{"id":"W4236722288","doi":"10.1145/1269899.1254904","title":"Synthetic designs","year":2007,"lang":"en","type":"article","venue":"ACM SIGMETRICS Performance Evaluation Review","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Communications Research Centre Canada","funders":"","keywords":"Computer science; Design of experiments; Reliability engineering; Statistical power; Variation (astronomy); Sample size determination; Sample (material); Statistical hypothesis testing; Software; Industrial engineering; Engineering; Statistics; 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"],"consensus_categories":[],"category_scores_codex":[0.01548488,0.0001598182,0.0002325434,0.0006248645,0.0001199977,0.0000769412,0.001812047,0.00005924995,0.0001624881],"category_scores_gemma":[0.02454101,0.0001445807,0.00007579573,0.005044169,0.00002585022,0.000597697,0.0003279848,0.0002310297,0.0006967089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002515674,"about_ca_system_score_gemma":0.0001990294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001683942,"about_ca_topic_score_gemma":2.916402e-7,"domain_scores_codex":[0.9967914,0.0001168434,0.0004659733,0.0004110479,0.001756504,0.0004582084],"domain_scores_gemma":[0.994983,0.002325021,0.000127016,0.001737958,0.0006750433,0.0001519291],"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":[9.755948e-7,0.00002666612,0.004920271,0.000515546,0.000008980224,0.000002423767,0.00002989724,0.0001947934,0.00004178936,0.000373345,0.001732935,0.9921524],"study_design_scores_gemma":[0.001763959,0.0008357227,0.4523291,0.007473436,0.0002676134,0.0002070465,0.00001217928,0.3827247,0.01045497,0.001166262,0.1406486,0.002116469],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03576613,0.13212,0.8270358,0.0009558544,0.000802897,0.001533529,6.130052e-7,0.0004546036,0.001330571],"genre_scores_gemma":[0.8577875,0.05478497,0.08597749,0.001007033,0.000113437,0.0001420038,0.000007787183,0.00002856385,0.000151169],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9900359,"threshold_uncertainty_score":0.9836757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1290392097846172,"score_gpt":0.380485539652118,"score_spread":0.2514463298675008,"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."}}