{"id":"W4377194214","doi":"10.1142/s2811032323500017","title":"A Survey on Code Representation","year":2023,"lang":"en","type":"article","venue":"World Scientific Annual Review of Artificial Intelligence","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Embedding; Computer science; Benchmark (surveying); Representation (politics); Artificial intelligence; Code (set theory); Feature learning; Machine learning; Natural language processing; Space (punctuation); Programming language","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":[0.001447603,0.001131046,0.001005775,0.00532455,0.000707131,0.002912768,0.002221646,0.001412335,0.009771743],"category_scores_gemma":[0.0100573,0.0006191924,0.001243974,0.009927519,0.001132137,0.007833354,0.002016987,0.002190969,0.004441802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001383187,"about_ca_system_score_gemma":0.002951378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004005988,"about_ca_topic_score_gemma":0.002649603,"domain_scores_codex":[0.9979091,0.0004216528,0.0002049287,0.0003991883,0.000930129,0.0001348349],"domain_scores_gemma":[0.9965135,0.001915406,0.0001959167,0.000528794,0.0007485541,0.0000978751],"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":[0.00003588599,0.00007238841,0.001229222,0.00210156,0.00002769706,0.00006890495,0.0001923232,0.005541319,0.0008661723,0.08602948,0.04138457,0.8624505],"study_design_scores_gemma":[0.00001561432,0.0001015965,0.00164576,0.002652115,0.00004809005,0.0009729824,0.0003620369,0.03479853,0.002899413,0.159963,0.796464,0.00007687215],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01080364,0.369234,0.5412527,0.01054309,0.001769996,0.0003146268,0.003423562,0.00448146,0.05817679],"genre_scores_gemma":[0.07015269,0.5534887,0.3292906,0.003534356,0.002528088,0.0006018519,0.01426364,0.00167746,0.02446253],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009771743,"threshold_uncertainty_score":0.03268969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135828696490033,"score_gpt":0.3974601391959184,"score_spread":0.2838772695469152,"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."}}