Complete research compendium for PhysGuard-FL, a physics-aware Byzantine-robust federated-learning framework evaluated for chemical-process monitoring. The frozen benchmark uses six Tennessee Eastman Process operating modes, 20 federated clients, 20 communication rounds, five local steps, and 10 matched random seeds. The primary robustness benchmark comprises 70 runs across seven aggregation methods under model-replacement attacks with 30% Byzantine clients. The secondary benchmark comprises 40 runs across four shared aggregation methods under sign-flip attacks with 20% Byzantine clients. The archive preserves all 110 run-level experiment outputs, original summaries, Student-t 95% confidence intervals, paired t-tests, Wilcoxon signed-rank tests, Holm-adjusted p-values, seed-wise wins and ranks, cross-attack comparisons, figures, documentation, and executable statistical post-processing scripts. The package supports transparent statistical auditing and reproducibility of the quantitative results reported in the associated PhysGuard-FL study.
Miguel Ángel Cornelio-Chujutalli, King Klaus Ramírez-Pizango, Karenth Elena Ramírez Álvarez· Zenodo (CERN European Organi...· 0 citations
Complete research compendium for PhysGuard-FL, a physics-aware Byzantine-robust federated-learning framework evaluated for chemical-process monitoring. The frozen benchmark uses six Tennessee Eastman Process operating modes, 20 federated clients, 20 communication rounds, five local steps, and 10 matched random seeds. The primary robustness benchmark comprises 70 runs across seven aggregation methods under model-replacement attacks with 30% Byzantine clients. The secondary benchmark comprises 40 runs across four shared aggregation methods under sign-flip attacks with 20% Byzantine clients. The archive preserves all 110 run-level experiment outputs, original summaries, Student-t 95% confidence intervals, paired t-tests, Wilcoxon signed-rank tests, Holm-adjusted p-values, seed-wise wins and ranks, cross-attack comparisons, figures, documentation, and executable statistical post-processing scripts. The package supports transparent statistical auditing and reproducibility of the quantitative results reported in the associated PhysGuard-FL study.
Miguel Ángel Cornelio-Chujutalli, King Klaus Ramírez-Pizango, Karenth Elena Ramírez Álvarez· Zenodo (CERN European Organi...· 0 citations
ThermoDiff-PCM is a reproducibility package for physics-guided transfer diffusion applied to the inverse design of protic organic salt phase-change materials. The archive contains curated PCM development and locked validation tables, preprocessing and modeling scripts, trained checkpoints, leakage-control documentation, external inverse-retrieval results, statistical tests, manuscript figures, and chemically refined expanded-space candidate rankings. The PCM-specific development set contains 69 protic organic salts, with 7 additional experimentally evaluated salts retained as a locked unseen-combination validation set. Auxiliary ionic-liquid melting-point data were used for leakage-controlled transfer pretraining after removal of exact PCM/external pair overlaps. Generated candidates are computational priorities and should not be interpreted as experimentally validated discoveries.
Miguel Ángel Cornelio-Chujutalli, Karenth Elena Ramírez Álvarez, King Klaus Ramírez-Pizango· Zenodo (CERN European Organi...· 0 citations
ThermoDiff-PCM is a reproducibility package for physics-guided transfer diffusion applied to the inverse design of protic organic salt phase-change materials. The archive contains curated PCM development and locked validation tables, preprocessing and modeling scripts, trained checkpoints, leakage-control documentation, external inverse-retrieval results, statistical tests, manuscript figures, and chemically refined expanded-space candidate rankings. The PCM-specific development set contains 69 protic organic salts, with 7 additional experimentally evaluated salts retained as a locked unseen-combination validation set. Auxiliary ionic-liquid melting-point data were used for leakage-controlled transfer pretraining after removal of exact PCM/external pair overlaps. Generated candidates are computational priorities and should not be interpreted as experimentally validated discoveries.
Miguel Ángel Cornelio-Chujutalli, Karenth Elena Ramírez Álvarez, King Klaus Ramírez-Pizango· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
