MétaCan
Menu
← Back to cohort
Record W7126425372 · doi:10.21428/594757db.88028518

C++ Source Code Verification Pipeline

2025· article· en· W7126425372 on OpenAlexaff
Neil Pais, Ritu Chaturvedi

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsUniversity of Guelph
Fundersnot available
KeywordsBespokeSource codeCorrectnessClassifier (UML)Pipeline (software)Artificial neural networkSoftwareDeep learningNatural language

Abstract

fetched live from OpenAlex

Deep Learning (DL) techniques in Natural Language Processing have evolved at a remarkable pace. The recent advances in language modeling, machine translation, and paragraph understanding significantly underscore the potential of DL within the field of Software Engineering, particularly in program learning. This study aims to enhance the application of DL in program learning by examining the input embeddings used to train models, especially when the training data comprises source code. Unlike standard text, source code possesses unique characteristics and semantics. Therefore, our primary objective is to establish a framework for comparing various C++ input embeddings to identify the most effective one for training a predictive machine learning classifier. This classifier will focus on assessing the correctness of code. Aligning with broader educational goals, our research intends to improve student learning outcomes through the effective and automated grading of programming assignments. Experimental results indicate that CodeT5 demonstrates superior effectiveness in generating embeddings that are well-suited for training a bespoke neural network to accurately distinguish between correct and incorrect code.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.041
Threshold uncertainty score0.136

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.009
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0410.026

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.014
GPT teacher head0.280
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicSoftware Engineering Research→French-language works237,207→