{"id":"W2068577692","doi":"10.1076/clin.15.3.309.10273","title":"The Effect of Differing Scoring Methods for the Tower of London Task on Developmental Patterns of Performance","year":2001,"lang":"en","type":"article","venue":"The Clinical Neuropsychologist","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Psychology; Construct (python library); Developmental psychology; Tower; Construct validity; Psychometrics; Computer science; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.00403756,0.0001689172,0.0003771871,0.00002408824,0.0002018452,0.00001006362,0.0006452622,0.00006797552,0.00007273287],"category_scores_gemma":[0.00297376,0.00007522898,0.000258981,0.0001443324,0.0007598053,0.00002066703,0.0001548508,0.0003877175,0.000004609708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008848468,"about_ca_system_score_gemma":0.000009005193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003541467,"about_ca_topic_score_gemma":0.000005212959,"domain_scores_codex":[0.9973982,0.0009978509,0.0008687924,0.0003106295,0.0001318295,0.0002926726],"domain_scores_gemma":[0.9648415,0.03403493,0.0004200404,0.0005981734,0.00007455776,0.00003075867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001950683,0.0001443392,0.3505096,0.00003575068,0.0001041088,0.00000202163,0.0002490256,0.00001172359,0.001228964,0.0002288458,0.00006079292,0.6454741],"study_design_scores_gemma":[0.001414134,0.003459499,0.9892166,0.0001031806,0.00006920566,0.00002260275,0.0003057453,0.0001355238,0.001583744,0.00009462704,0.003491078,0.0001040868],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908822,0.0001548719,0.003145821,0.0004292467,0.001285089,0.000662306,0.00001085631,0.00001862577,0.003411001],"genre_scores_gemma":[0.9987825,0.0002009225,0.0002505702,0.0002182698,0.0001302857,0.00007456622,0.000001108307,0.00002226268,0.0003195725],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.64537,"threshold_uncertainty_score":0.3560084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1243958263553888,"score_gpt":0.4684013883971636,"score_spread":0.3440055620417748,"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."}}