{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01532304,0.0006714449,0.001528204,0.0005512834,0.0002814815,0.00104476,0.003568088,0.0003817985,0.000005985556],"category_scores_gemma":[0.01804775,0.000601199,0.0003531127,0.00164472,0.00008960396,0.000172482,0.003717801,0.001437213,0.0001210355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001784413,"about_ca_system_score_gemma":0.0003155088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001036536,"about_ca_topic_score_gemma":0.00005145594,"domain_scores_codex":[0.9940366,0.002163998,0.0008614209,0.001487865,0.0005278548,0.0009223047],"domain_scores_gemma":[0.9674702,0.030389,0.0002252445,0.001432402,0.0002616925,0.0002214043],"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":[4.223888e-7,0.00001107851,0.0006173691,0.007368214,0.0001323212,0.00001861901,0.0001112625,0.0003223685,1.780616e-8,0.0002424334,0.0004930596,0.9906828],"study_design_scores_gemma":[0.0001363705,0.0002776033,0.004226502,0.01257225,0.000236344,0.0001904895,0.000009253963,0.1940433,9.747957e-7,0.0007791354,0.7855687,0.001959099],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008113831,0.5284628,0.469694,0.00001064309,0.0009368471,0.0004313833,0.00001173528,0.0004333595,0.00001105596],"genre_scores_gemma":[0.0006205075,0.9610745,0.03720593,0.000009548147,0.0003248574,0.00005940199,0.000214734,0.0001441636,0.0003464038],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9887238,"threshold_uncertainty_score":0.9999923,"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."}}