{"id":"W2942737328","doi":"10.1093/gigascience/giz035","title":"Datastorr: a workflow and package for delivering successive versions of 'evolving data' directly into R","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Software versioning; Data sharing; Process (computing); Software; Software engineering; Cornerstone; Data science; Data mining; Information retrieval; Database; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.00524648,0.0001059748,0.000213484,0.0002627473,0.0003187175,0.0004737937,0.003074958,0.00002435075,0.0001287675],"category_scores_gemma":[0.005033305,0.00008256293,0.00003745061,0.001098075,0.0002523259,0.001408701,0.003139126,0.0000608357,0.00008537572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002217777,"about_ca_system_score_gemma":0.00007349656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001704407,"about_ca_topic_score_gemma":0.00008749374,"domain_scores_codex":[0.9971293,0.00005621268,0.0003855548,0.001142191,0.0009991297,0.0002876045],"domain_scores_gemma":[0.9952947,0.001805194,0.0002305025,0.002338524,0.000211857,0.0001191434],"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":[0.00006770132,0.0001371617,0.04234663,0.0001053509,0.00003182454,0.000009165353,0.003860614,0.0007641962,0.03254876,0.002411897,0.09591746,0.8217992],"study_design_scores_gemma":[0.0009868358,0.0002046914,0.03286988,0.0002845229,0.0000424188,0.000005928319,0.004063468,0.8678613,0.002908164,0.006108987,0.08412275,0.0005411026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7509694,0.000364115,0.2436549,0.0003721844,0.001977199,0.0004997628,0.0004055728,0.00004950433,0.001707423],"genre_scores_gemma":[0.9669881,0.000007641917,0.03233216,0.00006602386,0.00002713204,0.000003269538,0.00004054086,0.000004654561,0.0005304441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8670971,"threshold_uncertainty_score":0.60257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1117146732902034,"score_gpt":0.3812909210249006,"score_spread":0.2695762477346972,"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."}}