{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003474481,0.0002741816,0.0002703152,0.0003655612,0.0001899765,0.0001891118,0.001584808,0.0003014214,0.000006504285],"category_scores_gemma":[0.00002202951,0.0003279449,0.000192611,0.0008177974,0.00004809783,0.0003869295,0.002049294,0.0005218072,0.00008639701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001503136,"about_ca_system_score_gemma":0.0001315455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001398358,"about_ca_topic_score_gemma":0.00001363415,"domain_scores_codex":[0.9980659,0.0001454906,0.0002033714,0.001074914,0.0001106831,0.0003996151],"domain_scores_gemma":[0.9982293,0.0000326084,0.0002279874,0.001226946,0.0001587988,0.0001243833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008709003,0.0001469147,0.00005097661,0.00005040976,0.0000490508,0.0001458338,0.000622987,0.8781583,0.00001025487,0.1157319,0.00306967,0.001954935],"study_design_scores_gemma":[0.0002075247,0.00004125529,0.00004732795,0.00006978259,0.00002032118,0.000004557441,0.00007198725,0.9419275,0.0001270003,0.05687763,0.000269574,0.0003355653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02168231,0.00005345549,0.968944,0.0001275156,0.000599519,0.0004626974,0.00001034686,0.005564336,0.002555822],"genre_scores_gemma":[0.941327,0.0001905634,0.05301145,0.00003646118,0.0001005751,0.000005163636,0.00005955967,0.00002940293,0.005239842],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9196447,"threshold_uncertainty_score":0.9999173,"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."}}