{"id":"W2128309607","doi":"10.1088/1749-4699/8/1/014007","title":"SkData: data sets and algorithm evaluation protocols in Python","year":2015,"lang":"en","type":"article","venue":"Computational Science & Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"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; Scripting language; Benchmark (surveying); Algorithm; Set (abstract data type); Data structure; On the fly; Data mining; Programming language; Theoretical computer science; World Wide Web; Operating system","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":[0.004455702,0.0001022208,0.0001035429,0.0002157304,0.0001431673,0.000937777,0.001556069,0.00002714097,0.000002344195],"category_scores_gemma":[0.0007306664,0.00009217568,0.000008374013,0.0009912348,0.0002175179,0.007198435,0.001040674,0.0001198137,0.0000264849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000142283,"about_ca_system_score_gemma":0.001170416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008615493,"about_ca_topic_score_gemma":0.00002074495,"domain_scores_codex":[0.997382,0.0001482303,0.0002396358,0.0007937814,0.001215315,0.0002210322],"domain_scores_gemma":[0.9986321,0.0001082015,0.0001205849,0.0007881738,0.0002175225,0.0001334421],"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":[0.00001081384,0.0001901001,0.0115863,0.00001434291,0.000003648792,0.000006716088,0.0008516039,0.04004339,0.0001040896,0.04354638,0.002605764,0.9010369],"study_design_scores_gemma":[0.0003920565,0.00003523535,0.1135144,0.00002292246,0.000001744657,0.00001364264,0.00004024287,0.8645036,0.000008662435,0.01965261,0.001705703,0.000109175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01337629,0.00008207884,0.9809254,0.001769638,0.0002128978,0.002454484,0.00005255088,0.00007565498,0.001050984],"genre_scores_gemma":[0.7427831,0.000003301961,0.2555101,0.000292782,0.00008557094,0.0004426405,0.0008203692,0.000008162324,0.00005396904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9009277,"threshold_uncertainty_score":0.9043006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1567270387717614,"score_gpt":0.4233779894547364,"score_spread":0.266650950682975,"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."}}