{"id":"W2892938424","doi":"10.1109/bigdata.2018.8622095","title":"Predicting computational reproducibility of data analysis pipelines in large population studies using collaborative filtering","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Compute Canada","keywords":"Reproducibility; Computer science; Pipeline transport; Population; Process (computing); Set (abstract data type); Pipeline (software); Data mining; Relevance (law); Speedup; Variance (accounting); Statistics; Mathematics; Parallel computing; Engineering","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":[0.003578097,0.0001882706,0.0006058287,0.0005532008,0.00008804361,0.0001362205,0.001205495,0.00008779803,0.00001385269],"category_scores_gemma":[0.001680013,0.0001796869,0.00006419496,0.002220969,0.00005677084,0.0007759637,0.005886096,0.0001355138,8.161402e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009346738,"about_ca_system_score_gemma":0.0001770011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003806814,"about_ca_topic_score_gemma":0.001101021,"domain_scores_codex":[0.9963511,0.000248201,0.001006011,0.001805345,0.000423977,0.0001654171],"domain_scores_gemma":[0.9948638,0.0001550815,0.0007112644,0.003260435,0.0009752482,0.00003415614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006391825,0.0001718023,0.5800842,0.0002719125,0.0007659906,0.000002145272,0.001931993,0.4138791,0.0000152212,0.002213265,0.0001801968,0.0004777279],"study_design_scores_gemma":[0.0001196358,0.000008290408,0.04060713,0.0001171008,0.0001399656,3.01015e-7,0.0002794714,0.9555737,0.00004815927,0.002945714,0.000009507625,0.0001509835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1438075,0.0001512202,0.8548186,0.00008451045,0.0002164183,0.0001952352,0.0006277337,0.0000662231,0.00003253406],"genre_scores_gemma":[0.7005914,0.00002742422,0.2970994,0.00003819516,0.00008447874,0.000002150472,0.002133882,0.000006026822,0.0000170215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5577192,"threshold_uncertainty_score":0.7336597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.189093103643665,"score_gpt":0.4506390377404407,"score_spread":0.2615459340967757,"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."}}