Aero-engine predictive maintenance is challenged by heterogeneous operating conditions, complex degradation patterns, and the need for interpretable maintenance alerts rather than solely numerical life estimates. This study investigates a condition-aware data-driven framework for jet engine health assessment using the NASA C-MAPSS dataset, which contains four benchmark subsets (FD001–FD004) with different operating conditions and fault modes. Instead of formulating the task as conventional remaining useful life regression, this study reformulates degradation assessment as a three-class health state classification problem, including Normal, Warning, and Fault. A unified preprocessing pipeline is developed, incorporating condition-wise normalization, first-order differential feature construction, and per-unit sliding window segmentation to reduce operating-condition bias, capture degradation dynamics, and prevent data leakage. Five representative models are evaluated under the same framework, including XGBoost, LightGBM, Random Forest, a context-aware multi-scale temporal attention convolutional neural network, and a bidirectional long short-term memory network. The results show that the proposed framework achieves consistently high classification accuracy across all four subsets, with the best results of 0.9841 on FD001, 0.9764 on FD002, 0.9891 on FD003, and 0.9832 on FD004. In addition, Bi-LSTM outperforms MSTA-CNN on all subsets, for example improving accuracy from 0.9614 to 0.9747 on FD002 and from 0.9773 to 0.9806 on FD004, which is consistent with the importance of long-term temporal dependency modeling for this task. These findings suggest that the proposed framework provides an effective and maintenance-decision-aligned solution for C-MAPSS-based health monitoring, where the three-class alert output offers clearer operational meaning than a single numerical life estimate.

Using U.S. county health measures and labor-market fundamentals, we predict cross-state employment performance out of sample. We construct an employment relativity index, state employment per capita relative to the contemporaneous U.S. rate, to net out national shocks. We use health measures and non-employment labor-market fundamentals (hiring intensity and earnings), tune tree-based models within the training window, and achieve R2=0.846 on a 2022-2024 holdout. A leakage-safe ridge-stacked ensemble yields R2=0.863. SHAP and rolling-origin tests highlight education, labor-market dynamism, and health burden as stable predictors.

This study examines whether context-validated acute distress disclosures in annual Form 10-K filings improve bankruptcy-risk ranking beyond accounting variables. The analysis links U.S. Securities and Exchange Commission filing data, Item 7 Management’s Discussion and Analysis text, and bankruptcy events from the Florida–UCLA–LoPucki Bankruptcy Research Database for fiscal years 2010–2021. The primary sample contains 21,239 nonfinancial firm-year observations and 159 one-year bankruptcy events. The paper develops a Validated Distress Disclosure (VDD) Dictionary that flags going-concern uncertainty, covenant noncompliance, and lender forbearance or waiver after sentence-level context filtering. In the 2019–2021 holdout test, adding VDD indicators to a six-variable Ohlson-related accounting baseline increases the area under the receiver operating characteristic curve (AUC) from 0.8682 to 0.8827 ($\Delta =0.0146$; 95% confidence interval (CI) [0.0040, 0.0275]) and precision–recall AUC (PR-AUC) from 0.0924 to 0.2060 ($\Delta =0.1136$; 95% CI [0.0458, 0.2132]). Benchmark and decomposition tests indicate that the main signal is concentrated in going-concern disclosures and that VDD is best interpreted as an auditable ranking supplement to accounting variables and broader text models, not as a calibrated probability-of-default model.

