{"id":"W4413369110","doi":"10.1177/10597123251364738","title":"Human Exploration in Complex Problem-Solving Tasks: More Effortful Interaction Leads to Higher Efficiency","year":2025,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"Deutsche Forschungsgemeinschaft","keywords":"Cognitive psychology; Computer science; Psychology; Cognitive science; Human–computer interaction; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001494745,0.0002532166,0.0004653214,0.001215097,0.0003359446,0.0004382246,0.0006984386,0.00009857481,0.0007042766],"category_scores_gemma":[0.0002866162,0.0002069048,0.0001436172,0.00211726,0.00006642329,0.000808773,0.0003649482,0.0002443068,0.0003356222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002668242,"about_ca_system_score_gemma":0.0000596837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004237926,"about_ca_topic_score_gemma":0.0009059765,"domain_scores_codex":[0.9961221,0.0002326327,0.001266911,0.0008566994,0.001147452,0.0003742465],"domain_scores_gemma":[0.9979857,0.0004163104,0.0003074033,0.0006949387,0.0004881299,0.0001075101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005650637,0.002500682,0.2623889,0.00003694743,0.000041589,0.0002514108,0.01406658,0.01907025,0.1684988,0.1742714,0.1196721,0.2386362],"study_design_scores_gemma":[0.0008610021,0.0003208262,0.9607584,0.0002738283,0.00002857722,0.000006183069,0.005727299,0.002890416,0.0004692018,0.007882646,0.02032674,0.0004548694],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9417262,0.00008478409,0.04216396,0.0004675347,0.0008503913,0.001341411,0.0000133227,0.00009719765,0.01325522],"genre_scores_gemma":[0.9905248,2.360703e-7,0.002261806,0.0002650514,0.00006947637,0.0002359381,0.000005786469,0.00001656069,0.006620396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6983694,"threshold_uncertainty_score":0.8437335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2465736852457586,"score_gpt":0.4542089808319268,"score_spread":0.2076352955861682,"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."}}