{"id":"W2112433871","doi":"10.1145/1134285.1134333","title":"On the success of empirical studies in the international conference on software engineering","year":2006,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Empirical research; Soundness; Computer science; Point (geometry); Software engineering; Software quality; Software; Quality (philosophy); Management science; Data science; Software development; Engineering; Programming language; Mathematics; Epistemology","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","bibliometrics"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3901805,0.00151332,0.001892061,0.01034325,0.005391782,0.01574033,0.00351994,0.004772105,0.006753711],"category_scores_gemma":[0.8209343,0.0009168242,0.001120844,0.01432511,0.0170562,0.0151328,0.007184146,0.005621204,0.001339868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01149913,"about_ca_system_score_gemma":0.00718197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002626201,"about_ca_topic_score_gemma":0.00294695,"domain_scores_codex":[0.447762,0.3929068,0.02762025,0.01630945,0.1118707,0.003530661],"domain_scores_gemma":[0.0476665,0.8069263,0.03653058,0.03316179,0.07370698,0.002007861],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002992081,0.00206549,0.1440974,0.01050369,0.002781742,0.0004082826,0.04668674,0.00434444,0.002350661,0.3145071,0.04611034,0.423152],"study_design_scores_gemma":[0.001425296,0.006983007,0.3470192,0.03585118,0.002281487,0.001240758,0.0571233,0.01434217,0.01807436,0.2210617,0.2935252,0.00107246],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4290594,0.1015163,0.08229239,0.1148473,0.006443825,0.00257252,0.001500911,0.0004114701,0.2613559],"genre_scores_gemma":[0.9655107,0.007835664,0.01385547,0.006524859,0.001228868,0.00121553,0.0003960005,0.0001891045,0.003243802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9896567,"threshold_uncertainty_score":0.752016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09787210732289231,"score_gpt":0.3613300767234555,"score_spread":0.2634579694005632,"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."}}