Nov 15, 2026 Codequiry software is now free and a one-time payment for lifetime access. See plans →
Alex Petrov

Alex Petrov

Detection Systems Engineer at Codequiry

Alex focuses on refactoring-resistant similarity detection and benchmarking Codequiry against tools like MOSS, JPlag and Dolos.

Articles by Alex Petrov

How AI Code Detectors Score ChatGPT, Claude, and Copilot General 10 min
Alex Petrov Alex Petrov • 2 days ago

How AI Code Detectors Score ChatGPT, Claude, and Copilot

Every AI code detector you've tried is some weighted blend of three signals: perplexity, burstiness, and structural regularity. I put 900 generated files and 240 human ones through all three to see where each one fires, where it fails, and why Copilot autocomplete is the hardest case of the lot.

What 4,800 Take-Home Submissions Revealed About AI Code General 12 min
Alex Petrov Alex Petrov • 3 days ago

What 4,800 Take-Home Submissions Revealed About AI Code

I kept every take-home submission from six bootcamp cohorts and ran them through three scoring passes. Here is what the numbers say about AI-generated code, which signals survive contact with real students, and where every detector I tried still gets it wrong.

How to Detect Code Copied From Stack Overflow General 10 min
Alex Petrov Alex Petrov • 3 weeks ago

How to Detect Code Copied From Stack Overflow

Pasting from Stack Overflow is the most common form of web code plagiarism, and peer comparison tools like MOSS will never see it. Here's how token fingerprinting actually matches a submission to a 2013 answer, how to read a web match report without overreacting, and why "Stack Overflow is public domain" is the most expensive misconception in the room.

A Checklist for Auditing Take-Home Code for AI Generation General 13 min
Alex Petrov Alex Petrov • 1 month ago

A Checklist for Auditing Take-Home Code for AI Generation

We ran 412 bootcamp take-home submissions through four independent detection signals and followed 63 flagged candidates to a live code interview. This is what we found about which signals actually predict AI-generated code, which ones just predict "this person read a tutorial," and how to build an audit you can defend when a candidate pushes back.

Stack Overflow, GitHub, and Course Sites Across 4,000 Submissions General 10 min
Alex Petrov Alex Petrov • 1 month ago

Stack Overflow, GitHub, and Course Sites Across 4,000 Submissions

I ran 4,000 bootcamp submissions through web-source matching and 22% matched something public. Most of those matches were harmless. Here's what a real Stack Overflow diff looks like, why GitHub matches almost always come with a receipt, and how I stopped flagging half my class with false positives.

Do AST Plagiarism Detectors Beat Token Matching on Refactored Code? General 12 min
Alex Petrov Alex Petrov • 1 month ago

Do AST Plagiarism Detectors Beat Token Matching on Refactored Code?

I seeded 48 known-copy pairs into 1,247 real bootcamp submissions and ran them through MOSS, JPlag, Dolos, and Codequiry. Token-based engines held up against renaming and reformatting, then collapsed once control flow changed. Here's the data, the methodology, and where every engine breaks.

Running a Mid-Cohort AI and Plagiarism Sweep on 300 Submissions General 9 min
Alex Petrov Alex Petrov • 1 month ago

Running a Mid-Cohort AI and Plagiarism Sweep on 300 Submissions

A week-by-week account of the three-signal sweep one bootcamp runs at week 7 of every cohort: peer similarity, web matching, and AI detection in one batch. Includes the ignore-list mistake that cost us two evenings, what LLM-shaped student code actually looks like, and how to turn a flag into a conversation instead of a verdict.

How One Bootcamp Screens 400 Take-Homes for AI Code General 10 min
Alex Petrov Alex Petrov • 1 month ago

How One Bootcamp Screens 400 Take-Homes for AI Code

387 files, three scores, one hiring round. Here's what a 12-week bootcamp learned after moving take-home review from three exhausted instructors to an automated pass that checks peer similarity, public web sources, and AI generation, including the false positives we cleared and the two assignment changes that mattered more than any detector.

Can a Python Submission Be Traced Back to a Java Repository? General 15 min
Alex Petrov Alex Petrov • 1 month ago

Can a Python Submission Be Traced Back to a Java Repository?

Two Python submissions scored 4% against each other and in the 70s against a Java gist from 2017. Cross-language plagiarism is the fastest-growing blind spot in academic integrity because translation destroys the text while preserving everything that matters. Here's what survives a translation, what detectors actually see, and where the false positives come from.

How Cross-Language Code Plagiarism Detection Works General 13 min
Alex Petrov Alex Petrov • 2 months ago

How Cross-Language Code Plagiarism Detection Works

A Java submission and a Python submission looked nothing alike, but they were the same algorithm translated line by line. This is the story of how cross-language code plagiarism detection actually works, where it catches translated code, and where it still fails.

Designing Coding Assignments That AI Can't One-Shot General 10 min
Alex Petrov Alex Petrov • 2 months ago

Designing Coding Assignments That AI Can't One-Shot

As a bootcamp instructor, I've graded hundreds of take-home coding challenges. The AI-resistant ones share a pattern: they ask for process artifacts, not just final code. Here's how to design assignments that hold up.

The Long Road to Refactoring-Resistant Code Plagiarism Detection General 6 min
Alex Petrov Alex Petrov • 2 months ago

The Long Road to Refactoring-Resistant Code Plagiarism Detection

A hands-on retrospective on how code similarity detection grew from naive line diffs to tokenization, ASTs, and fingerprinting. Follow a step-by-step Python prototype and a production workflow with Codequiry to catch refactored plagiarism in CS courses.