A study posted to arXiv (2610.00314v1) found that predictive credit for research-agent explanations remained unconfirmed across 336 prospective states in controlled learning, 12 Tox21 endpoints, and 2…
SMILESGNN, a multimodal architecture that fuses a SMILES Transformer encoder with a GATv2 graph encoder via cross-attention, achieved AUC-ROC 0.987 and F1 0.906 on ClinTox with only 0.4M parameters, a…
A new modular Context-Augmented Prompting framework boosts small language model accuracy in molecular property predictions by up to 74% on the Tox21 dataset, using graph-derived context from a trained…
A new Context-Augmented Prompting framework improves molecular property prediction in small language models by integrating graph-based tools, achieving up to 74% relative accuracy gains on Tox21, thou…