Gap report
MoleculeNet: A Benchmark for Molecular Machine Learning
Wu Z et al. · Chem. Sci., 2018
Benchmark scope and split logic are strong, but some implementation choices still depend on translator defaults.
Specified
Dataset lineup and benchmark framing are explicit.
Metrics are tied to task family.
Scaffold and random split regimes are documented.
Partial
Feature generation differs across benchmarks and is not completely normalized.
Some baseline hyperparameters are described by family, not exact config.
Missing
A single pinned environment for every benchmark variant.
One unified seed policy across all experiments.
Template fit
Benchmark suite
Confidence: High. Reported gaps: 5.
Next step
Use this example gap report as a review aid, then check the matching template coverage before relying on generated defaults for a real paper translation.