{"id":"W3186953399","doi":"","title":"Modelling Recognition in Human Puzzle Solving","year":2021,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Adversarial system; Artificial intelligence; Simple (philosophy); Context (archaeology); Reinforcement learning; Artificial neural network; Machine learning; Epistemology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002134941,0.0002281797,0.0002273504,0.0002117283,0.0001994259,0.002796845,0.0008593169,0.0001371328,0.0002432726],"category_scores_gemma":[0.0002023118,0.0002512515,0.0001284885,0.0009457506,0.00005668144,0.008954789,0.0005839951,0.0004837667,0.001894619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004862992,"about_ca_system_score_gemma":0.000109836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000738686,"about_ca_topic_score_gemma":0.000006768121,"domain_scores_codex":[0.9977991,0.0001042699,0.0005623622,0.0006682777,0.0003486051,0.0005173899],"domain_scores_gemma":[0.9988955,0.0001707837,0.0001058992,0.0005677913,0.00007204388,0.000188023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009713458,0.002653187,0.1651242,0.0003178892,0.0001330242,0.003419401,0.00173105,0.03765295,0.009667814,0.1773064,0.003362966,0.598534],"study_design_scores_gemma":[0.0002926475,0.00006457607,0.0003030504,0.0003966408,0.000006945559,0.00005556466,0.0001588916,0.2011468,0.1691428,0.5893406,0.03802831,0.001063175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5999178,0.0003691148,0.3498575,0.001326624,0.0003277209,0.0002397514,0.0001991304,0.0008289692,0.0469334],"genre_scores_gemma":[0.9750503,0.00001720993,0.02361584,0.0004208326,0.0001125165,0.00001716817,0.0001821081,0.00004108214,0.0005428987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5974708,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0475140153750972,"score_gpt":0.2508875830646463,"score_spread":0.2033735676895491,"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."}}