Human reliability remains a critical concern in safety-critical domains such as nuclear power, where operational failures are often linked to human error. While conventional human reliability analysis (HRA) methods have been widely adopted, they rely heavily on expert judgment for identifying human failure events (HFEs) and assigning performance influencing factors (PIFs). This reliance introduces challenges related to reproducibility, subjectivity, and limited integration of interface-level data. In particular, current approaches lack the capacity to rigorously assess how human-machine interface design contributes to operator performance variability and error susceptibility. To address these limitations, this study proposes a framework for risk-informed human failure event identification and interface-induced risk assessment driven by AutoGraph (InSight-R). By linking empirical behavioral data to the interface-embedded knowledge graph (IE-KG) constructed by the automated graph-based execution framework (Auto-Graph), the InSight-R framework enables automated HFE identification based on both error-prone and time-deviated operational paths. Furthermore, we discuss the relationship between designer-user conflicts and human error. This framework offers actionable insights for interface design optimization and contributes to the advancement of mechanism-driven HRA methodologies. Keywords: Knowledge-Graph-Driven, Automated, Interface-Induced Risk, Human Error Identification 1 Introduction Human error remains a leading contributor to failures in complex socio-technical systems such as nuclear power plants, aviation, and healthcare, where safety-critical operations depend on accurate and timely human decisions [1, 2]. Human reliability analysis (HRA) methods have been widely used to model operator behavior and assess the likelihood of human failure events (HFEs) [3]. However, prevailing HRA approaches are often constrained by their reliance on expert judgment, particularly in the identification of HFEs and the assignment of performance influencing factors (PIFs) [3, 4]. In traditional HRA frameworks such as the integrated human event analysis system for event and condition assessment (IDHEAS-ECA), HFEs are primarily determined through expert elicitation, a process that, while practical, suffers from limited reproducibility, insufficient transparency, and weak theoretical grounding [5].

More than 100 people have been killed in air crashes this year already, including in a midair collision between a commercial airliner and a helicopter near Washington, DC, and a plane crashing into a bus on a Sao Paulo street. The fatal incidents in the first two months of the new year came after last year was declared one of the deadliest in aviation history with at least 318 deaths in 11 civilian airplane crashes, including two incidents in the last week of December. While fatal air crashes are rare, they attract extraordinary attention, often reinstilling the fear of flying. At least 25 million adults in the United States alone have a fear of flying, according to the Cleveland Clinic. The fear is often exacerbated not just by the crashes but also incidents like emergency landings, a door blowing off a plane and aircraft skidding off runways.

This article examines the characteristics of human errors in processing transportation requests. The role of artificial intelligence (AI) in maritime transportation is explored. The main methods and technologies used for automating and optimizing the handling of transportation requests are analyzed, along with their impact on reducing the number of errors. Examples of successful AI implementation in large companies are provided, confirming the positive influence of these technologies on overall operational efficiency and customer service levels. Introduction Maritime transport plays a crucial role in global trade, facilitating the movement of goods between continents and contributing to economic growth and international integration.

Effective labeled data collection plays a critical role in developing and fine-tuning robust streaming analytics systems. However, continuously labeling documents to filter relevant information poses significant challenges like limited labeling budget or lack of high-quality labels. There is a need for efficient human-in-the-loop machine learning (HITL-ML) design to improve streaming analytics systems. One particular HITL- ML approach is online active learning, which involves iteratively selecting a small set of the most informative documents for labeling to enhance the ML model performance. The performance of such algorithms can get affected due to human errors in labeling. To address these challenges, we propose ORIS, a method to perform Online active learning using Reinforcement learning-based Inclusive Sampling of documents for labeling. ORIS aims to create a novel Deep Q-Network-based strategy to sample incoming documents that minimize human errors in labeling and enhance the ML model performance. We evaluate the ORIS method on emotion recognition tasks, and it outperforms traditional baselines in terms of both human labeling performance and the ML model performance.

