{"id":"W4389162832","doi":"10.1145/3611643.3613101","title":"Ad Hoc Syntax-Guided Program Reduction","year":2023,"lang":"en","type":"article","venue":"","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; Programming language; Abstract syntax tree; Debugging; Interpreter; Compiler; Grammar; Reduction (mathematics); Syntax; Parsing; Context (archaeology); Natural language processing; Linguistics","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":[0.0002841426,0.00007773707,0.00007411654,0.0001319325,0.00009165552,0.0001264414,0.0004195471,0.00004148404,0.000006859198],"category_scores_gemma":[0.000161189,0.00006721468,0.00003682908,0.0008804529,0.00002347165,0.0001910603,0.0001736927,0.00006797748,0.0002764768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002160078,"about_ca_system_score_gemma":0.00002807411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002466728,"about_ca_topic_score_gemma":7.669629e-7,"domain_scores_codex":[0.9991961,0.00002448952,0.0001217116,0.0002733333,0.0001691964,0.0002151427],"domain_scores_gemma":[0.9993331,0.00006381793,0.0000329084,0.0004608526,0.00005697825,0.00005227271],"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":[6.219117e-7,0.00002775636,0.0001547297,0.000006329257,0.000003416925,0.0000100807,0.0001414263,0.000005720614,0.0001531888,0.002476412,0.3614911,0.6355292],"study_design_scores_gemma":[0.0005703957,0.001139315,0.01116607,0.0002320755,0.00001761265,0.0007394069,0.00005039111,0.344152,0.02303615,0.4877997,0.1297475,0.001349412],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.05748154,0.0001333055,0.4316836,0.005789933,0.001312966,0.0006871895,7.203299e-7,0.4914368,0.01147398],"genre_scores_gemma":[0.22049,0.00002569853,0.776431,0.0001266165,0.00006175147,0.000120703,0.000003593564,0.00001141203,0.00272921],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6341798,"threshold_uncertainty_score":0.3553642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05371215305656096,"score_gpt":0.3313578660265555,"score_spread":0.2776457129699946,"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."}}