{"id":"W4390092823","doi":"10.48550/arxiv.2312.13064","title":"LPR: Large Language Models-Aided Program Reduction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Government of Canada; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Programming language; JavaScript; Compiler; Reduction (mathematics); Debugging","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":[0.001527654,0.002246276,0.0009145139,0.00156295,0.000699057,0.00127022,0.003341203,0.0009585603,0.006365473],"category_scores_gemma":[0.005026017,0.00103486,0.003206268,0.001031566,0.001357045,0.003216825,0.002819184,0.002931079,0.002382808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200868,"about_ca_system_score_gemma":0.00326255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005327521,"about_ca_topic_score_gemma":0.01220103,"domain_scores_codex":[0.9974554,0.0007449021,0.0001300658,0.0005511522,0.0009274656,0.0001909795],"domain_scores_gemma":[0.9973325,0.001216021,0.0002131202,0.0008529891,0.0003379312,0.00004749825],"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":[0.0004492223,0.0003158382,0.003237555,0.001302051,0.0002350225,0.0004635463,0.0007039465,0.2384668,0.0417225,0.04991256,0.04878049,0.6144105],"study_design_scores_gemma":[0.00009211365,0.0001225511,0.0003554396,0.00005916417,0.00008543854,0.0001552895,0.000106044,0.9094436,0.02638423,0.03743082,0.02571786,0.0000473994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009133654,0.0003916954,0.9149687,0.0003303172,0.0000549162,0.0001788226,0.0006183761,0.07172661,0.002596943],"genre_scores_gemma":[0.119571,0.0003233064,0.8637127,0.0004588072,0.00004461072,0.0004862406,0.003603637,0.007755216,0.004044504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006365473,"threshold_uncertainty_score":0.02129465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09144310366350977,"score_gpt":0.2306588627671377,"score_spread":0.1392157591036279,"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."}}