{"id":"W4398722366","doi":"10.7910/dvn/bsungb/22lbes","title":"third pilot - cognitive intelligence test - data.tab","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); Computer science; Cognition; Psychology; Geology; Neuroscience","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001438436,0.0021476,0.001351074,0.003494615,0.0007026457,0.00187877,0.003270535,0.002187606,0.04967497],"category_scores_gemma":[0.009239239,0.000471726,0.001049641,0.003737577,0.0004014757,0.001096891,0.001787029,0.002026377,0.06032452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001188596,"about_ca_system_score_gemma":0.001966128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0197804,"about_ca_topic_score_gemma":0.04114295,"domain_scores_codex":[0.9990405,0.0001489901,0.0001330865,0.0002371478,0.0002633647,0.0001769287],"domain_scores_gemma":[0.9952741,0.0009495774,0.0003642411,0.001028675,0.00179507,0.0005882828],"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":[0.0001762819,0.0000675957,0.003369167,0.0003305279,0.00003325945,0.00003385893,0.00002328884,0.0002239268,0.00007826662,0.0001948765,0.9915717,0.003897274],"study_design_scores_gemma":[0.001167136,0.000127522,0.03274706,0.0004327939,0.0001013086,0.0002363353,0.0002599441,0.001729774,0.001129981,0.002128,0.95987,0.00007014124],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0007095625,0.00004500408,0.00007941068,0.0001020919,0.00004287375,0.00002668983,0.99803,0.0002992453,0.0006651689],"genre_scores_gemma":[0.001203542,0.00002139782,0.0002285571,0.00004134131,0.00001214318,0.0001087737,0.9975128,0.0000453665,0.0008260637],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.950325,"threshold_uncertainty_score":0.1661794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05564113560527996,"score_gpt":0.2872465183087988,"score_spread":0.2316053827035188,"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."}}