Deep hypergraph learning is evaluated almost entirely through leaderboards that rank methods by mean accuracy over a few random seeds, usually without significance testing. Is there a best hypergraph neural network, or does the apparent ordering reflect seed noise? We independently recomputed the node-classification track of DHG-Bench on a single GPU with twenty random seeds (against five upstream) and a different software stack, and applied a four-layer statistical audit to the per-seed accuracies: a reproducibility check, per-dataset paired Wilcoxon tests with Holm correction, an across-datasets Friedman/Iman–Davenport omnibus with Nemenyi and Holm-corrected pairwise tests, and a variance decomposition. Within a single dataset, twenty seeds distinguish most method pairs (74–98%), so the protocol is not underpowered. Across the nine datasets where all 17 methods complete, the omnibus rejects global equality (Kendall’s W=0.45), yet no pair survives Holm correction, and the top methods fall within one critical-difference band. One dataset carries more seed noise than between-method signal and cannot rank methods. The recompute also documents a non-reproducible method, a label-range data fault, and missing per-dataset configurations in the public release. No single method is statistically best across these datasets, so single-leader claims are not supported; we release a reusable significance-aware evaluation protocol.
V. Tynchenko, S. Kurashkin, Alexey S. Borodulin et al.· Machine Learning and Knowled...· 0 citations
Spent water-based drilling fluids generated during the construction of technological wells impose substantial environmental, water-management, transportation, and energy burdens. Conventional practices, including storage in temporary pits, prolonged settling, and off-site disposal, do not enable process-water recovery and require repeated handling of suspensions with a high solids content. This study evaluates a pressure-driven cylindrical hydrodynamic disperser as the central component of a compact on-site treatment system. Unlike conventional mechanical mixers, the disperser contains no driven shaft within the active chamber. Particle–reagent contact is intensified through controlled jet shear, vortex-induced redistribution, and the motion of freely moving steel balls. Field-derived drilling fluids containing 30–40 wt.% solids, with densities of 1.12–1.17 g/cm3, pH values of 7.4–8.2, and median particle sizes of 15–50 μm, were treated at velocity gradients of 500–1500 s−1 for 60–180 s using Superfloc N-300 dosages of 0–100 g/t. The optimal operating conditions were G = 1300 s−1, τ = 150 s, and D = 50 g/t. Under these conditions, the separation efficiency reached 91–93%, the residual suspended-solids concentration decreased to 120–130 mg/L, process-water recovery reached 80%, sludge volume decreased by 40–60%, and specific energy consumption was approximately 0.30 kWh/m3. More intensive treatment increased the separation efficiency to 94–95% but resulted in a less favorable balance among energy consumption, reagent dosage, and resource recovery. Compared with mechanical mixing, the selected treatment system reduced flocculant consumption by 37.5%, treatment time by more than threefold, and specific energy consumption by 40%. These results support the use of modular on-site systems for process-water recirculation and reduced sludge-transport requirements at remote drilling sites.
B. Mauletbekova, B. Kaliyev, B. Myrzakhmetov et al.· Applied Sciences· 1 citation
This review is, to the authors' knowledge, the first organised around the current generation of tabular foundation models, and taxonomises the architectures by pretraining regime, maps the capability space across five axes, isolates the language-model-on-tabular strand for prediction, feature engineering and generation, and summarises openness and deployment.
S. Kurashkin, V. Tynchenko, Alexey S. Borodulin et al.· Machine Learning and Knowled...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
