{"id":"W3172682396","doi":"10.1162/99608f92.8bb28793","title":"The Building Blocks of Statistical Education in the Data Science Ecosystem","year":2021,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ecosystem; Data science; Environmental science; Environmental resource management; Computer science; Ecology; 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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02494943,0.0001403298,0.0003233534,0.0001464871,0.0006653403,0.001233736,0.03371926,0.00001612514,0.00004206243],"category_scores_gemma":[0.008746939,0.00007877979,0.00002584274,0.007435407,0.000992078,0.006885674,0.00936281,0.000196468,0.0001173512],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008736226,"about_ca_system_score_gemma":0.007340629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000619069,"about_ca_topic_score_gemma":0.0001680546,"domain_scores_codex":[0.9949085,0.000405248,0.0007272977,0.001456689,0.001980061,0.0005222638],"domain_scores_gemma":[0.9847987,0.0007583501,0.0003406215,0.01347019,0.0004926841,0.0001394432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[8.255843e-7,0.0001824908,0.0004794633,0.0006235457,0.00001007641,0.00001981263,0.0001003591,0.000005810746,0.001073619,0.410523,0.03015772,0.5568233],"study_design_scores_gemma":[0.00007308503,0.00001615968,0.002400703,0.002481626,0.00006618269,0.0001885063,0.0001715993,0.08350869,0.0002873335,0.0009230645,0.9096445,0.0002385271],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002442169,0.08978606,0.8661001,0.02313457,0.003295935,0.002952287,0.003411936,0.0001353773,0.008741581],"genre_scores_gemma":[0.2495193,0.2186564,0.5224229,0.007307416,0.0003204093,0.0001180174,0.001489741,0.00003035612,0.0001355925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8794868,"threshold_uncertainty_score":0.9998031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06011675050366747,"score_gpt":0.3821871329555472,"score_spread":0.3220703824518797,"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."}}