{"id":"W4404445448","doi":"10.1609/aiide.v20i1.31872","title":"Generalized Entropy and Solution Information for Measuring Puzzle Difficulty","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Canadian Institute for Advanced Research","keywords":"Entropy (arrow of time); Mathematics; Statistical physics; Computer science; Physics; Thermodynamics","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001193337,0.000141315,0.0001283908,0.0001021169,0.0001322041,0.001041637,0.0002428789,0.00003996178,0.000007190839],"category_scores_gemma":[0.0001173536,0.00009639206,0.00007413703,0.0001064172,0.00007215037,0.002521748,0.0001904872,0.0001046528,0.00001351833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004695284,"about_ca_system_score_gemma":0.00001603844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008414396,"about_ca_topic_score_gemma":0.000001051155,"domain_scores_codex":[0.9990691,0.000005511504,0.000301909,0.0002478186,0.0002088439,0.0001668051],"domain_scores_gemma":[0.9994639,0.00006354117,0.000119855,0.00006976232,0.0002291315,0.00005386907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000198632,0.0001083504,0.00004736464,0.0001469079,0.00004654419,1.968706e-7,0.00356476,0.000009947838,0.05377351,0.450753,0.0003377827,0.4910131],"study_design_scores_gemma":[0.0001045569,0.0004152228,0.0001149844,0.0009711639,0.00001844447,0.000009307329,0.001758517,0.2887136,0.6476527,0.05722694,0.002766121,0.0002483879],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7621854,0.00007139143,0.226568,0.005824119,0.0007950828,0.001081885,0.00005559781,0.0001195225,0.003299052],"genre_scores_gemma":[0.9992031,0.00006863455,0.0003989097,0.0001211158,0.00002757758,0.00006766099,0.000005185104,0.000004429597,0.0001033954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5938792,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04732470678743708,"score_gpt":0.272570042256081,"score_spread":0.2252453354686439,"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."}}