{"id":"W4394927149","doi":"10.1007/s10270-024-01170-4","title":"Improving repair of semantic ATL errors using a social diversity metric","year":2024,"lang":"en","type":"article","venue":"Software & Systems Modeling","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal; McGill University; Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Metric (unit); Diversity (politics); Natural language processing; Information retrieval; Data science; Artificial intelligence; Sociology","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":[],"consensus_categories":[],"category_scores_codex":[0.005366365,0.001014694,0.001284065,0.004667362,0.001563401,0.001588762,0.001875844,0.001495983,0.001731159],"category_scores_gemma":[0.03352158,0.0003496292,0.000795103,0.002256979,0.001127025,0.004970568,0.00401035,0.001186763,0.0003986854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118351,"about_ca_system_score_gemma":0.001764582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002414712,"about_ca_topic_score_gemma":0.005484502,"domain_scores_codex":[0.9903077,0.003069773,0.0006532391,0.001102493,0.004265956,0.0006007965],"domain_scores_gemma":[0.9626982,0.01568116,0.005128487,0.006651221,0.008387726,0.001453174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001331127,0.001330046,0.06775519,0.0004241581,0.0004337798,0.0005345328,0.001439326,0.2221719,0.0468562,0.01329341,0.004558485,0.6398718],"study_design_scores_gemma":[0.00009466495,0.001240482,0.01432497,0.00005823134,0.0002199282,0.0004039326,0.0009154584,0.9300625,0.02627756,0.02324528,0.003082753,0.00007423014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5537392,0.0006902659,0.4354294,0.0006012906,0.0001280034,0.0001604591,0.0003078475,0.003458338,0.005485164],"genre_scores_gemma":[0.9231866,0.00007396557,0.07523319,0.00006240708,0.00005136464,0.00003601165,0.0003309668,0.0001666594,0.000858782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005366365,"threshold_uncertainty_score":0.02838039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.055793967027818,"score_gpt":0.2822911530338823,"score_spread":0.2264971860060643,"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."}}