{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006766988,0.001133987,0.000859855,0.007047432,0.001702258,0.002057732,0.002015878,0.001362792,0.008345058],"category_scores_gemma":[0.03696743,0.0005643333,0.00103776,0.01107875,0.001069562,0.001721726,0.003478131,0.001768595,0.008608325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001931545,"about_ca_system_score_gemma":0.002426275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01591032,"about_ca_topic_score_gemma":0.02447073,"domain_scores_codex":[0.9906394,0.002024087,0.001098422,0.001714898,0.004031648,0.0004916115],"domain_scores_gemma":[0.9147844,0.02769312,0.007956428,0.02252169,0.02404454,0.002999795],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001425821,0.0009450495,0.1081571,0.002963274,0.0004017396,0.001026082,0.00417343,0.002051653,0.004347702,0.00311735,0.7651052,0.1062855],"study_design_scores_gemma":[0.0003786199,0.000428479,0.4095989,0.0006181597,0.000181573,0.0005769014,0.002232572,0.003330108,0.007770487,0.002574615,0.5720909,0.0002188826],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.185349,0.001236334,0.009770012,0.001302441,0.0004380042,0.001156242,0.7776764,0.005831671,0.01723995],"genre_scores_gemma":[0.093944,0.0003680237,0.01253543,0.0003772372,0.0001355682,0.001739005,0.8812528,0.001380504,0.008267356],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.993233,"threshold_uncertainty_score":0.0357877,"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."}}