Nov 15, 2026 Codequiry software is now free and a one-time payment for lifetime access. See plans →
Priya Sharma

Priya Sharma

AI Research & Education Specialist at Codequiry

Priya studies AI-assisted coding in the classroom and how detection tools hold up against ChatGPT, Copilot, Claude and Gemini output.

Articles by Priya Sharma

How a Course Coordinator Automates Weekly Code Integrity Checks General 13 min
Priya Sharma Priya Sharma • 9 hours ago

How a Course Coordinator Automates Weekly Code Integrity Checks

A weekly integrity pass over a 1,100-submission CS1 cohort takes about 90 minutes once it is scripted: peer similarity, web source matching, and AI generation scoring funnel into one triage table. Here is the full workflow, including the thresholds, the calibration data behind them, and the places where the numbers stop being trustworthy.

A Year of AI Code Detection Across 4,120 Submissions General 10 min
Priya Sharma Priya Sharma • 1 week ago

A Year of AI Code Detection Across 4,120 Submissions

A mid-sized public university ran AI generation scoring, peer similarity, and web-source matching over a full academic year of computer science submissions. The detector numbers were the easy part. What the department actually learned came from a 312-submission control set, a kappa of 0.58, and a six-fold spread in how instructors responded to the same score.

How Code Similarity Detection Moved From Lines to Trees General 9 min
Priya Sharma Priya Sharma • 1 week ago

How Code Similarity Detection Moved From Lines to Trees

Three decades of code similarity detection can be told as two changes in the unit of comparison, from lines to token sequences to syntax trees. Each shift shrank the review queue by an order of magnitude. Here's what each era bought, what it still misses, and how generated code forced the field to add a second axis.

Building a Token-Based Code Similarity Checker in Python General 12 min
Priya Sharma Priya Sharma • 3 weeks 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.

Running AI Code Detection on Take-Home Interview Submissions General 10 min
Priya Sharma Priya Sharma • 3 weeks 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.

How a Lead TA Triages 400 Similarity Reports Before Grades Post General 10 min
Priya Sharma Priya Sharma • 1 month 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.

A Framework for Reading AI Code Detection Scores General 9 min
Priya Sharma 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.

What One CS Department Learned From a Year of AI Code Detection General 11 min
Priya Sharma Priya Sharma • 2 months 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.

Interpreting Code Similarity Scores in Programming Courses General 9 min
Priya Sharma Priya Sharma • 2 months 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.

What 41,000 Code Submissions Reveal About Similarity Score Thresholds General 9 min
Priya Sharma Priya Sharma • 2 months 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.

Similarity Score Distributions Across Four Intro CS Languages General 12 min
Priya Sharma Priya Sharma • 3 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.

Detecting Stack Overflow Code in Student Java Submissions General 10 min
Priya Sharma Priya Sharma • 3 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.