{"id":"W7126425372","doi":"10.21428/594757db.88028518","title":"C++ Source Code Verification Pipeline","year":2025,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Bespoke; Source code; Correctness; Classifier (UML); Pipeline (software); Artificial neural network; Software; Deep learning; Natural 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":[0.001154804,0.001619907,0.0008003051,0.002202406,0.0005579444,0.001499817,0.002136952,0.0007171985,0.04053857],"category_scores_gemma":[0.009157396,0.0007290137,0.001360733,0.001052177,0.0004974088,0.001966233,0.001953387,0.001820523,0.02625184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001298159,"about_ca_system_score_gemma":0.003641225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007123115,"about_ca_topic_score_gemma":0.006728284,"domain_scores_codex":[0.9984426,0.0001178087,0.00009987623,0.0004835965,0.0007014379,0.0001548066],"domain_scores_gemma":[0.9964297,0.0007817377,0.0002338542,0.0007865852,0.001631924,0.0001360775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007816142,0.0002540799,0.006700076,0.001127679,0.0001693034,0.0007773848,0.0003856705,0.02976793,0.02929976,0.01504949,0.2525814,0.6631056],"study_design_scores_gemma":[0.0003187932,0.0004167482,0.009159341,0.0002940168,0.00008192028,0.0009751784,0.0002289892,0.5563845,0.141264,0.03420156,0.256456,0.000219076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.02162489,0.000490263,0.4352247,0.0006685465,0.0002883343,0.0007352447,0.01624538,0.5080336,0.01668902],"genre_scores_gemma":[0.3289767,0.000565762,0.4716209,0.001214689,0.0001461334,0.0009255805,0.09392109,0.06098698,0.04164229],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.04053857,"threshold_uncertainty_score":0.1356151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443259837562605,"score_gpt":0.2795492443964362,"score_spread":0.2651166460208102,"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."}}