{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00153433,0.001926442,0.0008665344,0.001638467,0.0007273285,0.001504351,0.003499122,0.001100121,0.003863558],"category_scores_gemma":[0.006178726,0.0007044721,0.002363468,0.001079334,0.002127178,0.003424388,0.003079892,0.002701998,0.002066312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008814252,"about_ca_system_score_gemma":0.003910224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003214998,"about_ca_topic_score_gemma":0.005898043,"domain_scores_codex":[0.9972676,0.0005976339,0.000249798,0.0005898767,0.0009731796,0.0003219329],"domain_scores_gemma":[0.9954427,0.001202975,0.0004166219,0.002104613,0.0007108597,0.0001222619],"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":[0.0009564023,0.0008962805,0.01197548,0.002629417,0.0004339218,0.0009013906,0.001234093,0.04890608,0.1601714,0.08112842,0.060102,0.6306651],"study_design_scores_gemma":[0.0005290227,0.001396997,0.004892169,0.000335368,0.0006095523,0.001788849,0.0005689677,0.4878333,0.2528377,0.0998551,0.1489736,0.0003793331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05068131,0.000770163,0.8409871,0.0005551596,0.0002289216,0.000576186,0.001030555,0.09902516,0.006145407],"genre_scores_gemma":[0.2654741,0.0005095141,0.7040958,0.0009530962,0.00009859232,0.0008686104,0.004783936,0.01450394,0.008712461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003863558,"threshold_uncertainty_score":0.01292485,"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."}}