{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006479251,0.002444688,0.0006966733,0.001281935,0.0003313567,0.0007510232,0.001379838,0.001247438,0.001202073],"category_scores_gemma":[0.00369874,0.0006007485,0.001199172,0.001166484,0.0008913187,0.002871291,0.001420977,0.002230877,0.001041216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043233,"about_ca_system_score_gemma":0.001106979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007650756,"about_ca_topic_score_gemma":0.01618488,"domain_scores_codex":[0.9994224,0.0001205863,0.0000264867,0.0002632273,0.0000889986,0.00007830877],"domain_scores_gemma":[0.9986145,0.0005073707,0.0001759083,0.0003591682,0.0002671485,0.00007582884],"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":[0.0002324343,0.0003421335,0.006836898,0.0003022669,0.0001815662,0.0002087805,0.0001788203,0.513875,0.01593333,0.007193949,0.01601021,0.4387046],"study_design_scores_gemma":[0.00001328504,0.00005679006,0.0005390155,0.00001400311,0.00001892184,0.00003893521,0.0000251589,0.9854665,0.002681197,0.009862641,0.001273171,0.00001045508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.177948,0.001726573,0.7967585,0.001000487,0.0002311128,0.000176278,0.001929931,0.01585859,0.004370552],"genre_scores_gemma":[0.7564558,0.0009612111,0.2207234,0.0009099189,0.0001271056,0.0002775806,0.01177482,0.0009123827,0.00785773],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007650756,"threshold_uncertainty_score":0.01521248,"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."}}