{"id":"W4387394671","doi":"10.1609/aiide.v19i1.27499","title":"Entropy as a Measure of Puzzle Difficulty","year":2023,"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":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Exploit; Ranking (information retrieval); Witness; Entropy (arrow of time); Variety (cybernetics); Set (abstract data type); Artificial intelligence; Machine learning; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002429926,0.001017179,0.0008211084,0.005390851,0.0003892712,0.001794824,0.0007657632,0.000905862,0.00359453],"category_scores_gemma":[0.0299947,0.0003686204,0.0007686071,0.002239641,0.001556205,0.003093016,0.00210926,0.001036779,0.0005139401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007059634,"about_ca_system_score_gemma":0.0003485853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009222469,"about_ca_topic_score_gemma":0.001095593,"domain_scores_codex":[0.9969394,0.0006895504,0.0003207793,0.0004343516,0.001416756,0.0001992032],"domain_scores_gemma":[0.9792243,0.0140695,0.00291445,0.001708849,0.001218553,0.0008643155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001613785,0.001027631,0.3735257,0.001290892,0.001071789,0.0007725027,0.003050457,0.2023591,0.05961867,0.06628767,0.006520283,0.2828615],"study_design_scores_gemma":[0.0001138507,0.001437078,0.4009891,0.0001656835,0.0002094033,0.0008696779,0.0011517,0.4776954,0.02094891,0.08990231,0.006196381,0.0003205347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7401671,0.0006952927,0.2381251,0.0002536858,0.00009568831,0.0002930601,0.002137718,0.0006312035,0.01760125],"genre_scores_gemma":[0.9706116,0.0001594605,0.02617997,0.00003248681,0.00003914589,0.0001197076,0.001515594,0.00007410054,0.001267886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005390851,"threshold_uncertainty_score":0.01285088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04936860510762716,"score_gpt":0.2936480159845815,"score_spread":0.2442794108769543,"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."}}