{"id":"W3152754465","doi":"10.5281/zenodo.3519618","title":"Dataset of A Large-scale Study about Quality and Reproducibility of Jupyter Notebooks / Understanding and Improving the Quality and Reproducibility of Jupyter Notebooks","year":2019,"lang":"en","type":"dataset","venue":"Figshare","topic":"Education and Learning Interventions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reproducibility; Quality (philosophy); Scale (ratio); Computer science; Data quality; Data mining; Data science; Psychology; Reliability engineering; Statistics; Engineering; Mathematics; Cartography; Geography; Operations management; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01198289,0.0003642979,0.0009211157,0.0001573633,0.0002177272,0.0001540535,0.001063199,0.0002254143,0.001295133],"category_scores_gemma":[0.01109582,0.000290704,0.0001586068,0.000191718,0.000183418,0.0002919524,0.002120152,0.0006749185,0.000008899961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006859097,"about_ca_system_score_gemma":0.0002311821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001042648,"about_ca_topic_score_gemma":0.0008147903,"domain_scores_codex":[0.9926051,0.001503746,0.001719456,0.003293702,0.0005665706,0.0003113643],"domain_scores_gemma":[0.9855273,0.001053818,0.001960307,0.01096912,0.0003725551,0.0001168666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00007755215,0.000901092,0.0126475,0.008087682,0.0001676724,0.000001497967,0.005805626,0.00000358516,0.00008666323,0.00005054812,0.9715951,0.0005754597],"study_design_scores_gemma":[0.002072686,0.0008531744,0.8214646,0.003459993,0.0002686124,0.00001447166,0.004644282,0.0004641731,0.0006849259,0.0005156976,0.1644276,0.001129798],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02479499,0.000230203,0.00008544215,0.000203209,0.0002439379,0.001338636,0.9730659,0.00001992798,0.00001776334],"genre_scores_gemma":[0.1159055,0.000004463139,0.0002249628,0.0001572112,0.00006204315,0.0000722453,0.8834448,0.00001602523,0.0001126543],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.8088171,"threshold_uncertainty_score":0.9999545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2369330848068405,"score_gpt":0.4178144840514952,"score_spread":0.1808813992446547,"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."}}