{"id":"W4402442339","doi":"10.1145/3650212.3652126","title":"LPR: Large Language Models-Aided Program Reduction","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Government of Canada; University of Waterloo","funders":"","keywords":"Computer science; Compiler; Programming language; JavaScript; Generality; Semantics (computer science); Debugging; Reduction (mathematics)","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000261389,0.00008648737,0.00007000597,0.0001057665,0.00005851423,0.0003207086,0.000322624,0.00004546338,0.00001237104],"category_scores_gemma":[0.00003356396,0.00006987316,0.00004752758,0.000399672,0.00001327976,0.0004562528,0.0001307597,0.0001113864,0.00006651272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002678459,"about_ca_system_score_gemma":0.00003714736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007439862,"about_ca_topic_score_gemma":0.000002068397,"domain_scores_codex":[0.9992037,0.00002210527,0.0001070043,0.0003069805,0.0001514042,0.0002088132],"domain_scores_gemma":[0.9994774,0.00004531964,0.00001295677,0.00038797,0.00002976346,0.00004660586],"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":[0.000001082586,0.00009794798,0.0000208859,0.00004200816,0.00001199993,0.000058938,0.001771537,0.00002700519,0.000251761,0.1805056,0.1432747,0.6739365],"study_design_scores_gemma":[0.00004819799,0.00007839256,0.00001747732,0.00006452284,0.000003902671,0.0001049325,0.00001580886,0.8352141,0.001703017,0.1575582,0.005039193,0.0001522038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002713124,0.0005151791,0.8984004,0.0006250374,0.0003656647,0.0001552729,8.310046e-7,0.08749774,0.009726704],"genre_scores_gemma":[0.5753335,0.00000481024,0.4231447,0.0000780345,0.00007500865,0.00004190524,0.000002513463,0.00000852945,0.001310956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8351871,"threshold_uncertainty_score":0.30926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02354237607111619,"score_gpt":0.3102948756575512,"score_spread":0.286752499586435,"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."}}