{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001575269,0.002638059,0.0009989276,0.001514787,0.0007197956,0.001422556,0.004061808,0.001011574,0.007104766],"category_scores_gemma":[0.005562772,0.001137569,0.003684352,0.001040564,0.001539532,0.003697558,0.003186986,0.003345494,0.002904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001340345,"about_ca_system_score_gemma":0.003594099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005711811,"about_ca_topic_score_gemma":0.01390507,"domain_scores_codex":[0.9968207,0.0008801534,0.0001693948,0.000659784,0.001232599,0.0002372492],"domain_scores_gemma":[0.9967615,0.001364837,0.0002548353,0.00111213,0.0004475302,0.00005923298],"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":[0.000569888,0.0003809773,0.003994555,0.001719737,0.0003418492,0.0006003331,0.0008009172,0.2293032,0.05215862,0.05102133,0.05959605,0.5995125],"study_design_scores_gemma":[0.000133216,0.0001825797,0.0004940412,0.00007829363,0.0001340697,0.0002076009,0.0001347078,0.8831634,0.03733505,0.04037402,0.03769464,0.00006850169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01064061,0.0006702538,0.900268,0.0004475357,0.00008045067,0.0002264819,0.0007740781,0.08338647,0.003506038],"genre_scores_gemma":[0.1390593,0.0004544553,0.8388128,0.0006636634,0.00006658679,0.0005935909,0.004484278,0.01023756,0.005627699],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007104766,"threshold_uncertainty_score":0.02376777,"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."}}