{"id":"W4300960622","doi":"10.1007/s10664-022-10223-5","title":"A controlled experiment of different code representations for learning-based program repair","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Code (set theory); Source code; Representation (politics); Artificial intelligence; Point (geometry); Syntax; Programming language; Perspective (graphical); Process (computing); Natural language processing; Set (abstract data type)","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":[0.0004619356,0.0002244845,0.0004434206,0.0002684862,0.0002080556,0.00005347774,0.0007002062,0.00004961792,0.00004157525],"category_scores_gemma":[0.00368448,0.0002209662,0.0003754682,0.0006190948,0.0000251701,0.00009448664,0.0004103858,0.0003911869,0.00000177086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002509956,"about_ca_system_score_gemma":0.0001044501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007396978,"about_ca_topic_score_gemma":4.334389e-7,"domain_scores_codex":[0.9977441,0.00009672384,0.0004592634,0.0005090194,0.0006957548,0.0004950995],"domain_scores_gemma":[0.9955553,0.003479933,0.00009556532,0.0005767038,0.0001221561,0.0001703804],"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":[0.0001302909,0.0006919187,0.05214154,0.0001229039,0.0001420971,0.00001761095,0.0005531971,0.9415842,0.0004051982,0.0002179376,0.002159903,0.00183315],"study_design_scores_gemma":[0.003539946,0.001057253,0.01682961,0.00002341123,0.00001724711,0.000005849875,0.0000282366,0.963706,0.002591805,0.00003383371,0.01182937,0.0003375045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.125132,0.0002498413,0.8684027,0.0002737334,0.0003726105,0.001502994,0.00001231397,0.004048437,0.00000543341],"genre_scores_gemma":[0.836029,0.000001117242,0.1587044,0.00003849035,0.00005283027,0.004955577,0.00002328416,0.00004706109,0.0001482252],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.710897,"threshold_uncertainty_score":0.9010739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03017434424875222,"score_gpt":0.3311016495021448,"score_spread":0.3009273052533926,"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."}}