Developing Machine Learning Coding Similarity Indicators for C and C++ Corpuses
Bibliographic record
Abstract
In the digital era of technology and advanced automation, data or information is vulnerable to copying, altering, and claiming someone else's work as their own. Source code theft or e-plagiarism is challenging to track in hundreds of assignments submitted by students. Despite the year's efforts, the digital plagiarism detection software currently available performs well enough for a nave programmer to detect literal plagiarism. The available source code similarity detectors provide insufficient results when a student uses complex strategies such as word substitution or reordering programming constructs. To overcome the above-mentioned challenges, this research aims to deliver an assistive forensic engine for the professors and teaching assistants to evaluate the similarities in the student's assignments. This research's primary objective is to help the evaluators get closer to the sophisticated code thieves and abide by the university's academic dishonesty regulations. The proposed forensic similarity detection engine's constructive methodology is specially designed for studies where C and C++ programming languages are majorly used in academic assignments. After selecting the ATM (Attribute counting metrics), the system implementation is divided into two phases, where phase one consists of lexical analysis and tokenizer customization. The second phase mostly consists of rolling out the supervised learning algorithm on the generated data to classify the comparison of two files as a truth value. The similarity elements and observations recorded can be represented to the evaluators in the form of visualizations for ease of understanding and efficient decision making. The paper also relates the proposed system with the previous and existing system and mitigates the past issues noted in the latter half.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".