{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002066766,0.0002614324,0.0001789039,0.0004843797,0.0001301714,0.0003019133,0.0002655254,0.0001265103,0.000009662934],"category_scores_gemma":[0.0001138747,0.0002702732,0.00008559308,0.0006818926,0.00003149967,0.0003580356,0.000003526949,0.0003578018,0.00001447407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009594816,"about_ca_system_score_gemma":0.00007834757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002638274,"about_ca_topic_score_gemma":0.000002214557,"domain_scores_codex":[0.9986759,0.0000240128,0.0002053584,0.0005072335,0.0002891005,0.0002983342],"domain_scores_gemma":[0.9978861,0.001424684,0.00002402616,0.0004934448,0.00005091288,0.000120865],"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":[0.000004475282,0.00007888707,0.00003810965,0.0001637552,0.000009704159,0.00003741865,0.0002234766,0.9870446,0.0001453884,0.00008144599,0.0005824695,0.01159029],"study_design_scores_gemma":[0.0001794759,0.0001343657,0.00003547582,0.0004461241,0.00001772635,0.00000752856,0.000001861235,0.9885599,0.009991651,0.0001877485,0.0001534424,0.0002846752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001432422,0.00008662547,0.9806431,0.0001952773,0.0003540704,0.0001784213,0.00003590108,0.01704603,0.0000281665],"genre_scores_gemma":[0.6632918,0.000004941491,0.3362948,0.0002320651,0.00002760001,0.00004264557,0.000004566166,0.00004160683,0.0000599433],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6618594,"threshold_uncertainty_score":0.999975,"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."}}