LLM safety classifiers such as Llama Guard detect overtly harmful prompts well but remain vulnerable to jailbreaks that disguise intent via role-play, fictional framing, or indirect requests. We present Reflect-Guard: Llama-Guard-3-8B fine-tuned via QLoRA to generate a distilled, GPT-4o-mini-sourced safety rationale before its verdict. Using only 1000training examples and a five-condition ablation, we isolate reflection’s contribution from that of ordinary supervised fine-tuning (SFT). SFT on verdict labels alone already accounts for most of the aggregate gain over the un-fine-tuned baseline (WildGuardTest F₁: 0.770 → 0.860; JailbreakBench guard bypass rate: 10.3% → 0.0%). Adding reflection does not improve these aggregate numbers further (F₁ falls to 0.842, guard bypass rises to 1.8%) but reallocates performance toward adversarially framed inputs: adversarial-subset recall rises from 0.845 (SFT-only) to 0.921 (+7.6 pp), at a cost of −7.9 pp precision on that subset. The same direction holds across three training seeds (paired t-tests, $p=0.018$ for overall F₁ and $p=0.027$ for adversarial recall), though we interpret these values cautiously given the small number of seeds. Measured inference latency is 17.9× the baseline’s, driven by ∼92 additional reflection tokens per prompt. The same checkpoint, without additional fine-tuning, shows promising zero-shot transfer to a 329-example financial-harm benchmark (F₁: 0.868 → 0.929; recall: 0.767 → 0.867, zero false positives); preliminary two-seed evidence, however, suggests the SFT-only condition may match or exceed this result, so we treat the finance improvement as evidence toward generalization rather than a settled advantage of reflection specifically. Benchmarked against WildGuard, PromptGuard, and a prompted (non-fine-tuned) GPT-4o-mini reasoning classifier on the same sets, WildGuard leads on aggregate WildGuardTest F₁ (0.887), while Reflect-Guard achieves higher adversarial-subset recall than every evaluated classifier, including WildGuard (0.921 vs. 0.827) and the prompted teacher (0.636). Overall, supervised fine-tuning drives most of the aggregate gain over an un-fine-tuned classifier, while the generated safety rationale yields a narrower, latency-costly improvement specifically in adversarial-subset recall, a precision–recall tradeoff relevant to safety-critical deployments that prioritize recall over inference speed.

Short-term traffic forecasting is a critical component of intelligent transportation systems. While deep learning architectures for this task have proliferated rapidly, the sensor-level data characteristics—zero-value prevalence, distributional heterogeneity, and cross-sensor correlation structure—that drive architecture-specific failure modes remain insufficiently understood, and their implications for evidence-based model selection in real deployments have not been systematically addressed. This study addresses that question through a sensor-network diagnostic framework applied to the METR-LA dataset (Metropolitan Los Angeles; 207 inductive loop detectors, 5-min resolution). The framework integrates systematic characterization of sensor data properties, a controlled benchmark of four representative architectures—Transformer, Spatio-Temporal Graph Convolutional Network (STGCN), Diffusion Convolutional Recurrent Neural Network (DCRNN), and Gated Temporal Convolutional Network (Gated TCN)—under a unified 12→3 prediction setting, and a novel per-sensor regression analysis that quantitatively links zero-value ratios to model-specific prediction errors across all 207 sensors. Building on these findings, this study further proposes Graph-Enhanced Transformer (GETFormer), a lightweight hybrid architecture that augments the Transformer with a single-hop Graph Convolutional Network (GCN) layer and a gated residual fusion module. The diagnostic findings and condition-dependent model-selection guidelines provide an empirically grounded foundation for principled hybrid architecture development in urban traffic sensing.

Robust defect classification is critical for intelligent process inspection and quality control in steel manufacturing, but it remains challenging when industrial tabular data are small, imbalanced, statistically skewed, and characterized by nonlinear inter-feature dependencies. This study proposes a robust steel plate defect classification framework based on a feature-embedded Transformer. A quantile-based transformation is first introduced to regularize heterogeneous and heavy-tailed process descriptors. Each numerical variable is then represented as a learnable feature token and processed by a Transformer encoder to model contextual interactions among positional, geometric, luminosity-related, and morphological attributes. Experiments were conducted on the Steel Plates Faults dataset, containing 1941 samples, 27 input features, and 7 defect categories. On the held-out test set, the model achieved an accuracy of 0.735, remaining competitive with XGBoost (0.794) and Random Forest (0.783). SHAP and self-attention analyses further indicate that the model captures distributed and interaction-aware defect representations, providing an interpretable solution for robust industrial defect classification.