As large language models increasingly rely on external data sources, compensating data contributors has become a central concern. But how should these payments be devised? We revisit data valuations from a $\textit{market-design perspective}$ where payments serve to compensate data owners for the $\textit{private}$ heterogeneous costs they incur for collecting and sharing data. We show that popular valuation methods-such as Leave-One-Out and Data Shapley-make for poor payments. They fail to ensure truthful reporting of the costs, leading to $\textit{inefficient market}$ outcomes. To address this, we adapt well-established payment rules from mechanism design, namely Myerson and Vickrey-Clarke-Groves (VCG), to the data market setting. We show that Myerson payment is the minimal truthful mechanism, optimal from the buyer's perspective. Additionally, we identify a condition under which both data buyers and sellers are utility-satisfied, and the market achieves efficiency. Our findings highlight the importance of incorporating incentive compatibility into data valuation design, paving the way for more robust and efficient data markets. Our data market framework is readily applicable to real-world scenarios. We illustrate this with simulations of contributor compensation in an LLM based retrieval-augmented generation (RAG) marketplace tasked with challenging medical question answering.

Modern operational landscapes, spanning domains such as retail, healthcare, finance, and software systems, are increasingly characterized by complex interdependencies and massive data streams. In such settings, anomalies rarely arise from a single isolated factor; rather, they emerge as the cumulative effect of multi-hop causal chains. Existing RCA methods typically focus on detecting outliers or isolating single nodes based on correlation or localized attribution. However, these approaches do not provide a complete explanation of why a failure occurred. In other words they do not systematically trace all possible causal pathways from an observed effect back to its initial triggers. The primary motivation for our work is to address this limitation by developing a package that systematically reconstructs the full causal pathway from an observed anomaly back to its root cause. By leveraging the strengths of the DoWhy causal inference library, our method extends existing techniques to not only identify individual anomalous nodes but also trace entire multi-hop causal chains. This end-to-end approach enables practitioners to intervene precisely at the earliest disruption points, thereby reducing the risk of recurring failures and improving overall system reliability.

Two years ago, the long and lucrative relationship between Electronic Arts and Fifa broke down, with EA taking its ball home and launching EA Sports FC, a new brand for its footie sim series. Fifa president Gianni Infantino made a sulky declaration that he would find a new developer and that, "the only authentic, real game that has the Fifa name will be the best one available for gamers and football fans". This seemed like a ludicrous boast: EA had 20 years of experience making mainstream football sims – an expensive and highly sophisticated endeavour. How could Fifa hope to find a studio capable of competing? Well, it looks as if the global football body may have found its new best friend.

Anytime heuristic search algorithms try to find a (potentially suboptimal) solution as quickly as possible and then work to find better and better solutions until an optimal solution is obtained or time is exhausted. The most widely-known anytime search algorithms are based on best-first search. In this paper, we propose a new algorithm, rectangle search, that is instead based on beam search, a variant of breadth-first search. It repeatedly explores alternatives at all depth levels and is thus best-suited to problems featuring deep local minima. Experiments using a variety of popular search benchmarks suggest that rectangle search is competitive with fixed-width beam search and often performs better than the previous best anytime search algorithms.

Offloading computation to nearby edge/fog computing nodes, including the ones carried by moving vehicles, e.g., vehicular fog nodes (VFN), has proved to be a promising approach for enabling low-latency and compute-intensive mobility applications, such as cooperative and autonomous driving. This work considers vehicular fog computing scenarios where the clients of computation offloading services try to minimize their own costs while deciding which VFNs to offload their tasks. We focus on decentralized multi-agent decision-making in a repeated unknown game where each agent, e.g., service client, can observe only its own action and realized cost. In other words, each agent is unaware of the game composition or even the existence of opponents. We apply a completely uncoupled learning rule to generalize the decentralized decision-making algorithm presented in \cite{Cho2021} for the multi-agent case. The multi-agent solution proposed in this work can capture the unknown offloading cost variations susceptive to resource congestion under an adversarial framework where each agent may take implicit cost estimation and suitable resource choice adapting to the dynamics associated with volatile supply and demand. According to the evaluation via simulation, this work reveals that such individual perturbations for robustness to uncertainty and adaptation to dynamicity ensure a certain level of optimality in terms of social welfare, e.g., converging the actual sequence of play with unknown and asymmetric attributes and lowering the correspondent cost in social welfare due to the self-interested behaviors of agents.

The unordered tree edit distance is a natural metric to compute distances between trees without intrinsic child order, such as representations of chemical molecules. While the unordered tree edit distance is MAX SNP-hard in principle, it is feasible for small cases, e.g. via an A* algorithm. Unfortunately, current heuristics for the A* algorithm assume unit costs for deletions, insertions, and replacements, which limits our ability to inject domain knowledge. In this paper, we present three novel heuristics for the A* algorithm that work with custom cost functions. In experiments on two chemical data sets, we show that custom costs make the A* computation faster and improve the error of a 5-nearest neighbor regressor, predicting chemical properties. We also show that, on these data, polynomial edit distances can achieve similar results as the unordered tree edit distance.

If your accounts payable (AP) team is stuck dealing with duplicate invoices, overpayments, and mistakes, it may be time to reconsider your manual invoice data capture system. AP specialists tediously type in each invoice and match the data line-for-line from the physical copy into their systems. This isn't just time-consuming, but it can also produce some of the following drawbacks: The latest addition to the SmartCapture feature-set is a tool called Line Item Capture, which further simplifies invoice data entry by extracting descriptions, unit costs, and quantities in minutes with 99% accuracy, and removing up to 83% of data entry from AP. With the launch of SmartCapture earlier this year, Beanworks customers were able to save even more time, while helping to eliminate errors and mitigate the risk of fraud in accounting. SmartCapture automatically picks up the header information from invoices, simplifying the day-to-day challenges in data entry.

Robotics-as-a-service (RaaS) is about to eat the world of work. While much of the attention in the world of automation technology has been focused on self-driving cars, many other markets traditionally dominated by human-in-the-loop solutions are reaching a point of inflection, enabling RaaS solutions to take over. Robotics companies historically have sold their customers -- you guessed it -- robots. In the enterprise, robots have often been leveraged to streamline manufacturing. Giant companies with ominous, global, megacorp-sounding names like FANUC and ABB provide solutions that require hundreds of thousands, if not millions, of investment dollars just to get started.

Ed Baig gives a look at the new Apple Watch Series 4. One key new feature: fall detection. The changes in the consumer marketplace this year have been largely driven by new tech products. Our world has been shaped in large part by just a handful of revolutionary consumer products and the companies behind them. Such milestones include the first modern automobile, first sold by Mercedes in 1901, and the first smartphone, introduced to the market by IBM in 1994. While the impact new products have on the world rarely rises to the significance of the first personal automobile, each year brings a new lineup of consumer products, some of them the first of their kind, to the market – and 2018 is no exception.

The Chart of the Week is a weekly Visual Capitalist feature on Fridays. Industrial robots have come a long way since George Devol invented "Unimate" in 1961. After pitching his idea to Joseph Engelberger at a cocktail party, the two soon saw their new creation become the first mass-produced robotic arm to be used in factory automation. Today, this robot class is raising the bar of global manufacturing to new heights, striking a seamless mix of strength, speed, and precision. As a result, demand for industrial robots keeps growing at a robust 14% per year, setting the stage for 3.1 million industrial robots in operation globally by 2020.