{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02923631,0.0001286875,0.0002790565,0.0001984162,0.0001240732,0.00008665833,0.001254164,0.00005997034,0.002588721],"category_scores_gemma":[0.01905989,0.0000964272,0.00008954822,0.0005072486,0.0002473075,0.0003665652,0.001107587,0.00009892801,0.0001419334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004002747,"about_ca_system_score_gemma":0.00007111008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005382609,"about_ca_topic_score_gemma":0.0002025817,"domain_scores_codex":[0.9954847,0.000678572,0.0008279699,0.001078878,0.001708369,0.0002215662],"domain_scores_gemma":[0.9934971,0.001355622,0.0003627854,0.003895067,0.0007788648,0.0001105093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000454392,0.0001244865,0.195572,0.000006205154,0.00001101733,4.226884e-7,0.0007073215,0.0000103017,0.00004340901,0.0001859572,0.00475834,0.7985351],"study_design_scores_gemma":[0.0003864723,0.0001309168,0.6933794,0.00001603536,0.00006608758,0.000001843389,0.0007221645,0.01302533,0.0006670111,0.2875907,0.003818458,0.000195591],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848324,0.0001172159,0.004014264,0.000189967,0.001046503,0.0003876138,0.00001427301,0.0000407243,0.009357054],"genre_scores_gemma":[0.9895754,0.000005268927,0.009863071,0.00002702118,0.00003671002,0.00001241605,0.000004997981,0.000005296418,0.0004698409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7983395,"threshold_uncertainty_score":0.9996055,"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."}}