{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001337662,0.0006229637,0.0005832356,0.0002705028,0.0004723471,0.0008449099,0.006863486,0.000303386,0.003164819],"category_scores_gemma":[0.002250198,0.000602322,0.0000795068,0.0003795253,0.0003822052,0.002036245,0.005154169,0.0008595662,0.09518804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007722899,"about_ca_system_score_gemma":0.0006461846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001392733,"about_ca_topic_score_gemma":0.0002653587,"domain_scores_codex":[0.9959453,0.0002475039,0.0005714722,0.001731264,0.000739292,0.00076521],"domain_scores_gemma":[0.9910621,0.002005645,0.0004306131,0.005976495,0.0002488113,0.0002763358],"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":[0.0000282458,0.0001594712,0.00003760331,0.0001836247,0.000075768,0.0001532122,0.00009090098,0.00000144716,0.000001905312,0.00004664819,0.9989277,0.0002934843],"study_design_scores_gemma":[0.0004849955,0.0005024357,0.00002960998,0.0006091502,0.0001281032,0.00005125743,0.00005153881,0.001288027,0.00001295528,0.000166144,0.9959385,0.0007372493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000004923267,0.000009534492,0.006616984,0.00002339926,0.00155137,0.000358908,0.9906456,0.0003150097,0.00047423],"genre_scores_gemma":[0.00002684227,0.0001475505,0.006845048,0.001015794,0.001039387,0.0000286895,0.9904106,0.00002817662,0.000457974],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09202322,"threshold_uncertainty_score":0.9996428,"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."}}