408955,0.04579001,0.04824127],"study_design_scores_gemma":[0.0003004351,0.0002178491,0.005381481,0.00009113506,0.00006223448,0.0004724791,0.000571103,0.158306,0.003119521,0.8125288,0.01887926,0.00006976921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7730389,0.000972973,0.06121129,0.01443187,0.0003981189,0.0001975505,0.00120627,0.0006663842,0.1478767],"genre_scores_gemma":[0.9662421,0.0003701683,0.01778373,0.001072483,0.000152813,0.0001664477,0.0008599411,0.00007402395,0.01327831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009170078,"threshold_uncertainty_score":0.03067702,"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."}}