CORTEXA
← Browse
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24Cited by 0

Chemistry-stratified reliability audit of selective abstention for universal machine-learning interatomic potentials

Zeyu Fu

Version 0.3.0 provides the sanitized, hermetic code and frozen result records supporting the chemistry-stratified selective-abstention analysis. It includes the 32-UIP roster analysis, prototype-blocked confidence intervals, mechanism and sensitivity controls, manuscript sources, deterministic tests, and a vendored MIT-licensed subset of relmetrics. External Matbench Discovery prediction files are not redistributed; DATA_MANIFEST.md records their filenames, sizes, and SHA-256 checksums.

View free PDFSource page

Related papers

openalexZenodo (CERN European Organization for Nuclear Research)2026-07-26

Interpretable machine-learning risk stratification at diagnosis for 3-year mortality in de novo metastatic prostate cancer (SEER): reproducibility code

Xin Wang, Guanglei Yao, Wei Ding

This archive contains the analysis code, the predictor dictionary, and the retrained primary model objects underlying the manuscript "Interpretable machine-learning risk stratification at the time of diagnosis for 3-year mortality in de novo metastatic prostate cancer: developmen…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-25

Harmonized soil-erosion database and machine-learning erodibility predictor for overtopping dam-breach forecasting

Hongning Lu

It provides (1) a harmonized multi-device soil-erosion database — 1,146 specimen records from EFA, SETD, JET, HET and related devices (1,013 with critical shear stress and 972 with erodibility coefficient), 186 raw erosion-rate-versus-shear-stress curves with power-law fits, and…

View free PDFSource page
openalexZenodo (CERN European Organization for Nuclear Research)2026-07-24

Code and data for: Leakage-audited machine learning versus ETAS for earthquake forecasting in the Sea of Marmara

Basri Kerem Alhan, Kenessary Khabat

Code, processed data products, configuration, and results artifacts for "Machine learning versus ETAS for earthquake forecasting in the Sea of Marmara: a leakage-audited negative result and a closed-form scoring artifact" (Alhan & Khabat, submitted to Seismica). Version 1.2.0 acc…

View free PDFSource page