arXiv:2608. 15082v1 Announce Type: new Abstract: Cold chain logistics has advanced technologically, yet most deployed systems remain reactive monitors, not decision-making agents: thresholds trigger alerts, but nothing relates violations to cumulative product degradation or converts degradation signals into logistics decisions.
arXiv:2607. 23273v1 Announce Type: cross Abstract: Computational nutrition needs precise ingredient data, but current databases are incomplete, inconsistent, and built for human reference rather than automated reasoning.
The paper audits a commercial non‑generative System‑1 model on biosecurity‑relevant benchmarks, evaluating accuracy, calibration, error detection, selective prediction, and sensitivity to answer‑option order. It finds that the model’s accuracy varies strongly by task, is reasonably well calibrated when the vendor’s uncertainty field is interpreted correctly, and that option order can cause significant prediction changes—averaging across rotations improves accuracy. The study also shows that applying averaging only to low‑confidence items recovers most of the gain at a lower cost.
The paper introduces Counterfactual Fragility Certificates (CFC), a model‑agnostic audit protocol that maps each prediction to an evidence‑failure trajectory, summarizing it with metrics such as greedy flip budget, margin‑collapse area, degradation thresholds, and fragility dominance score. CFC is shown to identify brittle high‑confidence predictions on seven tabular benchmarks with an AUROC of 0.915, outperforming existing scalar scores by up to +0.405. The method remains effective across various perturbation and review‑budget scenarios, and can also inform fragility‑aware regularization and temperature correction.
arXiv:2610.19291v1 Announce Type: new Abstract: In so-called "Industry 4.0," integrated sensors, analytics tools, and other digital technologies supplement industrial workflows, potentiating enhanced...
In so-called "Industry 4.0," integrated sensors, analytics tools, and other digital technologies supplement industrial workflows, potentiating enhanced visibility and automation. Prognostics and healt...
arXiv:2606. 09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds.
arXiv:2607. 13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed.
The paper challenges the assumption that large language models (LLMs) produce deterministic safety responses by examining how random seeds and temperature settings affect refusal decisions. Across four instruction‑tuned models and 876 harmful prompts, 18‑28% of prompts flipped between refusal and compliance depending on sampling configuration, with higher temperatures reducing decision stability. The authors introduce a Safety Stability Index (SSI) and recommend multi‑sample evaluation protocols that account for stochastic variation rather than relying on single‑shot tests.
arXiv:2606. 26185v1 Announce Type: new Abstract: LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluations where a pass/fail verdict may gate downstream deployment decisions.
The paper evaluates the green benefits of individual AI modules within a smart‑agriculture platform through two Monte Carlo simulations. In Experiment 1, AI diagnosis significantly increases the likelihood of reducing pesticide and fertilizer use compared to traditional extension services, with up to a 49 % probability of a 20 % pesticide reduction when accuracy and adoption are high. Experiment 2 shows that adding AI irrigation scheduling to IoT‑based engineering yields a 5 percentage‑point increase in median water savings and a 30.5 % reduction in paddy methane emissions, while farmer adoption remains the key limiting factor for achieving green targets.
arXiv:2607. 22067v2 Announce Type: replace-cross Abstract: Competence claims for a language model in a safety-critical domain are credible when measured against a standard the domain already enforces.
arXiv:2607. 26313v1 Announce Type: cross Abstract: Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost.