
Soft-error detection in resource-constrained out-of-order processors requires balancing reliability against the cost of redundant execution. This paper proposes an independent dual-trajectory mechanism that preserves separate data-dependence chains while sharing physical backend resources, with error checking at selected architectural-event boundaries. Evaluation on SPECint2006 shows that redundant execution costs 18.3% geometric-mean IPC, versus 5.5% for a SHREC-like checker, along with higher protection-logic area. A 2400-injection campaign achieves an 86.4% conditional detection rate and a 78.5% reduction in adjudicated silent data corruption (SDC) relative to a detection-disabled baseline. A targeted ablation further demonstrates the benefit of independent value propagation, increasing detection from 8.7% to 84.3% compared with shared-source execution. These results quantify the reliability benefits of logical independence and its associated performance and hardware costs within a fixed-capacity out-of-order backend.
Offline reinforcement learning aims to learn effective policies from fixed datasets without further interaction with the environment. However, limited behavior-policy coverage can lead to value-estimation errors and unreliable policy improvement, particularly when multiple critics provide conflicting update directions. To address these challenges, we propose Probability-Ratio-Constrained Q-Learning (PCR-QL), which integrates behavior-density modeling, conservative ensemble-based Q-learning, and probability-ratio-regularized policy extraction to control distributional shift. Building on this framework, we further introduce Consensus-Gated PCR-QL (CG-PCR-QL), which evaluates critic-specific actor gradients using shared states and policy noise and adaptively attenuates the ensemble-mean policy-improvement direction according to the weakest critic-gradient agreement. Theoretically, we establish results connecting ratio-constrained Bellman approximation, behavior-density estimation errors, policy-feasibility repair, and multi-critic gradient geometry, together with conditional guarantees for completed optimizer updates. Experiments on eleven Datasets for Deep Data-Driven Reinforcement Learning (D4RL) benchmark tasks compare nine policy-extraction rules across ten matched runs. CG-PCR-QL achieves a mean performance improvement of +6.32 (95% CI [5.14, 7.50]) over PCR-QL and a pooled interquartile-mean (IQM) improvement of +7.19 [5.63, 8.69]. Furthermore, an analysis of 2400 paired Adam-update events shows an increase of +13.0 [11.1, 14.9] percentage points in the frequency of simultaneous improvement across all critics. Additional ablations and diagnostics examine the effects of gradient consensus, behavior-density estimation, parameter sensitivity, and computational cost. These results highlight the effectiveness of integrating probability-ratio constraints with critic-gradient consensus for more reliable policy improvement in offline reinforcement learning.
This paper introduces a new sixth-order (2+1)-dimensional generalized Calogero–Bogoyavl enskii–Schiff (S2GCBS) equation and provides exact analytical solutions by using Physics-Informed Neural Network simulation (PINNs). By applying an appropriate traveling wave transformation, the governing nonlinear partial differential equation is reduced to an ordinary differential equation. A systematic solution procedure is then employed to derive several classes of exact solutions. As a result, different types of wave structures are obtained, including hyperbolic function solutions (soliton solutions), trigonometric function solutions (periodic wave solutions), and rational solutions. In particular, the obtained results contain bright soliton solutions, dark soliton solutions, singular soliton solutions, and periodic wave solutions expressed in compact analytical forms. These solutions reveal the rich dynamical behavior of the gCBS model and demonstrate the effectiveness of the proposed method in constructing exact solutions for nonlinear evolution equations arising in mathematical physics. The physical characteristics of the obtained solutions are illustrated through several graphical representations.
Scene text image super-resolution must preserve character identity and glyph geometry, including approximate symmetry where present and asymmetric details that distinguish characters. Erroneous optical character recognition (OCR) priors can distort characters during generative reconstruction. We combine constrained large language model (LLM) correction and Mamba-based visual sequence modeling in a conditional residual diffusion method. The LLM proposes replacements within OCR candidate and edit constraints; deterministic validation rejects invalid suggestions and retains the original transcription. Corrected text, position, and low-resolution structural priors are fused by sample-level reliability gating and injected through cross-attention. A bottleneck Mamba block models horizontal visual dependencies. Under separately trained TextZoom and Real-CE protocols, the method achieves peak signal-to-noise ratios of 25.06 and 24.38 dB and exact-match accuracies of 83.4% and 50.2%, respectively. Five-seed paired ablations show that constrained OCR correction improves full-model reconstruction by 0.07 dB in PSNR and 0.6 percentage points in exact-match accuracy on both TextZoom and Real-CE, with the corresponding 95% confidence intervals excluding zero. Compared with the tested lightweight Transformer, Mamba reduces reconstruction latency by 7.82 ms with comparable quality. Independent recognition evaluation supports improved readability. The results support constrained correction and complementary visual conditioning.
During symmetrical faults in photovoltaic (PV)-integrated distribution networks, induction motor (IM) deceleration elevates reactive-power demand and delays post-fault voltage recovery, whereas conventional voltage-driven support can withdraw prematurely upon initial voltage rebound. To resolve this mismatch, this paper proposes a coordinated transient voltage support (CTVS) strategy that explicitly incorporates IM electromechanical dynamics. A coupled differential-algebraic equation (DAE) model integrating third-order IM dynamics, distributed PV (DPV) DC-link dynamics, and network power balance is formulated, from which a trajectory-local closed-loop Q–V sensitivity is derived to characterize location-dependent support effectiveness. The CTVS controller coordinates critical-bus voltage magnitude, voltage-decrease rate, and rotor slip through fixed spatial participation coefficients under local converter current limits and DC-link voltage feedback. Case studies on a modified IEEE 33-bus feeder under Bus-32 three-phase faults demonstrate that, for the representative 140 ms fault, CTVS suppresses post-fault secondary voltage depression and reduces the sustained recovery delay to 23.85 ms, compared with 342.30 ms for local low-voltage ride-through and 390.85 ms for adaptive Q–V droop control. Matched ablations identify slip-conditioned support persistence as the principal contributor to sustained voltage recovery, whereas the fixed spatial coefficients provide a local allocation advantage under unsaturated conditions rather than a separate large-disturbance recovery benefit under the tested conditions.