Manual data annotation is an important NLP task but one that takes considerable amount of resources and effort. In spite of the costs, labeling and categorizing entities is essential for NLP tasks such as semantic evaluation. Even though annotation can be done by non-experts in most cases, due to the fact that this requires human labor, the process is costly. Another major challenge encountered in data annotation is maintaining the annotation consistency. Annotation efforts are typically carried out by teams of multiple annotators. The annotations need to maintain the consistency in relation to both the domain truth and annotation format while reducing human errors. Annotating a specialized domain that deviates significantly from the general domain, such as fantasy literature, will see a lot of human error and annotator disagreement. So it is vital that proper guidelines and error reduction mechanisms are enforced. One such way to enforce these constraints is using a specialized application. Such an app can ensure that the notations are consistent, and the labels can be pre-defined or restricted reducing the room for errors. In this paper, we present SHADE, an annotation software that can be used to annotate entities in the high fantasy literature domain. Specifically in Dungeons and Dragons lore extracted from the Forgotten Realms Fandom Wiki.

The UK government's decision to let technology companies self-regulate gambling-style loot boxes in video games has been called into question, after some of the developers put in charge of new industry guidelines broke their own rules. In the past six months, the advertising regulator has upheld complaints against three companies involved in drawing up industry rules, including the leading developer Electronic Arts (EA), for failing to disclose that their games contained loot boxes. An expert who submitted the complaints said he had found hundreds more examples of breaches but had only taken a handful to the Advertising Standards Authority (ASA) in order to highlight the problem. Loot boxes are in-game features that allow players to pay, with real money or virtual currency, to open a digital envelope containing random prizes, such as an outfit or a weapon for a character. Despite warnings from experts that loot boxes carry similar risks to gambling, the then Department for Digital, Culture, Media and Sport said in July 2022 it would not follow other countries, such as Belgium, in choosing to regulate them as gambling products.

Artificial intelligence could provide the'ultimate second opinion' as it is just as good as doctors at analysing X-rays, scientists have claimed. Tests using AI software on millions of old scans diagnosed conditions at least as accurately as radiologists 94 per cent of the time. The joint study by Warwick University and King's College London suggested it could prove vital in avoiding human error when checking patients' results. The AI software, which can scan X-rays as soon as they are taken, is able to understand the seriousness of each condition and flag the more urgent ones immediately. The study's authors suggested it could be used to screen X-rays, freeing up time for busy doctors to focus on more critical patients and helping deal with chronic NHS staffing shortages.

The Assured and Trustworthy Human-centered AI (ATHAI) symposium was held as part of the AAAI Fall Symposium Series in Arlington, VA from October 25-27, 2023. The symposium brought together three groups of stakeholders from industry, academia, and government to discuss issues related to AI assurance in different domains ranging from healthcare to defense. The symposium drew over 50 participants and consisted of a combination of invited keynote speakers, spotlight talks, and interactive panel discussions. On Day 1, the symposium kicked off with a keynote by Professor Missy Cummings (George Mason University) titled "Developing Trustworthy AI: Lessons Learned from Self-driving Cars". Missy shared important lessons learned from her time at the National Highway Traffic Safety Administration (NHTSA) and interacting with the autonomous vehicle industry.

Digital technologies have dramatically accelerated the digital transformation in process industries, boosted new industrial applications, upgraded the production system, and enhanced operational efficiency. In contrast, the challenges and gaps between human and artificial intelligence (AI) have become more and more prominent, whereas the digital divide in process safety is aggregating. The study attempts to address the following questions: (i)What is AI in the process safety context? (ii)What is the difference between AI and humans in process safety? (iii)How do AI and humans collaborate in process safety? (iv)What are the challenges and gaps in human-AI collaboration? (v)How to quantify the risk of human-AI collaboration in process safety? Qualitative risk analysis based on brainstorming and literature review, and quantitative risk analysis based on layer of protection analysis (LOPA) and Bayesian network (BN), were applied to explore and model. The importance of human reliability should be stressed in the digital age, not usually to increase the reliability of AI, and human-centered AI design in process safety needs to be propagated.

The collaboration between humans and artificial intelligence (AI) is a significant feature in this digital age. However, humans and AI may have observation, interpretation, and action conflicts when working synchronously. This phenomenon is often masked by faults and, unfortunately, overlooked. This paper systematically introduces the human-AI conflict concept, causes, measurement methods, and risk assessment. The results highlight that there is a potential second decision-maker besides the human, which is the AI; the human-AI conflict is a unique and emerging risk in digitalized process systems; and this is an interdisciplinary field that needs to be distinguished from traditional fault and failure analysis; the conflict risk is significant and cannot be ignored. Keywords: human-AI conflict, risk, digitization, automation. 1. Introduction Automation, digitization, and artificial intelligence (AI) have become the trends in the development of industrial history (Pistikopoulos et al., 2021).