{"id":"W2159715729","doi":"10.1145/1852786.1852789","title":"Can we evaluate the quality of software engineering experiments?","year":2010,"lang":"en","type":"article","venue":"","topic":"Software Engineering Techniques and Practices","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Usability; Computer science; Checklist; Quality (philosophy); Software quality; Reliability (semiconductor); Context (archaeology); Process (computing); Quality Score; Software; Software engineering; Data science; Software development; Psychology; Human–computer interaction; Engineering; Operations management","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":[0.0007510505,0.00009275531,0.0001054358,0.00003688754,0.00004107142,0.00005825957,0.0008030649,0.00004384035,0.00005128497],"category_scores_gemma":[0.0005153014,0.00006056643,0.00004980209,0.0001677063,0.00001863532,0.0002120961,0.0001894101,0.0001984172,0.000004353654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007749614,"about_ca_system_score_gemma":0.00002842525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001757142,"about_ca_topic_score_gemma":0.00001301115,"domain_scores_codex":[0.9992513,0.0000295518,0.0001870088,0.0001542706,0.0002352549,0.0001426155],"domain_scores_gemma":[0.998639,0.0005241391,0.00005191912,0.0006845957,0.00005815377,0.00004214117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001226621,0.0001657306,0.00696753,0.0001458489,0.0001273948,0.000006291131,0.004440084,0.001360473,0.1549759,0.741554,0.003084422,0.08716005],"study_design_scores_gemma":[0.0007172728,0.0002299052,0.03429094,0.00007308793,0.00002786318,0.00005162607,0.0001073005,0.08948134,0.7830105,0.01495848,0.07587922,0.001172403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.072703,0.0001020507,0.9240505,0.001510105,0.0005679981,0.0001205549,0.000001316975,0.0007472067,0.0001972789],"genre_scores_gemma":[0.6610458,0.000009663958,0.3387696,0.0000611168,0.00002936327,0.00001787244,2.863662e-7,0.000006027421,0.00006028876],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7265955,"threshold_uncertainty_score":0.2469827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04263385987164619,"score_gpt":0.3358986261512139,"score_spread":0.2932647662795677,"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."}}