Expert insights on AI code detection and academic integrity
Stay ahead with expert analysis and practical guides
General
10 min
Dr. Sarah Chen
·
1 month ago
A CS professor ran 1,200 Java submissions through three AI code detectors. Codequiry caught 94% of known AI files and flagged only 3.5% of pre-LLM human code, while the other tools posted two to three times that false positive rate. The full numbers and methods are below.
General
9 min
Priya Sharma
·
1 month ago
Across 41,000 student submissions at a large public university, an 85% token-level similarity score between two students predicted confirmed misconduct 92% of the time in introductory courses. This guide walks through the exact calibration workflow, score distributions by language, and tiered review thresholds that worked for my assessment team.
General
11 min
Dr. Sarah Chen
·
1 month ago
This is the workflow Dr. Sarah Chen uses every week to catch plagiarism that survives renaming, reordering, and refactoring. It layers token normalization, AST comparison, and a smart review queue, then walks through what to look for in a diff before talking to a student.
General
14 min
Emily Watson
·
1 month ago
Web code plagiarism is distinct from peer copying, and standard similarity tools miss it. This guide breaks down how to detect code lifted from Stack Overflow, GitHub, and tutorials, with a practical grading workflow that catches it without drowning TAs in false flags.
General
10 min
Alex Petrov
·
1 month ago
Quoted Google searches used to be the standard way to catch a Stack Overflow lift. I tracked the shift across tools, fingerprints, and live web corpora, and why modern checks need to pair source matching with AI detection. The short version: the web changed the question from "who copied whom" to "where did this code come from."
General
11 min
Emily Watson
·
1 month ago
A practical walkthrough for CS instructors and TAs: wire Codequiry's peer similarity and AI detection into a GitHub Actions workflow, get CSV results on every commit, and triage suspicious submissions in under a minute each.
General
8 min
Rachel Foster
·
1 month ago
AI code detectors are producing false positives on the most ordinary submissions in CS1: code that looks the same because the assignment required it. This reported piece examines the data, the workflow changes instructors are making, and why combining AI detection with structural similarity reduces the error rate.
General
9 min
James Okafor
·
1 month ago
Line diffs collapse when students rename variables, reorder functions, and extract methods. Here's how token fingerprints and AST normalization catch refactored copies, and how to triage hundreds of similarity reports without drowning in false positives.
General
9 min
Alex Petrov
·
1 month ago
A bootcamp instructor explains how token-level perplexity works as an AI code signal, what thresholds we actually use in Java review, and why a single statistical score is never enough on its own.
General
6 min
Rachel Foster
·
1 month ago
Set up an automated code plagiarism detection pipeline in GitHub Actions using Codequiry's REST API. Follow precise steps to write a workflow YAML and a Python script that submits student code, receives similarity scores, flags suspicious pushes, and optionally detects AI-generated code. Includes threshold tuning, result interpretation, and false positive handling.
General
12 min
Priya Sharma
·
1 month ago
A three-semester analysis of 4,100 CS1 submissions shows why a 70% similarity score means different things in Python, Java, C++, and JavaScript. I break down percentile thresholds, boilerplate effects, false positives, and how to pair similarity checks with AI detection.
General
10 min
Priya Sharma
·
1 month ago
Most plagiarism checkers only compare submissions against each other, so a Stack Overflow snippet with renamed variables sails through. We break down how web source matching uses token and AST fingerprints to catch code copied from Stack Overflow, GitHub, and tutorials, and show a Java example where refactoring did not hide the source.