The fifth edition of the Roma-BZCAT catalog (5BZCAT) contains 227 blazars of the uncertain type (BZU), whose available data do not support an unambiguous assignment to the BL Lacertae object (BZB), flat-spectrum radio quasar (BZQ), or host-galaxy-dominated blazar-like source (BZG) categories. We construct a machine-readable value-added catalog for these sources using 1151 BZB, 1909 BZQ, and 274 BZG catalog entries as the supervised reference sample. The compact input set contains redshift, optical magnitude, radio, X-ray, and gamma-ray measurements; missingness indicators; and spectral slopes connecting the radio, optical, and X-ray bands. Redshift and its availability are explicitly treated as optical-spectroscopy-related label proxies. Cross-validation shows that the Light Gradient Boosting Machine (LightGBM) provides the most reliable probability scores among the tested models, although the stacking ensemble gives a slightly higher balanced accuracy. The final catalog reports LightGBM probabilities and contains 61 BZB-like, 120 BZQ-like, and 46 BZG-like sources; 17 are flagged for low probability separation. These probabilities quantify similarity to existing 5BZCAT labels conditional on catalog measurements, rather than an independent physical taxonomy.

We present an uncertainty-aware, fine-grained multiclass classification of unresolved Fermi Large Area Telescope (LAT) gamma-ray sources in the 4FGL-DR4 catalog. We define the unresolved-source population as blank-class sources, sources labeled “ UNK ,” and blazar candidates of uncertain type, and classify them within a supervised 22-class catalog taxonomy. The baseline analysis represents each source through the three catalog spectral forms—power law (PL), log parabola (LP), and PL with a superexponential cutoff (PLEC)—and compares TabNet, random forest, and a stacked TabNet + random forest ensemble. The ensemble reaches accuracies of 92.95%, 92.45%, and 94.13% for the PL, LP, and PLEC representations, respectively. To quantify the role of feature choice, we further perform controlled ablations using an all-spectral configuration, which combines PL, LP, and PLEC parameters simultaneously, together with LP-only, PL-only, PLEC-only, and photometry + variability representations. Each configuration is tested with and without uncertainty columns and with λ max = 0.1 –0.5 for synthetic interpolation. The strongest ablation result is obtained by the uncertainty-aware PLEC configuration, with accuracy and weighted F ₁ of 0.9614. We also provide probabilistic predictions for all 4186 unresolved sources, including top-3 class probabilities, full class-probability vectors, top 1 – top 2 probability margins, and predictive entropy.

The rapid growth of in-vehicle applications has driven the adoption of edge computing in the Internet of Vehicles, enabling resource-constrained vehicles to offload tasks for efficient execution. However, this optimization is challenging due to dynamic network conditions and the need to balance latency, energy, and task completion, making real-time optimal solutions intractable. To address these issues, this paper investigates a heterogeneous computing architecture consisting of task vehicles, idle serving vehicles, and roadside units, and formulates a multi-objective optimization model that jointly minimizes system latency, energy consumption, and task dropping rate. To tackle the decision-making challenges arising from vehicle mobility, channel fluctuations, and dynamic node load variations, a Time-varying Topology Adaptation Algorithm is proposed. The algorithm incorporates a dual adaptive mechanism: an internal parameter adaptation module that dynamically balances the exploration and exploitation capabilities of the algorithm, and an external environment-aware adaptation mechanism that integrates real-time multi-dimensional states to align heuristic rules with the dynamic network environment. Theoretical analysis verifies the convergence of the algorithm under dynamic constraints. Finally, comparative experiments on real-world datasets validate the effectiveness of the proposed algorithm in improving system utility, latency, energy consumption, and task dropping rate under high-mobility and high-load conditions. The source code is publicly available at https://github.com/Lose-Code/TTA.