Priya Sharma

General 12 min

Priya Sharma • 1 day ago

Building a Token-Based Code Similarity Checker in Python

A working build guide to the similarity pipeline behind most academic code checks: tokenization, k-gram fingerprinting, winnowing, and AST shape comparison in roughly 300 lines of Python. Includes the threshold calibration table we used across six assignments and an honest account of where a homegrown checker stops being enough.

Read

General 10 min

Priya Sharma • 1 day 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.

Read

General 10 min

Priya Sharma • 2 weeks ago

How a Lead TA Triages 400 Similarity Reports Before Grades Post

A lead TA at a mid-sized CS department gets 412 similarity pairs back from a single algorithms assignment and has six days to decide which ones matter. This is the triage method she uses: score stacking, cohort-normalized thresholds, and a written rubric that has survived two grade appeals.

Read

General 9 min

Priya Sharma • 1 month ago

A Framework for Reading AI Code Detection Scores

A single AI detection score is a ranking, not a verdict, and most of the damage we've seen comes from reading it as one. This is the five-step triage we settled on after two years of grading CS 1 and CS 2 cohorts of roughly 400 submissions, including the score bands, the script, and the two cases where the whole thing fell apart.

Read

General 11 min

Priya Sharma • 1 month ago

What One CS Department Learned From a Year of AI Code Detection

A public research university ran AI code detection as part of its grading workflow for a full academic year: eleven assignments, three courses, 4,118 submissions. The interesting number isn't the 3.8% that ended in a finding. It's the roughly two flagged files that got cleared for every one that held up, and what the department changed because of it.

Read

General 9 min

Priya Sharma • 1 month ago

Interpreting Code Similarity Scores in Programming Courses

Similarity scores are ranking signals, not verdicts. I'll walk through the distributions, thresholds, and triage rules I use when reviewing code similarity reports for 400-student courses, plus where AI-generated code fits in the same queue.

Read

General 9 min

Priya Sharma • 1 month ago

What 41,000 Code Submissions Reveal About Similarity Score Thresholds

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.

Read

General 12 min

Priya Sharma • 2 months ago

Similarity Score Distributions Across Four Intro CS Languages

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.

Read

General 10 min

Priya Sharma • 2 months ago

Detecting Stack Overflow Code in Student Java Submissions

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.

Read

General 11 min

Priya Sharma • 2 months 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 14 min

Priya Sharma • 2 months 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 12 min

Priya Sharma • 3 months 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