{"id":"W2972465897","doi":"10.1007/s10009-019-00530-6","title":"Diversity of graph models and graph generators in mutation testing","year":2019,"lang":"en","type":"article","venue":"International Journal on Software Tools for Technology Transfer","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Emberi Eroforrások Minisztériuma; Natural Sciences and Engineering Research Council of Canada; Magyar Tudományos Akadémia; Budapesti Műszaki és Gazdaságtudományi Egyetem","keywords":"Computer science; Test suite; Predicate abstraction; Random testing; Graph; Model-based testing; Theoretical computer science; Predicate (mathematical logic); Software quality; Programming language; Test case; Software; Software engineering; Model checking; Machine learning; Software development","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003621998,0.0001352918,0.0001997358,0.0009920273,0.0001369859,0.00006986558,0.0008233027,0.0001547,0.000001952164],"category_scores_gemma":[0.0004370459,0.0001289334,0.0000791834,0.0004356054,0.0000721038,0.00066955,0.0001806311,0.0002886193,9.666547e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005489747,"about_ca_system_score_gemma":0.00004413755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001643092,"about_ca_topic_score_gemma":0.000003757841,"domain_scores_codex":[0.99888,0.00002466926,0.0003286768,0.0002738771,0.000307904,0.000184904],"domain_scores_gemma":[0.9987747,0.0005012092,0.00008670385,0.0001810049,0.0004179002,0.00003846999],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001776988,0.0003433404,0.3905751,0.00005531672,0.000204214,0.00015991,0.001235167,0.007601483,0.001203656,0.1239298,0.0002300929,0.4742842],"study_design_scores_gemma":[0.001696416,0.0007455391,0.009124073,0.0003279725,0.00001383713,0.0004183487,0.00002264969,0.01336405,0.007160775,0.9667837,0.00004323369,0.0002993931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4833988,0.00004514564,0.5152939,0.0002701297,0.00019311,0.0001133322,0.000006759524,0.000665189,0.00001368855],"genre_scores_gemma":[0.8154672,0.0000209532,0.1843204,0.0001515778,0.0000148734,0.00001113075,0.000001835149,0.000008557595,0.000003504676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.842854,"threshold_uncertainty_score":0.5257754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03993430915760716,"score_gpt":0.2690731531534225,"score_spread":0.2291388439958153,"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."}}