{"id":"W4280635309","doi":"10.1371/journal.pone.0268426","title":"Addressing the need for interactive, efficient, and reproducible data processing in ecology with the datacleanr R package","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data Analysis with R","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"Helmholtz-Gemeinschaft; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Workflow; Data science; Data quality; Data processing; Outlier; Data type; Data mining; Quality (philosophy); Database; Service (business); Artificial intelligence; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001568805,0.00009747095,0.0001753193,0.00009858283,0.0005639865,0.0003204013,0.00241856,0.00001216407,0.000009001542],"category_scores_gemma":[0.0003053367,0.00005660767,0.000009982145,0.0007250584,0.00009749462,0.0006399695,0.00294468,0.000268643,0.000001969577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003818736,"about_ca_system_score_gemma":0.00009155957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003836243,"about_ca_topic_score_gemma":0.0002013557,"domain_scores_codex":[0.9983256,0.0001972855,0.0001645731,0.0007659938,0.0003059177,0.0002406669],"domain_scores_gemma":[0.9970704,0.0003222065,0.0001707744,0.002359499,0.00005129319,0.00002580703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003632299,0.03318485,0.1918999,0.002575579,0.004232252,0.0005073327,0.1107527,0.02523788,0.1031652,0.01742195,0.1008568,0.4065332],"study_design_scores_gemma":[0.0008445724,0.0001939943,0.007806205,0.00009881966,0.000166914,0.00002266683,0.002139973,0.9843316,0.001711476,0.0002042339,0.002246503,0.0002330547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.859912,0.0007581398,0.1032476,0.03315304,0.0000943687,0.001900684,0.0003213533,0.0001501249,0.0004626739],"genre_scores_gemma":[0.9868762,0.000003926556,0.01197009,0.0007284147,0.00003895243,0.000133937,0.0001236339,0.00001264498,0.0001121832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9590937,"threshold_uncertainty_score":0.4494326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1763984246597676,"score_gpt":0.3123639623910735,"score_spread":0.1359655377313059,"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."}}