{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01204317,0.002803002,0.0018368,0.003372203,0.001798396,0.005701167,0.007386613,0.001549796,0.03932123],"category_scores_gemma":[0.04506695,0.00313847,0.002394933,0.003696571,0.002701435,0.01106906,0.009613873,0.006929241,0.03459992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003086228,"about_ca_system_score_gemma":0.006665038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00541607,"about_ca_topic_score_gemma":0.004739375,"domain_scores_codex":[0.9867578,0.002868147,0.002638637,0.001802271,0.005111709,0.0008212921],"domain_scores_gemma":[0.975369,0.008780937,0.00124877,0.009666024,0.004108401,0.0008268447],"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":[0.001787814,0.0006505305,0.00485898,0.001852832,0.0002853379,0.0003061882,0.001063129,0.01586829,0.005545378,0.03811789,0.7944457,0.1352178],"study_design_scores_gemma":[0.0009805107,0.0002506562,0.005718524,0.0005899467,0.0001215021,0.0005059029,0.0004340457,0.1675767,0.06547202,0.1815248,0.5762596,0.0005658076],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003690532,0.0001359772,0.2932478,0.0007814231,0.0002013315,0.001114657,0.05479307,0.6374072,0.008627973],"genre_scores_gemma":[0.08195586,0.0004482093,0.4053994,0.002436567,0.0001731527,0.01361278,0.2168271,0.2655804,0.01356636],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.03932123,"threshold_uncertainty_score":0.1315426,"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."}}