Nov 22, 2026 Codequiry now allows free accounts with unlimited peer to peer scanning with Hexagram and MOSS. See plans →

Code Intelligence Hub

Expert insights on AI code detection and academic integrity

Latest Articles

Stay ahead with expert analysis and practical guides

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.

How Do You Set a Similarity Threshold You Can Defend in a Hearing? General 12 min
Marcus Rodriguez Marcus Rodriguez · 3 weeks ago

How Do You Set a Similarity Threshold You Can Defend in a Hearing?

A 71% similarity score means nothing on its own, but it has to survive a room full of people who want an answer. Here is the exact calibration workflow I use: normalization settings, cohort percentiles, tiered thresholds, and an evidence packet that holds up when a student appeals.

How Code Similarity Detection Moved From Text to Trees General 17 min
James Okafor James Okafor · 4 weeks ago

How Code Similarity Detection Moved From Text to Trees

Five generations of code similarity detection have each been beaten by a student with a text editor. This is the technical history of how detectors moved from byte comparison to tokens, fingerprints, syntax trees and learned vectors, and what that arc tells you about choosing a tool that can still find a match when the code has been renamed, refactored, or generated by a model.

Stacking AI Detection and Plagiarism Checks in One Grading Pass General 12 min
Dr. Sarah Chen Dr. Sarah Chen · 4 weeks ago

Stacking AI Detection and Plagiarism Checks in One Grading Pass

A CS2 course with 412 students and eleven TAs ran peer similarity, web-source matching, and AI-generation scoring in one pass per assignment instead of three separate workflows. The interesting result wasn't the flag count. It was that the review meetings stopped arguing about whether a submission looked suspicious and started arguing about what the department's own AI policy actually permitted.

How to Detect Code Copied From Stack Overflow in Submissions General 12 min
Rachel Foster Rachel Foster · 1 month ago

How to Detect Code Copied From Stack Overflow in Submissions

A department ran a web-source scan on 412 intro Python submissions and got 61 hits, 23 of which were noise. This is the eight-step workflow they built afterward, from normalizing LMS exports and budgeting GitHub's code search rate limit to ranking matches by token count instead of percentage and assembling an evidence packet that survives an appeal.

How Do You Scan a Course for Both Copied and AI-Written Code? General 15 min
Dr. Sarah Chen Dr. Sarah Chen · 1 month ago

How Do You Scan a Course for Both Copied and AI-Written Code?

Running one scan and hoping it covers everything is how courses end up with both missed cases and false accusations. This walkthrough separates peer similarity, web provenance, and machine generation into three pipelines, then shows how to merge them into a ranked queue a TA can work through in an afternoon.

How a Lead TA Triages 400 Similarity Reports Before Grades Post General 10 min
Priya Sharma Priya Sharma · 1 month ago

How a Lead TA Triages 400 Similarity Reports Before Grades Post

A lead TA at a mid-sized CS department gets 412 similarity pairs back from a single algorithms assignment and has six days to decide which ones matter. This is the triage method she uses: score stacking, cohort-normalized thresholds, and a written rubric that has survived two grade appeals.

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.

A Contractor Code Provenance Checklist for CTOs General 10 min
Marcus Rodriguez Marcus Rodriguez · 1 month ago

A Contractor Code Provenance Checklist for CTOs

Meridian, a 40-person benefits SaaS, had 340,000 lines of contracted code and no way to answer question 34 on a diligence questionnaire. Here's the five-gate provenance audit that followed, what the tools actually found, and the clause in the MSA that would have made all of it cheap.

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.

Can a CI Gate Detect AI-Generated Code in a Pull Request? General 12 min
David Kim David Kim · 1 month ago

Can a CI Gate Detect AI-Generated Code in a Pull Request?

A DevSecOps lead's field notes on putting AI-generated code detection inside a real CI pipeline: what the detector actually measures, which files produce false positives on day one, and why the gate should warn on pull requests but only block on release. Includes the config we run and the numbers we got.

Telling AI-Generated Code Apart From Peer Copying General 9 min
Emily Watson Emily Watson · 1 month ago

Telling AI-Generated Code Apart From Peer Copying

When a whole class prompts the same model, peer similarity scores climb even though nobody copied anybody. Here is how to read an AI detection score, a clustering pattern, and a genuine copy pair as three different things, and how I triage 200 submissions in under two hours without accusing the wrong students.