{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01196217,0.0006856302,0.0004496203,0.001799516,0.0003218545,0.0008977486,0.0006694994,0.0006362048,0.0007242637],"category_scores_gemma":[0.05344176,0.0004430265,0.0005420902,0.0008356686,0.0008081486,0.000785481,0.001364901,0.000821353,0.0002518825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006044924,"about_ca_system_score_gemma":0.0006692153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003801076,"about_ca_topic_score_gemma":0.008675653,"domain_scores_codex":[0.9896128,0.00430283,0.001493741,0.001510141,0.002397392,0.0006830902],"domain_scores_gemma":[0.938017,0.03849652,0.01178452,0.003806673,0.004931686,0.002963546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004851287,0.0004223292,0.9527535,0.00008715467,0.0004213645,0.0004131229,0.001902828,0.0002868143,0.01159768,0.00012922,0.0003603654,0.02677427],"study_design_scores_gemma":[0.00002698778,0.001470828,0.9954727,0.00001435129,0.00005837188,0.0002756889,0.0002671278,0.0001608883,0.002014015,0.00005052368,0.0001767165,0.00001172253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9984422,0.0002297368,0.0004576162,0.00003770689,0.00002132202,0.00002944869,0.0001180281,0.00001637908,0.0006476155],"genre_scores_gemma":[0.9977351,0.000138404,0.001288123,0.00005050597,0.000009546214,0.00005823689,0.0003505497,0.00002762905,0.0003419858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01196217,"threshold_uncertainty_score":0.06326276,"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."}}