View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $9K - $13K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (45)

[1]
Explaining GNN Explanations with Edge Gradients
2025Jesse He, Akbar Rafiey et al.
[2]
Can Interpretation Predict Behavior on Unseen Data?
2025V. Li, Jenny Kaufmann et al.
[3]
Graph neural networks extrapolate out-of-distribution for shortest paths
2025Robert R. Nerem, Samantha Chen et al.
[4]
EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification
2025Lin Zhang, Wenshuo Dong et al.
[5]
The Complexity Dynamics of Grokking
2024Branton DeMoss, Silvia Sapora et al.
[6]
Progressive distillation induces an implicit curriculum
2024Abhishek Panigrahi, Bing Liu et al.
[7]
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
2024Neil Rohit Mallinar, Daniel Beaglehole et al.
[8]
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
2024Lei Yu, Jingcheng Niu et al.
[9]
Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
2024Michael Hanna, Sandro Pezzelle et al.
[10]
Attribution Patching Outperforms Automated Circuit Discovery
2023Aaquib Syed, C. Rager et al.
[11]
Grokking as the Transition from Lazy to Rich Training Dynamics
2023Tanishq Kumar, Blake Bordelon et al.
[12]
SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning
2023Julian Minder, Florian Grötschla et al.
[13]
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks
2023Ziqian Zhong, Ziming Liu et al.
[14]
Towards Automated Circuit Discovery for Mechanistic Interpretability
2023Arthur Conmy, Augustine N. Mavor-Parker et al.
[15]
Progress measures for grokking via mechanistic interpretability
2023Neel Nanda, Lawrence Chan et al.
[16]
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
2022Kevin Wang, Alexandre Variengien et al.
[17]
Omnigrok: Grokking Beyond Algorithmic Data
2022Ziming Liu, Eric J. Michaud et al.
[18]
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
2022B. Barak, Benjamin L. Edelman et al.
[19]
GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
2022Kenza Amara, Rex Ying et al.
[20]
The CLRS Algorithmic Reasoning Benchmark
2022Petar Velivckovi'c, Adrià Puigdomènech Badia et al.

Showing 20 of 45 references

Founder's Pitch

"Introducing MINAR, a toolbox for discovering neuron-level circuits in GNNs trained for algorithmic reasoning."

Graph Neural NetworksScore: 4View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

1/4 signals

2.5

Quick Build

2/4 signals

5

Series A Potential

1/4 signals

2.5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 2/24/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.