On chemistry SMILES with a fixed 165-token base, BPE and Unigram-LM produce near-disjoint vocabularies (Jaccard ≤0.161) and Unigram-LM emits 29–41% more tokens across 22 matched conditions.
tmQM dataset—quantum geometries and properties of 86k transition metal complexes.Journal of Chemical Information and Modeling, 60(12):6135–6146, 2020
2 Pith papers cite this work, alongside 128 external citations. Polarity classification is still indexing.
2
Pith papers citing it
128
external citations · OpenAlex
years
2026 2representative citing papers
The paper introduces Experiment-as-Code Labs as a declarative stack synthesizing AI agents, systems orchestration, and physical lab control for AI-driven discovery.
citing papers explorer
-
Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
On chemistry SMILES with a fixed 165-token base, BPE and Unigram-LM produce near-disjoint vocabularies (Jaccard ≤0.161) and Unigram-LM emits 29–41% more tokens across 22 matched conditions.
-
Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery
The paper introduces Experiment-as-Code Labs as a declarative stack synthesizing AI agents, systems orchestration, and physical lab control for AI-driven discovery.