PreprintLicence not statedChemRxiv
Accept or abstain? A pre-specified test of reliability gates calibrated on held-out chemistry for molecular property and reaction-yield models
- 1Blackthorn AI Ltd.
Related
- Polymer Informatics Atlas: Property-Specific Representations, Chemistry-Aware Generalization, and Reliability-Aware Machine Learning Across Five Polymer Properties
- Molecular Property Prediction with Well-Calibrated Uncertainties via Graph Neural Networks and Conformal Quantile Regression
- Systematic evaluation of LLM-based zero-shot model construction in chemistry and materials science: predictive performance and response reliability
- Fluorinated carbon nanotubes for electrochemical energy storage: from bonding chemistry to structure–property relationships
- Physics-Guided Learning with Calibrated Uncertainty for Molecular Thermodynamics Beyond Observed Chemical Space
BibTeX
@misc{gurbych2026accept,
title = {{Accept or abstain? A pre-specified test of reliability gates calibrated on held-out chemistry for molecular property and reaction-yield models}},
author = {Oleksandr Gurbych},
howpublished = {ChemRxiv},
year = {2026},
month = nov,
doi = {10.26434/chemrxiv.15011706/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011706/v1},
}
RIS
TY - UNPB
TI - Accept or abstain? A pre-specified test of reliability gates calibrated on held-out chemistry for molecular property and reaction-yield models
AU - Oleksandr Gurbych
PY - 2026
DA - 2026/11/04
PB - ChemRxiv
DO - 10.26434/chemrxiv.15011706/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011706/v1
ER -