{"id":"W4398451061","doi":"10.7910/dvn/bsungb/gbzgzj","title":"third pilot - cognitive abilities 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); Cognition; Computer science; Psychology; Biology; Neuroscience; Ecology","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":[0.001471061,0.002051616,0.001167899,0.002956432,0.000673894,0.001740218,0.00303626,0.002094104,0.04490206],"category_scores_gemma":[0.009164222,0.0004320658,0.001045382,0.002869628,0.0004068582,0.001062201,0.001711899,0.001857186,0.05321579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028772,"about_ca_system_score_gemma":0.001665872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01882182,"about_ca_topic_score_gemma":0.04357383,"domain_scores_codex":[0.9991444,0.0001449007,0.0001146502,0.0002148795,0.0002256899,0.00015534],"domain_scores_gemma":[0.9953584,0.001056681,0.0003380123,0.001047808,0.001646867,0.0005522097],"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":[0.0002437005,0.00008748498,0.004085309,0.0004324071,0.00004046779,0.00003738225,0.00003245268,0.0002926935,0.0001085279,0.0002066817,0.9897819,0.0046511],"study_design_scores_gemma":[0.00145077,0.0001640533,0.03631397,0.0004455032,0.000121908,0.0002431437,0.0003084545,0.002194996,0.001506947,0.002192428,0.9549802,0.00007774379],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001066375,0.00005396187,0.0001122835,0.0001231263,0.00005320533,0.00003645005,0.9972996,0.000441257,0.0008138047],"genre_scores_gemma":[0.001703785,0.00002401416,0.0003081211,0.00005241334,0.00001367528,0.0001420746,0.9966569,0.00006590853,0.001033108],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9550979,"threshold_uncertainty_score":0.1502123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04368191948941372,"score_gpt":0.2708479359243129,"score_spread":0.2271660164348992,"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."}}