{"id":"W2115796408","doi":"10.1109/mise.2007.2","title":"A Framework for Empirical Evaluation of Model Comprehensibility","year":2007,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Key (lock); Quality (philosophy); Empirical research; Grounded theory; Human–computer interaction; Qualitative research","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":[0.002903314,0.00004847388,0.00008334022,0.00006897861,0.00002085328,0.00001464662,0.0003444886,0.00005787069,0.000008056554],"category_scores_gemma":[0.002250394,0.00004299105,0.00004245679,0.0002537602,0.0000211063,0.00009352012,0.00009216324,0.00007776505,0.000003349217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006425306,"about_ca_system_score_gemma":0.0001106271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003428034,"about_ca_topic_score_gemma":0.000002178107,"domain_scores_codex":[0.9988514,0.00002185697,0.0001595142,0.0001998151,0.0005864043,0.0001810094],"domain_scores_gemma":[0.9971015,0.001884479,0.00002098811,0.0004604608,0.000476114,0.00005639651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007260255,0.0005045376,0.0562851,0.0001560294,0.0000537441,0.000001058169,0.002236723,0.2858079,0.002063355,0.4008355,0.002465021,0.2495183],"study_design_scores_gemma":[0.0001432061,0.00002876032,0.030775,0.00000472906,0.00000227023,4.244221e-7,0.000003796889,0.8772972,0.002575169,0.08911078,0.00001692203,0.00004177777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.21007,0.00001992807,0.7892662,0.000126407,0.00006151613,0.0002336806,5.059647e-7,0.00009221327,0.0001295785],"genre_scores_gemma":[0.5403678,1.025986e-7,0.4595737,0.00002965006,0.00001001659,0.000006993054,2.825292e-7,0.000002137636,0.000009230951],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5914892,"threshold_uncertainty_score":0.2694094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2276443662194862,"score_gpt":0.4608701870562838,"score_spread":0.2332258208367976,"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."}}