{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02356287,0.002779311,0.001503641,0.003915367,0.001923479,0.005620761,0.007657326,0.001607777,0.03593347],"category_scores_gemma":[0.07305114,0.003019367,0.002736683,0.004214821,0.003225302,0.008958138,0.009563694,0.006173934,0.02839256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003017343,"about_ca_system_score_gemma":0.007801754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00472255,"about_ca_topic_score_gemma":0.00384959,"domain_scores_codex":[0.9788478,0.005549573,0.004464858,0.002737076,0.00744296,0.000957866],"domain_scores_gemma":[0.9473678,0.02137238,0.002356532,0.0207144,0.007189311,0.0009995162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002808698,0.000909792,0.008012472,0.002029412,0.0005178063,0.0004444174,0.001070023,0.02856906,0.007654837,0.05913209,0.6901478,0.1987036],"study_design_scores_gemma":[0.001508777,0.0003720372,0.006947777,0.0008041254,0.0001521412,0.0005896875,0.000395027,0.2862187,0.09084247,0.221193,0.3903231,0.0006532143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004025256,0.0001191768,0.3899416,0.0006483903,0.0001842313,0.001207722,0.03888643,0.5591301,0.005857283],"genre_scores_gemma":[0.1005451,0.0003494797,0.5062348,0.001677262,0.0001605038,0.017264,0.1628444,0.201166,0.009758442],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.03593347,"threshold_uncertainty_score":0.1246138,"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."}}