{"id":"W4282033849","doi":"10.1145/3542944","title":"Towards Learning Generalizable Code Embeddings Using Task-agnostic Graph Convolutional Networks","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Concordia University","funders":"","keywords":"Computer science; Source code; Downstream (manufacturing); Graph; Benchmarking; Code (set theory); Abstract syntax; Embedding; Task (project management); Artificial intelligence; Syntax; Theoretical computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001434423,0.0002684337,0.0003422294,0.000544905,0.0006691351,0.00007006585,0.0007634863,0.0001259565,0.00006615728],"category_scores_gemma":[0.002241154,0.000317175,0.0001177321,0.0009161876,0.0000590992,0.0001950611,0.000148761,0.001165498,0.000002659983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001909818,"about_ca_system_score_gemma":0.0001057275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001074956,"about_ca_topic_score_gemma":0.000001526064,"domain_scores_codex":[0.9976642,0.0004256969,0.0002820356,0.0006130066,0.0003755435,0.0006395507],"domain_scores_gemma":[0.9946135,0.004514094,0.00005742443,0.0005427467,0.00007821441,0.0001940039],"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":[0.0000128866,0.00003021475,0.0004235375,0.00002404557,0.00006902117,0.00002486171,0.0002832569,0.9890183,0.0005309579,0.0007066366,0.00003982643,0.008836485],"study_design_scores_gemma":[0.0005618735,0.0003105895,0.001496709,0.00002764792,0.00004163893,0.000609747,0.00004882383,0.9884799,0.0004838061,0.0004921294,0.006943395,0.0005037421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02898467,0.0007677525,0.9677242,0.0001158217,0.001289997,0.0001474193,0.00001554497,0.0009529143,0.000001689403],"genre_scores_gemma":[0.2319709,0.00008686443,0.7674868,0.0001062076,0.00006477505,0.0001145246,0.000008925,0.00004716766,0.0001138422],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2029862,"threshold_uncertainty_score":0.9999281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07716174346765048,"score_gpt":0.3182070995153627,"score_spread":0.2410453560477123,"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."}}