Code Intelligence Hub

General 8 min

Marcus Rodriguez · 1 month ago

Grading Assignments to Detect AI-Generated Code in Student Submissions

Most AI-generated code in student submissions goes unnoticed when instructors rely on intuition or a single detector. This research-style guide explains how to layer statistical signals, peer similarity, web-source checks, and rubric design to reliably catch AI-assisted code without manufacturing false positives.

Read →

General 8 min

James Okafor · 1 month ago

ChatGPT vs Copilot vs Gemini Code Detection Benchmarked

A head-to-head evaluation of AI code detection across ChatGPT-4o, GitHub Copilot, Claude 3.5 Sonnet, and Gemini 1.5 Pro. One pattern kept surfacing: text-only detectors miss refactored LLM code, while structural and multi-signal checks hold up.

Read →

General 7 min

Rachel Foster · 1 month ago

A Hiring Manager's Audit of AI-Generated Code in Take-Home Tests

An engineering leader audit of 1,284 remote take-home coding submissions found 31.2% flagged as likely AI-generated at high confidence. Manual review confirmed 279 of 401 high-confidence flags, with a 4.5% false positive rate among high-confidence flags. Here is what the data showed and how hiring managers should handle AI detection scores.

Read →

General 11 min

Dr. Sarah Chen · 1 month ago

What Happens When a CS Course Runs Both MOSS and ChatGPT Detectors

Over 1,200 student submissions from a large public university’s introductory Python course were analyzed with Codequiry’s similarity engine and its AI code detector. The results show how traditional plagiarism tools miss a growing fraction of unauthorized work—and why layering AI detection changes what instructors actually see.

Read →

General 11 min

Alex Petrov · 1 month ago

How a University Caught AI-Generated Code in 14Percent of CS2 Submissions

When Riverside University’s CS department ran an AI detector across 300 CS2 assignments alongside MOSS, they discovered a new layer of academic integrity challenges. The case study reveals what they found, how they calibrated thresholds, and why combining AI detection with source-code fingerprinting changed their grading workflow.

Read →

General 11 min

James Okafor · 1 month ago

Token Fingerprinting vs AST Matching on 1,000 Refactored Java Programs

When students rename variables, extract methods, and reorder statements to hide copied code, which detection algorithm actually holds up? A controlled experiment pits winnowing, token-based matching, and AST structural hashing against a ladder of refactoring transformations — and reveals why single-technique checkers miss the cases that academic-integrity panels care about most.

Read →

General 11 min

Marcus Rodriguez · 1 month ago

At What Point Does Token-Based Detection Fail Against Automated Refactoring?

Most plagiarism detectors rely on token streams, which break down as soon as students rename variables, reorder statements, or extract methods. We map the precise failure points, walk through AST-based recovery techniques, and show how fingerprinting fills the gaps that tree comparators leave behind. A must-bookmark deep‑dive for any CS educator or engineering lead who has watched suspect code sail right through a token‑only scanner.

Read →

General 11 min

Priya Sharma · 1 month ago

How Source Code Plagiarism Detection Escaped the Diff Trap

What started as a textual diff in Unix is now a high-stakes algorithmic arms race. This article traces the thirty-year evolution of source code plagiarism detection—from simple token matching and AST comparison to fingerprinting that survives variable renaming, and finally to the fresh challenge of AI-generated code. We examine the real detection rates, the tools that led each era, and where Codequiry fits as the first hybrid platform to unify peer, web, and AI checks in a single reporting workflow.

Read →

General 10 min

Marcus Rodriguez · 1 month ago

15,000 CS Submissions Test 3 Plagiarism Detection Algorithms

Code similarity tools all promise to catch cheaters, but their underlying algorithms differ dramatically. We ran a large-scale experiment—15,000 real CS1 Java submissions, 500 manually verified suspicious pairs—to compare winnowing (MOSS), AST hashing (JPlag-style), and fingerprinting side by side. The results expose which techniques survive renaming, refactoring, and template reuse, and why a layered approach matters for low false‑positive rates in production academic workflows.

Read →

General 14 min

Priya Sharma · 1 month ago

Thirty Years of Detecting Plagiarized Code, Then AI Arrived

When State University of Plains' CS department first faced GitHub Copilot-generated homework in 2022, their decades-old MOSS pipeline was useless. This retrospective traces their journey from manual suspicion to a layered detection stack that caught 31% of submissions as AI-generated last semester — and the hard lessons learned about false positives along the way.

Read →

General 10 min

Rachel Foster · 1 month ago

How Few AST Nodes Do You Need to Catch a Copied Function

A single function with renamed variables, reordered statements, and changed whitespace can still look structurally identical under the hood. This step-by-step guide builds a minimal AST clone detector in Python, explains where it breaks, and shows how production tools like Codequiry stack structural, token‑level, and web‑origin checks to catch the copying that student‑grade normalizers miss.

Read →

General 11 min

Alex Petrov · 1 month ago

Putting a Code Similarity Checker in Your Git Pre-Commit Hook

A copied snippet might survive a human code review after a quick variable rename and loop inversion. A similarity checker that understands ASTs won’t be fooled. This guide walks through wiring Codequiry’s API into your Git pre‑commit workflow, step by step, so every commit is scanned for non‑original code before it hits the branch.

Read →