# Detecting AI Assistance in Abstract Complex Tasks

arXiv: https://arxiv.org/abs/2507.10761 · HTML: https://mlsanity.com/paper/2507.10761/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 53 references that are in the map.
- First posted on arXiv 14 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks](https://mlsanity.com/paper/1907.04595/) (2019)
- [GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training](https://mlsanity.com/paper/2009.03294/) (2020)
- [A Comparison of LSTM and BERT for Small Corpus](https://mlsanity.com/paper/2009.05451/) (2020)
- [Why are Adaptive Methods Good for Attention Models?](https://mlsanity.com/paper/1912.03194/) (2019)
- [Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory](https://mlsanity.com/paper/2012.03083/) (2020)
- [The exploding gradient problem demystified - definition, prevalence, impact, origin, tradeoffs, and solutions](https://mlsanity.com/paper/1712.05577/) (2017)
- [REX: Rapid Exploration and eXploitation for AI Agents](https://mlsanity.com/paper/2307.08962/) (2023)
- [Are ResNets Provably Better than Linear Predictors?](https://mlsanity.com/paper/1804.06739/) (2018)
- [An Introduction to Neural Architecture Search for Convolutional Networks](https://mlsanity.com/paper/2005.11074/) (2020)
- [Are deep ResNets provably better than linear predictors?](https://mlsanity.com/paper/1907.03922/) (2019)
- [The Role of Heuristics and Biases During Complex Choices with an AI Teammate](https://mlsanity.com/paper/2301.05969/) (2023)

## Built on by (most cited first, 1 of 1)

- [Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming](https://mlsanity.com/paper/2609.17883/) (2026)

## Abstract (arXiv)

Detecting assistance from artificial intelligence is increasingly important as they become ubiquitous across complex tasks such as text generation, medical diagnosis, and autonomous driving. Aid detection is challenging for humans, especially when looking at abstract task data. Artificial neural networks excel at classification thanks to their ability to quickly learn from and process large amounts of data -- assuming appropriate preprocessing. We posit detecting help from AI as a classification task for such models. Much of the research in this space examines the classification of complex but concrete data classes, such as images. Many AI assistance detection scenarios, however, result in data that is not machine learning-friendly. We demonstrate that common models can effectively classify such data when it is appropriately preprocessed. To do so, we construct four distinct neural network-friendly image formulations along with an additional time-series formulation that explicitly encodes the exploration/exploitation of users, which allows for generalizability to other abstract tasks. We benchmark the quality of each image formulation across three classical deep learning architectures, along with a parallel CNN-RNN architecture that leverages the additional time series to maximize testing performance, showcasing the importance of encoding temporal and spatial quantities for detecting AI aid in abstract tasks.