{"id":"W4389980560","doi":"10.1016/j.jss.2023.111934","title":"A survey on machine learning techniques applied to source code","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Dalhousie University","funders":"H2020 European Research Council; European Research Council","keywords":"Computer science; Workflow; Source code; Machine learning; Context (archaeology); Software; Software engineering; Artificial intelligence; Task (project management); Code review; Data science; Static program analysis; Software development; Systems engineering; Programming language; Engineering; Database","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":[0.008219324,0.001192051,0.001200662,0.01371026,0.0006927259,0.002629425,0.002141767,0.001363412,0.002759503],"category_scores_gemma":[0.03665795,0.00081198,0.002046962,0.01942412,0.0008869573,0.004987786,0.001297965,0.002091516,0.002322656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218177,"about_ca_system_score_gemma":0.002198859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002565288,"about_ca_topic_score_gemma":0.002567314,"domain_scores_codex":[0.9917897,0.001925223,0.001117536,0.001080827,0.003866934,0.0002197104],"domain_scores_gemma":[0.9515827,0.03802421,0.001540839,0.002204451,0.006363091,0.0002847948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005594391,0.00008331462,0.008838652,0.008642048,0.0001973674,0.0001426387,0.0003165225,0.00363137,0.001877932,0.005089032,0.02033882,0.9507864],"study_design_scores_gemma":[0.00004717695,0.0004640023,0.0413124,0.01842663,0.0005397947,0.002371783,0.0009998383,0.03921994,0.01902314,0.04089694,0.836437,0.0002613857],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.02190757,0.692631,0.2469382,0.005760988,0.001491259,0.0004627442,0.003730542,0.002887691,0.02418998],"genre_scores_gemma":[0.08008909,0.7103574,0.1906219,0.00244781,0.00174779,0.000719421,0.008331302,0.0009401675,0.004745118],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01371026,"threshold_uncertainty_score":0.04346842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02886875562047403,"score_gpt":0.2772920157214117,"score_spread":0.2484232601009377,"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."}}