{"id":"W4397032804","doi":"10.1145/3664597","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","year":2024,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Software Engineering Research","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; KPI-driven code analysis; Benchmark (surveying); Deep learning; Source code; Code review; Static program analysis; Code (set theory); Machine learning; Software engineering; Data science; Software development; Software; Programming language; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00299255,0.0016407,0.001157038,0.0047104,0.0004347418,0.002097868,0.002988957,0.001471649,0.004905615],"category_scores_gemma":[0.01121244,0.0009833323,0.001031109,0.005875841,0.0009229009,0.004487081,0.002006992,0.003104569,0.003509188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001886475,"about_ca_system_score_gemma":0.003855365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005694219,"about_ca_topic_score_gemma":0.006200416,"domain_scores_codex":[0.9981321,0.0003219024,0.0001709343,0.0003017574,0.0009654635,0.0001078186],"domain_scores_gemma":[0.9947463,0.003076697,0.0002537365,0.0004596174,0.001292467,0.0001711737],"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":[0.0000549392,0.00008788248,0.0009376178,0.005522968,0.00009648569,0.00003224705,0.00007041173,0.008105238,0.0006580967,0.01832595,0.04405377,0.9220544],"study_design_scores_gemma":[0.00004703094,0.0003175446,0.00242884,0.007672431,0.0002557925,0.0004896761,0.0001715082,0.05420285,0.006399384,0.05447794,0.8734156,0.0001214404],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004310011,0.8720589,0.08767967,0.004929985,0.0008168147,0.0002024772,0.001075528,0.002094592,0.0268319],"genre_scores_gemma":[0.03230193,0.8863435,0.06463393,0.002081359,0.0007201888,0.0002789363,0.004388467,0.0007117355,0.008540016],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.005694219,"threshold_uncertainty_score":0.01641089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09497021096444722,"score_gpt":0.3811796623693111,"score_spread":0.2862094514048639,"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."}}