{"id":"W4402048137","doi":"10.1145/3690631","title":"T-Rec: Fine-Grained Language-Agnostic Program Reduction Guided by Lexical Syntax","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Syntax; Programming language; Reduction (mathematics); Natural language processing; Abstract syntax tree; Artificial intelligence","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":[0.000678729,0.0002369277,0.0002569907,0.0002990351,0.0001196885,0.0001249435,0.0003870548,0.0001867301,0.00001088098],"category_scores_gemma":[0.002439204,0.0002253461,0.0000945654,0.0005105615,0.00005550359,0.0001707942,0.00002490656,0.0004467592,0.00001074428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004923537,"about_ca_system_score_gemma":0.00004422303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009482848,"about_ca_topic_score_gemma":0.000001302391,"domain_scores_codex":[0.998547,0.0001649711,0.0002471963,0.0005555986,0.0001449887,0.000340305],"domain_scores_gemma":[0.9961993,0.003030384,0.00002664917,0.00057334,0.00004095561,0.0001293966],"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":[0.000008112876,0.00007486794,0.00001069497,0.0001271716,0.00006906418,0.00004455332,0.000663847,0.001583891,0.002454733,0.0005661341,0.005899044,0.9884979],"study_design_scores_gemma":[0.002919042,0.006974622,0.001334709,0.003514457,0.0009113926,0.01453172,0.000160129,0.5994504,0.1890113,0.07109649,0.1038217,0.006274058],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005930984,0.001144456,0.9691107,0.0008399004,0.001013637,0.000198845,0.00001139707,0.0217438,0.000006282328],"genre_scores_gemma":[0.1130455,0.00005534538,0.8863257,0.00006646891,0.00006866483,0.0001726422,0.000009154724,0.00003289638,0.0002237143],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9822238,"threshold_uncertainty_score":0.9189345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0649629231789791,"score_gpt":0.3495486032377718,"score_spread":0.2845856800587927,"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."}}