{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2346547,0.003201296,0.002060989,0.01949272,0.003405126,0.01188606,0.004419778,0.004717398,0.005599382],"category_scores_gemma":[0.5980626,0.001422193,0.00342722,0.01453951,0.0175019,0.02189794,0.01330298,0.006631928,0.0006541425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006046576,"about_ca_system_score_gemma":0.005161116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002921959,"about_ca_topic_score_gemma":0.001895924,"domain_scores_codex":[0.6948704,0.2375915,0.01656504,0.01361487,0.0344692,0.002888996],"domain_scores_gemma":[0.3608618,0.5231604,0.03046203,0.05859353,0.0249472,0.001974968],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005576048,0.001592688,0.04764707,0.002105822,0.0008224606,0.0002789891,0.03200618,0.01977891,0.003780478,0.7226422,0.005568871,0.1632187],"study_design_scores_gemma":[0.0004449357,0.00167862,0.03928492,0.002348194,0.000304935,0.0005241261,0.01546299,0.117546,0.003569466,0.7995271,0.01882134,0.0004873766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07151946,0.000835301,0.8921289,0.00217432,0.0001126819,0.003768027,0.0008574775,0.0005405243,0.02806332],"genre_scores_gemma":[0.5533111,0.000303163,0.4234243,0.0005307544,0.0000533436,0.02064769,0.0009003722,0.0002421536,0.0005871069],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2346547,"threshold_uncertainty_score":0.943807,"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."}}