{"id":"W2053901450","doi":"10.7771/1932-6246.1152","title":"On Evaluating Human Problem Solving of Computationally Hard Problems","year":2013,"lang":"en","type":"article","venue":"The Journal of Problem Solving","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Perception; Computational problem; Computational complexity theory; Euclidean geometry; Cognition; Computational model; Theoretical computer science; Artificial intelligence; Cognitive science; Mathematics; Algorithm; Psychology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0251685,0.0003560113,0.0008554127,0.0008302081,0.0007140544,0.0007608827,0.002503603,0.0001217098,0.001491297],"category_scores_gemma":[0.004704738,0.0002111851,0.0003581847,0.0008785717,0.0002116456,0.001329208,0.0004927129,0.0007700857,0.0002197321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001460491,"about_ca_system_score_gemma":0.0002839131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007078287,"about_ca_topic_score_gemma":0.00001337016,"domain_scores_codex":[0.9889125,0.001400232,0.003881975,0.0004238693,0.004807894,0.0005735232],"domain_scores_gemma":[0.9827921,0.0075395,0.004809772,0.0007789159,0.003871255,0.000208455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001821941,0.0004764973,0.003513933,0.0001680804,0.0002537873,0.00001492746,0.02536186,0.3470759,0.5041267,0.006155203,0.02200902,0.09066191],"study_design_scores_gemma":[0.003035008,0.001917154,0.03471207,0.003348896,0.0001522989,0.0003465856,0.004418605,0.1390883,0.002682404,0.8091861,0.0003960902,0.0007164718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.934307,0.0003411814,0.05833928,0.001614164,0.0004625424,0.001168146,0.000004836021,0.00003662692,0.003726269],"genre_scores_gemma":[0.8774673,0.000008192684,0.1215441,0.0002399294,0.0002016407,0.00000892064,9.47477e-7,0.00004451729,0.0004844501],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8030309,"threshold_uncertainty_score":0.9994215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2057732547937177,"score_gpt":0.4290050318615999,"score_spread":0.2232317770678822,"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."}}