{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001236419,0.0002430912,0.0004166279,0.0006061833,0.0005446203,0.0002203475,0.0007449157,0.0001557803,8.200868e-7],"category_scores_gemma":[0.0004917876,0.0002392078,0.0002837425,0.001370262,0.00004025092,0.0005637289,0.001156544,0.0002622372,0.000004999079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002314189,"about_ca_system_score_gemma":0.0001991674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005089654,"about_ca_topic_score_gemma":0.000004080676,"domain_scores_codex":[0.9976663,0.0001250766,0.0005385515,0.0006586299,0.0005945908,0.0004168791],"domain_scores_gemma":[0.9986686,0.0003156615,0.0001748605,0.0005284047,0.0002313407,0.00008109813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006542919,0.0005277799,0.1351893,0.02437572,0.001411678,0.001359334,0.04517721,0.610596,0.002577017,0.02274377,0.008189547,0.1477873],"study_design_scores_gemma":[0.00007154067,0.00003407697,0.00003213157,0.0006513167,0.00005529511,0.00005581676,0.00005631059,0.9960989,0.0000249975,0.002645415,0.00001286716,0.0002613373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1158333,0.002151225,0.862298,0.0000132325,0.0009051512,0.0002005727,0.000005249504,0.01857516,0.00001817909],"genre_scores_gemma":[0.8290654,0.000003028545,0.1707152,0.00001454169,0.0001434595,0.000007064237,0.000001432279,0.00002801856,0.00002189539],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.713232,"threshold_uncertainty_score":0.9754611,"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."}}