Generic molecular encoders show weak alignment with human olfactory rating geometry and no clear predictive increment over an RDKit-Morgan chemistry baseline, while human rating geometry is reproducible within but only partially across datasets.
Title resolution pending
1 Pith paper cite this work, alongside 292 external citations. Polarity classification is still indexing.
1
Pith paper citing it
292
external citations · OpenAlex
fields
q-bio.QM 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Predictive Accuracy: A Reliability-Aware Audit of Molecular Representations for Human Olfaction
Generic molecular encoders show weak alignment with human olfactory rating geometry and no clear predictive increment over an RDKit-Morgan chemistry baseline, while human rating geometry is reproducible within but only partially across datasets.