Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repair
Abstract
Repairing scientific models from functional observations differs fundamentally from supervised prediction: feedback may certify a solution without revealing which structural correction is responsible. We study this setting for genome-scale metabolic model (GEM) repair, where multiple reaction edits can explain the same phenotypes and many apparently distinct edits correspond to the same biological mechanism. This many-to-one structure creates a hidden failure mode for conventional exploration: diversity in the output space need not translate into diversity of scientific hypotheses. We introduce QuotientPO, which collapses equivalent repairs into canonical mechanisms and optimizes exploration directly over the resulting quotient space. To make quotient exploration informative under finite rollouts, we derive a kernelized Rényi estimator that resolves graded crowding among distinct repair cores beyond coarse exact-match counts. On 2,212 held-out GEMs, QuotientPO improves Success@32 from 17.93% to 20.10% (+12.1% relative) while consistently increasing distinct successful-core discovery under the same sampling budget. These results establish quotient-space exploration as a principled approach to mechanism-level discovery under verifier-induced equivalence.
Related
- Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
- Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
- Beyond the target: new dimensions of antifungal action
- Beyond traditional criteria: CRP and fibrinogen as biomarkers of metabolic syndrome in ART-treated people living with HIV and their association with HIF-1α rs11549465
- Distinct metabolic signatures define key HIV-1 clinical phenotypes and reveal targets beyond viral suppression
BibTeX
@misc{gong2026beyond,
title = {{Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repair}},
author = {Xuan Gong and Hanbo Huang and Wenbin Dai and Jing Wang and Lei Bai and Xiang Xiao and Weishu Zhao and Shiyu Liang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11627},
eprint = {2610.11627},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11627},
}
RIS
TY - UNPB
TI - Beyond Action Entropy: Quotient-Space Exploration for Genome-Scale Metabolic Model Repair
AU - Xuan Gong
AU - Hanbo Huang
AU - Wenbin Dai
AU - Jing Wang
AU - Lei Bai
AU - Xiang Xiao
AU - Weishu Zhao
AU - Shiyu Liang
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11627
UR - https://arxiv.org/abs/2610.11627
AB - Repairing scientific models from functional observations differs fundamentally from supervised prediction: feedback may certify a solution without revealing which structural correction is responsible. We study this setting for genome-scale metabolic model (GEM) repair, where multiple reaction edits can explain the same phenotypes and many apparently distinct edits correspond to the same biological mechanism. This many-to-one structure creates a hidden failure mode for conventional exploration: diversity in the output space need not translate into diversity of scientific hypotheses. We introduce QuotientPO, which collapses equivalent repairs into canonical mechanisms and optimizes exploration directly over the resulting quotient space. To make quotient exploration informative under finite rollouts, we derive a kernelized Rényi estimator that resolves graded crowding among distinct repair cores beyond coarse exact-match counts. On 2,212 held-out GEMs, QuotientPO improves Success@32 from 17.93% to 20.10% (+12.1% relative) while consistently increasing distinct successful-core discovery under the same sampling budget. These results establish quotient-space exploration as a principled approach to mechanism-level discovery under verifier-induced equivalence.
ER -