Local-correlation ML

CCSD(T) is quantum chemistry’s accuracy standard and too expensive to run routinely. This project asks whether the cheap byproducts of a local-correlation calculation, pair natural-orbital occupations and MP2 pair energies, carry enough signal for a small model to predict the full CCSD(T) correlation energy. Every pass/fail criterion was locked in writing before scoring, and negative results are reported at full weight.

A Gaussian process on twelve physics-motivated aggregates reaches 0.83 kcal/mol at 400 training molecules, under the pre-registered 1.0 kcal/mol bar. The per-pair neural ansatz the project was built to test fails, and a free-form DeepSets never catches the hand-crafted features even at 6000 molecules.

The uncertainty rounds are the practical payoff. The model’s own variance ranks molecules from an unseen element regime almost perfectly, but its error bars are wrong there, and all three label-free recalibration methods registered for the problem fail. About ten labels from the new regime restore trustworthy bars, and spending early shifted labels on training beats spending them on calibration.

The repository ships the frozen pre-registration documents, the committed results, and a test suite that machine-checks every number quoted in the README against them.