{"id":"W2475602767","doi":"10.25080/majora-8b375195-004","title":"SkData: Data Sets and Algorithm Evaluation Protocols in Python","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Rowland Institute at Harvard; National Science Foundation","keywords":"Python (programming language); Computer science; Upload; Parsing; Benchmark (surveying); Scripting language; Algorithm; Set (abstract data type); Data mining; Data set; Programming language; Theoretical computer science; Information retrieval; Artificial intelligence; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005335463,0.0001165277,0.0001597022,0.0002814754,0.0001399571,0.0006830572,0.003919029,0.0000446549,0.00001188919],"category_scores_gemma":[0.001627509,0.00007965659,0.0000104983,0.001515287,0.0004682746,0.004205823,0.001552465,0.0002015858,0.000006009427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004507761,"about_ca_system_score_gemma":0.00037951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006747979,"about_ca_topic_score_gemma":0.00005403582,"domain_scores_codex":[0.9977264,0.00004239921,0.0003938225,0.0007111608,0.0008542337,0.0002719186],"domain_scores_gemma":[0.9985355,0.00007950728,0.0003285147,0.0005684296,0.0004266641,0.00006136941],"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":[0.000002755375,0.00007844544,0.1982958,0.00005934389,0.000001582383,9.771308e-8,0.00180713,0.0000103511,0.007377317,0.01820861,0.0003006461,0.7738579],"study_design_scores_gemma":[0.0002149621,0.00003357032,0.3685924,0.0001565052,0.000001946725,0.000004121652,0.0003500079,0.615091,0.001435517,0.01361904,0.0003963003,0.000104658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9401301,0.0001594926,0.01058986,0.01553092,0.000531951,0.01947366,0.00003120963,0.0001735315,0.01337927],"genre_scores_gemma":[0.9719181,0.00001474868,0.02697645,0.00004277349,0.00001491765,0.001006367,0.000003975017,0.000002964601,0.00001969171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7737532,"threshold_uncertainty_score":0.7282597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08828722234852654,"score_gpt":0.368364488690674,"score_spread":0.2800772663421474,"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."}}