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

Building a Refactoring-Resistant Similarity Pipeline General 11 min
James Okafor James Okafor · 1 week ago

Building a Refactoring-Resistant Similarity Pipeline

Renaming variables and extracting helpers is the cheapest way to defeat a naive similarity checker, and the fix is not a better diff. This walks through the normalization stack that makes refactoring-resistant plagiarism detection work, from token streams to winnowing to tree edit distance, and is honest about the precision you pay for each step.

How Professors Actually Read a Code Plagiarism Report General 11 min
Dr. Sarah Chen Dr. Sarah Chen · 2 weeks ago

How Professors Actually Read a Code Plagiarism Report

A similarity score is not a verdict, and the gap between the two is where most integrity cases are won or lost. A CS professor with fifteen years in the classroom and two terms on an honor board explains what a code plagiarism report actually shows, which signals survive cross-examination, and how departments can read one without ruining a student's semester by mistake.

How a Staff Engineer Spots AI Code in Take-Home Exercises General 10 min
Rachel Foster Rachel Foster · 2 weeks ago

How a Staff Engineer Spots AI Code in Take-Home Exercises

Take-home exercises have become the most reliable place to catch AI-generated code in a hiring pipeline, but almost no team uses the three signals they already own. A staff engineer's screening routine, the code tells that survive a careful read, and the legal questions nobody has answered yet.

Calibrating an AI Code Detector to Cut False Positives General 10 min
James Okafor James Okafor · 2 weeks ago

Calibrating an AI Code Detector to Cut False Positives

An AI code detector is a measurement instrument, and like any instrument it needs a baseline before you trust the number it prints. This walks through per-file scoring, empirical false positive rates on pre-2023 submissions, cohort normalization, and why the AI score should never travel alone.

What 12,400 Submissions Taught Me About Similarity Thresholds General 9 min
Emily Watson Emily Watson · 2 weeks ago

What 12,400 Submissions Taught Me About Similarity Thresholds

Plot every similarity score in a class and you don't get a clean line between innocent and guilty. You get a fat hump in the forties and a long tail. Here's four semesters of data on what a code similarity threshold should actually be, and why the same number fails in Java and Python.

Setting AI Code Detection Thresholds on 1,200 Student Files General 12 min
Dr. Sarah Chen Dr. Sarah Chen · 2 weeks ago

Setting AI Code Detection Thresholds on 1,200 Student Files

Eleven of the 43 files I flagged as machine-written last fall belonged to students who had never opened a chat window. This is a step-by-step account of the calibration I now run every August: human baselines, per-file scoring, and a combining rule that cut my review queue from 214 to 61.

A Policy Gate Checklist for AI-Generated Code in Pull Requests General 13 min
David Kim David Kim · 3 weeks ago

A Policy Gate Checklist for AI-Generated Code in Pull Requests

We ran an AI-origin detection gate on 1,847 pull requests over 90 days and hand-reviewed a 300-PR sample to find out what these detectors actually catch. The statistical scorers everybody buys landed at 26% precision. Stacking four signal families got us to 65%. Here is the pipeline design, the numbers, and an evaluation matrix for picking a vendor.

Running AI Code Detection on Take-Home Interview Submissions General 10 min
Priya Sharma Priya Sharma · 3 weeks ago

Running AI Code Detection on Take-Home Interview Submissions

A take-home pipeline with 1,180 submissions and no AI screening is a coin flip dressed up as a hiring process. Here's what the scores actually measure, how to combine them with similarity checks, and where the whole method quietly falls apart.

A Checklist for Verifying Contractor Code Originality General 8 min
Marcus Rodriguez Marcus Rodriguez · 3 weeks ago

A Checklist for Verifying Contractor Code Originality

Most code originality problems arrive with an invoice attached, not a report card. Here is the six-step process I run on contracted codebases before the final payment clears, from contract language to the delivery gate that blocks a release tag.

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.