Code Intelligence Hub

General 7 min

Rachel Foster · 1 month ago

How UMass Amherst Brought AI Detection Into CS 121

When 800 students enroll in an introductory Python course, detecting AI-generated code by hand is impossible. UMass Amherst integrated an AI code detector trained on student-level patterns alongside traditional similarity checks—and uncovered a 14% AI flag rate, a 2% false positive rate, and a sustainable workflow that kept TAs focused on teaching rather than policing.

Read →

General 9 min

James Okafor · 1 month ago

Finding Stack Overflow Code in Student Submissions With Fingerprints

A study of 5,000 Java assignments from three US universities found that nearly one in four contained code blocks directly traceable to Stack Overflow answers — yet traditional similarity checkers missed them all. We applied token-sequence fingerprinting and a web index of 1.2 million programming snippets to surface hidden web plagiarism at scale.

Read →

General 11 min

James Okafor · 1 month ago

How Perplexity-Based AI Code Detectors Actually Work

Perplexity-based detectors aren’t magic — they measure how surprising a sequence of code tokens would be to a model trained on real human code. This report breaks open the inner math, real false-positive rates from Stanford and Edinburgh benchmarks, and why the strongest detectors stack statistical signals with AST fingerprinting and web-source checks.

Read →

General 10 min

Marcus Rodriguez · 1 month ago

How Perplexity and Burstiness Reveal AI-Written Code

AI code detectors don't read code—they measure its statistical shape. This piece breaks down the two key metrics, perplexity and burstiness, that separate lines from a language model from something a programmer actually typed. Real numbers, real edge cases, and how to combine signals for a higher-confidence verdict.

Read →

General 12 min

David Kim · 1 month ago

MOSS, JPlag, and AI Detectors Across 1,200 Obfuscated Submissions

A deep-dive comparison of MOSS, JPlag, Dolos, and hybrid detectors on deliberately obfuscated student Java code. Token-based algorithms catch most refactoring, but AI-generated obfuscation is changing the game — and combining similarity checks with AI detection is the only reliable way to stay ahead.

Read →

General 15 min

Dr. Sarah Chen · 1 month ago

How AST-Based Similarity Catches Disguised Code Plagiarism

Token-based plagiarism detectors match sequences of tokens, but smart students can evade them by renaming variables, reordering statements, and refactoring code. Abstract Syntax Tree (AST) comparison digs deeper into the structural DNA of a program, making it far harder to disguise copied code. Learn how AST-based detection works, why it catches what MOSS and JPlag miss, and where Codequiry’s multi-layered approach fits in.

Read →

General 11 min

David Kim · 1 month ago

Three Semesters of Detecting Collusion in CS1 Without Burnout

When you teach 400 students each semester, “check the MOSS output” stops being a casual Friday task and becomes a logistical nightmare. After three iterations of the same introductory Java course, I’ve settled on a repeatable workflow that catches collusion without sacrificing evenings, weekends, or relationships with honest students. Here’s exactly how the pipeline works, what tools sit where, and where Codequiry finally closed the gap I was losing sleep over.

Read →

General 12 min

Dr. Sarah Chen · 1 month ago

Why CS Departments Are Now Running AI Checks After Plagiarism

When Midwestern State University’s CS department discovered that MOSS alone missed nearly a third of suspicious submissions—many generated by ChatGPT—they implemented a two-stage detection pipeline. This is what they learned about running plagiarism checks first, then AI detection, and why the combination caught more than either tool alone.

Read →

General 12 min

Priya Sharma · 1 month ago

How Purdue Northwest Caught 34% More AI-Generated Code

After years of relying on MOSS to spot peer-to-peer code plagiarism, the CS department at Purdue Northwest saw a new problem: students submitting AI-generated code that looked original to traditional checkers. By adding an AI code detector and web‑source matching to their pipeline, they flagged 34% more AI‑written assignments in a single semester — giving instructors the concrete evidence they needed to uphold academic integrity.

Read →

General 10 min

Priya Sharma · 1 month ago

Side-by-Side AI and Plagiarism Detection in CS2

We ran both MOSS and an AI-generated code detector on all submissions across a semester of Data Structures. What we learned about catching ChatGPT-authored code — and where MOSS still shines — changed how our department thinks about academic integrity tooling.

Read →

General 11 min

Priya Sharma · 2 months ago

Automating Code Plagiarism and AI Checks in GitHub Classroom

GitHub Classroom automates assignment distribution, but grading still exposes copied code and AI-authored submissions late in the semester. By wiring Codequiry’s dual-purpose API into a GitHub Actions pipeline, instructors can flag both traditional plagiarism and LLM-generated solutions the moment a student pushes. This walkthrough shows the exact YAML and shell scripts you need, plus how to interpret the structured similarity and AI probability reports that come back.

Read →

General 7 min

Rachel Foster · 2 months ago

Across Two Semesters, AI Code Detector Accuracy Hit 87% in Python

A two-semester experiment at a mid-sized CS department put Codequiry’s AI code detector to the test across 1,200 student submissions. The tool achieved 87% overall accuracy in identifying AI-generated Python code, with a manageable false-positive rate and strong recall. The study surfaced distinct patterns in where detection excels—and where manual judgment remains essential.

Read →