{"id":"W4398709502","doi":"10.7910/dvn/2qzhpa/8lqs8u","title":"data_clean.do","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Environmental science","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","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004253844,0.0005692139,0.0007148899,0.0003395498,0.0001608676,0.001196376,0.01083921,0.0002829482,0.0110794],"category_scores_gemma":[0.0005260063,0.0005592615,0.0002096596,0.0009536498,0.0001089596,0.002212281,0.007042388,0.0007903992,0.6943976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008711997,"about_ca_system_score_gemma":0.0002983022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002351757,"about_ca_topic_score_gemma":0.00008120957,"domain_scores_codex":[0.9958962,0.0001862386,0.0005940152,0.001728393,0.001012408,0.0005827738],"domain_scores_gemma":[0.9908763,0.0001256818,0.0004253425,0.008026842,0.00008815726,0.0004576515],"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":[0.000006479047,0.0000576114,0.000001032881,0.00006289939,0.0001530787,0.000557338,0.00001395888,0.000003102516,0.000004004425,0.0005836186,0.99622,0.002336879],"study_design_scores_gemma":[0.000254619,0.0000456526,0.000006165843,0.00005184195,0.0001795899,0.00002974096,0.00001106566,0.0007319315,0.000009296499,0.00006379864,0.9980046,0.0006116622],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[8.139045e-8,0.000001590886,0.01634333,0.00004216635,0.0008700465,0.0001987947,0.9819986,0.0002300904,0.0003152536],"genre_scores_gemma":[9.952078e-7,0.0003104486,0.01008242,0.002598169,0.000403658,0.00001830108,0.9864177,0.00002587123,0.0001424386],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.6833182,"threshold_uncertainty_score":0.9998405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01846891884578107,"score_gpt":0.24243278595639,"score_spread":0.2239638671106089,"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."}}