{"id":"W2161694107","doi":"10.1145/2034863.2034873","title":"Repeatability and workability evaluation of SIGMOD 2011","year":2011,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Repeatability; Executable; Computer science; Process (computing); Statistics; Operating system; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1583614,0.001154887,0.001505571,0.01222464,0.003215079,0.007347183,0.002721819,0.00186341,0.002938565],"category_scores_gemma":[0.4475909,0.000665376,0.00165293,0.008223243,0.00204838,0.004864079,0.006249575,0.001836283,0.003149112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002607024,"about_ca_system_score_gemma":0.003616879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002596654,"about_ca_topic_score_gemma":0.002549262,"domain_scores_codex":[0.7594117,0.1075165,0.02562325,0.01595291,0.08671173,0.004784016],"domain_scores_gemma":[0.4315845,0.2324568,0.04168816,0.1241035,0.1595955,0.01057154],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.006542405,0.003093462,0.3048047,0.003570271,0.00217541,0.0004396537,0.01078563,0.01004959,0.01430078,0.009156674,0.1304938,0.5045876],"study_design_scores_gemma":[0.00107321,0.007207567,0.668603,0.0008110285,0.0009408839,0.001412943,0.005871598,0.05293326,0.04346526,0.01777779,0.1989438,0.0009597395],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8342363,0.006395853,0.06766856,0.006827115,0.003886247,0.004973188,0.01730976,0.01841901,0.040284],"genre_scores_gemma":[0.9151257,0.0006348221,0.04816952,0.0005214484,0.0009424173,0.003299776,0.02278153,0.002143001,0.00638171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8416386,"threshold_uncertainty_score":0.8375052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5113276891992731,"score_gpt":0.4290325120509692,"score_spread":0.08229517714830392,"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."}}