{"id":"W2281407436","doi":"10.1002/spe.2382","title":"DataMill: a distributed heterogeneous infrastructure forrobust experimentation","year":2015,"lang":"en","type":"article","venue":"Software Practice and Experience","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmarking; Dilemma; Computer science; Competition (biology); Empirical research; Compiler; Process (computing); Data science; 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":[0.0001845741,0.0001416192,0.0001176357,0.00005211848,0.0001738906,0.0003107151,0.0004512429,0.00006336094,0.000004023559],"category_scores_gemma":[0.0008035271,0.0001327237,0.00001961141,0.000278855,0.00006692219,0.001887009,0.0003332536,0.0001089841,0.000007606518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004805482,"about_ca_system_score_gemma":0.00007319416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004657913,"about_ca_topic_score_gemma":8.398873e-7,"domain_scores_codex":[0.9988625,0.00008620079,0.0001896787,0.000388511,0.0002586845,0.0002144207],"domain_scores_gemma":[0.9989417,0.0001266679,0.0001415208,0.0004163933,0.0001995261,0.0001741693],"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":[0.0006692726,0.001090876,0.01546309,0.0001290168,0.0002341177,0.0007668967,0.3314026,0.1106625,0.00188024,0.03127784,0.09504505,0.4113785],"study_design_scores_gemma":[0.004024892,0.001758454,0.001732563,0.0001651608,0.00007309836,0.00375858,0.02434118,0.4819632,0.04252469,0.01274745,0.423743,0.003167782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01411727,0.0005376952,0.9839334,0.0003510689,0.0001957274,0.0001227815,0.000005218123,0.0005756538,0.0001611435],"genre_scores_gemma":[0.4956663,0.00007696456,0.5032368,0.000905043,0.00003110529,0.000033112,0.00002658455,0.000007206464,0.0000168847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.481549,"threshold_uncertainty_score":0.5412313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02637679283596986,"score_gpt":0.3103458532838202,"score_spread":0.2839690604478504,"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."}}