Code Intelligence Hub

General 7 min

Rachel Foster · 1 month 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 →

General 12 min

Alex Petrov · 1 month ago

How Winnowing Fingerprints Resist Variable Renaming

Winnowing fingerprinting is the back‑bone of tools like MOSS that spot copied code even after students rename every variable and shuffle blocks. This deep‑dive unpacks the algorithm, its thresholds, and why a multimodal approach—token, AST, and web‑source checking—covers the gaps that fingerprinting alone leaves open.

Read →

General 11 min

Emily Watson · 1 month ago

Scanning a Codebase for GPL Violations Before Acquisition

When ZephyrCloud faced a pre-acquisition license audit, its engineering team turned to automated code similarity scanning after manual searches proved unreliable. The process uncovered several GPL-licensed snippets copied from Stack Overflow and GitHub, forcing a careful remediation effort that saved the deal. Here’s what they learned about using plagiarism detection for open-source compliance.

Read →

General 6 min

James Okafor · 1 month ago

Bootcamps Are Automatically Scanning Every Submission for AI Code

Coding bootcamps that graduate thousands of developers a year are shifting from manual spot-checks to automated AI code detection on every single submission. Here’s a hands‑on guide to building that pipeline with Codequiry’s API — from single‑file scanning to a full CI‑grade batch checker you can run in a GitHub Action.

Read →

General 8 min

James Okafor · 1 month ago

How Code Similarity Detection Grew From Diff to AI

From the early days of the Unix diff command to the rise of MOSS, JPlag, and AI-powered detectors, code similarity detection has undergone a quiet revolution. This retrospective traces the key technical milestones—tokenization, ASTs, fingerprinting, web-source matching, and the new frontier of AI-generated code—showing how each layer made plagiarism harder to hide. See how modern platforms like Codequiry unify these techniques into a single pipeline.

Read →

General 8 min

James Okafor · 1 month ago

Running a Side-by-Side Accuracy Benchmark of Code Plagiarism Checkers

We ran 2,400 real student Java assignments through MOSS, JPlag, Turnitin, and Codequiry with known ground truth. The F1 scores and false positive rates diverged by over 20 percentage points. Here’s what worked, what broke, and how to run your own benchmark.

Read →

General 11 min

James Okafor · 1 month ago

How an Engineering Team Automated Code Originality Checks for Contractors

When a mid-sized software firm started scaling external contractor contributions, they needed a way to verify code originality at scale. By integrating Codequiry’s API into their CI/CD pipeline, they built an automated gate that flagged plagiarized open-source snippets and AI-generated code before it ever hit the main branch. Here’s a look at their process, the false-positive tradeoffs, and the integration that saved their legal review hours.

Read →

General 12 min

Marcus Rodriguez · 1 month ago

Automating Source Code Plagiarism Checks With Canvas and Codequiry

When a single CS1 assignment yields 300+ submissions, manual plagiarism checking simply doesn't scale. This hands-on guide walks through connecting Canvas to Codequiry's API, running similarity and AI-detection scans with a handful of Python scripts, and posting flagged results directly back into the SpeedGrader — so you catch the cases that matter without drowning in paperwork.

Read →

General 11 min

Dr. Sarah Chen · 1 month ago

Designing Plagiarism-Resistant Programming Assignments

Copy-paste code and AI-generated solutions are flooding CS courses. Smart assignment design—parameterized prompts, incremental checkpoints, and open-ended specs—can make copying so cumbersome that students default to doing their own work. This deep dive builds a concrete, reusable playbook for instructors.

Read →

General 12 min

Marcus Rodriguez · 1 month ago

A Triage Protocol for AI-Generated Code in CS Assignments

A single run of an AI detector on a suspicious student submission is not enough. CS professors need a systematic triage protocol that stacks similarity analysis, AI code detection, web-source fingerprinting, and manual review into a defensible pipeline. This article outlines a concrete workflow you can implement this semester.

Read →

General 13 min

Priya Sharma · 1 month ago

A Framework for Scanning AI-Generated Code in Student Submissions

AI large language models can now generate passable code for many introductory CS assignments, leaving instructors scrambling. A systematic scanning framework—combining AI detection, plagiarism analysis, and human review gates—can reliably identify AI-written submissions while respecting due process. Here’s how to build one.

Read →

General 9 min

James Okafor · 1 month ago

Contractor Code Audit at a 50-Person SaaS Startup

When a growing SaaS startup suspected a third‑party deliverable contained unattributed open‑source code, they built a verification pipeline that now scans every contractor commit. Here’s what they learned about trade‑offs, accuracy, and the tools that stuck.

Read →