Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lueckmann, Jan-Matthis, Jain, Viren, Januszewski, Michał
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911421806149632
author Lueckmann, Jan-Matthis
Jain, Viren
Januszewski, Michał
author_facet Lueckmann, Jan-Matthis
Jain, Viren
Januszewski, Michał
contents Constructing mechanistic models of neural circuits is a fundamental goal of neuroscience, yet verifying such models is limited by the lack of ground truth. To rigorously test model discovery, we establish an in silico testbed using neuromechanical simulations of a larval zebrafish as a transparent ground truth. We find that LLM-based tree search autonomously discovers predictive models that significantly outperform established forecasting baselines. Conditioning on sensory drive is necessary but not sufficient for faithful system identification, as models exploit statistical shortcuts. Structural priors prove essential for enabling robust out-of-distribution generalization and recovery of interpretable mechanistic models. Our insights provide guidance for modeling real-world neural recordings and offer a broader template for AI-driven scientific discovery.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04492
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
Lueckmann, Jan-Matthis
Jain, Viren
Januszewski, Michał
Neurons and Cognition
Artificial Intelligence
Machine Learning
Constructing mechanistic models of neural circuits is a fundamental goal of neuroscience, yet verifying such models is limited by the lack of ground truth. To rigorously test model discovery, we establish an in silico testbed using neuromechanical simulations of a larval zebrafish as a transparent ground truth. We find that LLM-based tree search autonomously discovers predictive models that significantly outperform established forecasting baselines. Conditioning on sensory drive is necessary but not sufficient for faithful system identification, as models exploit statistical shortcuts. Structural priors prove essential for enabling robust out-of-distribution generalization and recovery of interpretable mechanistic models. Our insights provide guidance for modeling real-world neural recordings and offer a broader template for AI-driven scientific discovery.
title Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
topic Neurons and Cognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.04492