{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001324367,0.0006327362,0.0005461488,0.000297223,0.0004372545,0.0008064778,0.008820865,0.0003099625,0.002889083],"category_scores_gemma":[0.002052409,0.0006180455,0.00007305491,0.0005643169,0.0003080133,0.001880296,0.006017812,0.001006315,0.1572696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006783172,"about_ca_system_score_gemma":0.0005702066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000943,"about_ca_topic_score_gemma":0.0002082276,"domain_scores_codex":[0.995799,0.0002166833,0.0006130405,0.001848859,0.0007460429,0.0007763809],"domain_scores_gemma":[0.9915202,0.0015764,0.0004987188,0.005835295,0.00025183,0.0003175202],"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":[0.00002658539,0.0001665603,0.000015718,0.0001133901,0.00006838449,0.0003312963,0.00005563466,0.000003569707,0.000002596601,0.00004689901,0.9978985,0.001270846],"study_design_scores_gemma":[0.0002140265,0.0004724944,0.00001067804,0.0007187686,0.0001211466,0.00008963189,0.00002633913,0.004680227,0.00003462708,0.0001608616,0.9927158,0.0007553866],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[8.632223e-7,0.00000904774,0.08891656,0.00001768062,0.001472253,0.0003202911,0.9086859,0.0002554599,0.0003219247],"genre_scores_gemma":[0.00002851646,0.0002854885,0.01376972,0.001121361,0.0008801976,0.00002126175,0.9836184,0.00002745728,0.0002476198],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1543806,"threshold_uncertainty_score":0.9996271,"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."}}