{"id":"W4402979393","doi":"10.1109/tse.2024.3469582","title":"LTM: Scalable and Black-Box Similarity-Based Test Suite Minimization Based on Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trent University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Science Foundation Ireland","keywords":"Computer science; Test suite; Suite; Scalability; Black box; Minification; Similarity (geometry); Test (biology); Software testing; Programming language; Artificial intelligence; Natural language processing; Test case; Software; Machine learning; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001606565,0.001679135,0.001468799,0.001945313,0.0005230513,0.001228931,0.003041398,0.001182556,0.002272235],"category_scores_gemma":[0.01039791,0.0005771971,0.001673191,0.001180014,0.0009957781,0.002358354,0.002607097,0.001739103,0.001018973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542569,"about_ca_system_score_gemma":0.002898772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005033147,"about_ca_topic_score_gemma":0.006445027,"domain_scores_codex":[0.9966059,0.0008353331,0.0002375367,0.000662583,0.00139098,0.0002677532],"domain_scores_gemma":[0.99552,0.00196418,0.0006514445,0.0008341954,0.0008231046,0.0002070307],"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":[0.0005219019,0.0004163557,0.004876078,0.0004906138,0.0002202691,0.0004125723,0.0002320451,0.3393781,0.0321418,0.01240705,0.008228276,0.6006749],"study_design_scores_gemma":[0.00003225071,0.0001601901,0.0003633985,0.00001224569,0.00002123528,0.0001099069,0.00003000486,0.9821755,0.009828903,0.006255525,0.0009962813,0.00001458758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03178565,0.0003180002,0.9539198,0.0001850899,0.00003783467,0.0002295153,0.0003411955,0.01205797,0.001124961],"genre_scores_gemma":[0.3965284,0.0001762051,0.5952758,0.0003778215,0.00005999994,0.0006499056,0.003016325,0.001365228,0.002550332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005033147,"threshold_uncertainty_score":0.01119214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01206797920159852,"score_gpt":0.2277017311682432,"score_spread":0.2156337519666446,"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."}}