{"id":"W4398488223","doi":"10.7910/dvn/bsungb/ob3h7m","title":"third pilot - cognitive abilities test - Qualtrics questionnaire PDF version.pdf","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Test (biology); Psychology; Cognition; Cognitive psychology; Clinical psychology; Psychiatry; Biology","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001125928,0.0006334641,0.0005591329,0.0004175108,0.0006929261,0.0006174654,0.002571965,0.0004087852,0.0142833],"category_scores_gemma":[0.002814767,0.0006381726,0.0001444686,0.0005866992,0.0003684842,0.001280328,0.001385745,0.0009264724,0.4712648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000209112,"about_ca_system_score_gemma":0.0007475878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312811,"about_ca_topic_score_gemma":0.0001473328,"domain_scores_codex":[0.9962269,0.0003395785,0.0006028915,0.001239758,0.0008664524,0.0007244251],"domain_scores_gemma":[0.994963,0.001635569,0.0004996652,0.002118022,0.0004503272,0.0003334537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004556446,0.000199335,0.0001447185,0.0002682144,0.00005691648,0.0001503254,0.0001291164,0.00000690931,0.000002188729,0.00006289981,0.9987771,0.0001567352],"study_design_scores_gemma":[0.0006348335,0.000886168,0.00009232502,0.001256709,0.0001255422,0.00004890387,0.0000881608,0.000677664,0.00002715115,0.0002454287,0.995151,0.0007660937],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00002089932,0.00001179189,0.0079777,0.00003221761,0.001899277,0.000378657,0.9884408,0.0002914331,0.0009472733],"genre_scores_gemma":[0.00009423967,0.000205245,0.003330053,0.001014328,0.0006079119,0.000039862,0.9922178,0.00002459291,0.002465935],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4569815,"threshold_uncertainty_score":0.999607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01836904038498044,"score_gpt":0.2477808849300534,"score_spread":0.229411844545073,"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."}}