{"id":"W4366777692","doi":"10.1111/2041-210x.14113","title":"Improving ecological data science with workflow management software","year":2023,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Centre For Cold Ocean Resources Engineering","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Geological Survey; National Science Foundation","keywords":"Workflow; Computer science; Modular design; Workflow management system; Scripting language; Data science; Cyberinfrastructure; Software engineering; Software; Pipeline (software); Documentation; Database","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.03676891,0.0001041053,0.0001947549,0.0009400494,0.0005321353,0.0002278995,0.001563742,0.00006315795,0.00004631216],"category_scores_gemma":[0.006351348,0.00007281686,0.0000144241,0.003894049,0.0006189164,0.0006162042,0.003277367,0.0001477864,0.0001163513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001010309,"about_ca_system_score_gemma":0.00006512937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000206569,"about_ca_topic_score_gemma":0.0002064208,"domain_scores_codex":[0.996728,0.0005275016,0.0003811817,0.001324288,0.0005580134,0.000481039],"domain_scores_gemma":[0.996627,0.001726281,0.0001271335,0.001357887,0.00008169793,0.00008001048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002504721,0.00005060968,0.1985276,0.00000814763,0.000006155725,0.00003673182,0.00007123761,0.001272391,0.00003350592,0.003090759,0.002669716,0.794208],"study_design_scores_gemma":[0.0002320751,0.0000538182,0.8552897,0.000007966922,0.000008820209,0.000006746672,0.0005323773,0.1159347,0.000004328875,0.02531257,0.002522654,0.00009421422],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3119279,0.00004432621,0.6840518,0.0005549982,0.001559263,0.0002944947,0.000008922986,0.0001576003,0.001400719],"genre_scores_gemma":[0.3912671,0.00001275498,0.6077198,0.00008649188,0.00002907253,0.00001755617,0.00001296535,0.000003916225,0.0008503327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7941139,"threshold_uncertainty_score":0.9918491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1930758055602569,"score_gpt":0.4683509783682548,"score_spread":0.2752751728079978,"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."}}