Recommender systems exemplify sequential decision-making under uncertainty, strategically deciding what content to serve to users, to optimise a range of potential objectives. To balance the explore-exploit trade-off successfully, Thompson sampling provides a natural and widespread paradigm to probabilistically select which action to take. Questions of causal and counterfactual inference, which underpin use-cases like offline evaluation, are not straightforward to answer in these contexts. Specifically, whilst most existing estimators rely on action propensities, these are not readily available under Thompson sampling procedures. We derive exact and efficiently computable expressions for action propensities under a variety of parameter and outcome distributions, enabling the use of off-policy estimators in Thompson sampling scenarios. This opens up a range of practical use-cases where counterfactual inference is crucial, including unbiased offline evaluation of recommender systems, as well as general applications of causal inference in online advertising, personalisation, and beyond.

In production recommender systems, feature preprocessing must be faithfully replicated across training and inference environments. This often requires duplicating logic between offline and online environments, increasing engineering effort and introducing risks of dataset shift. We present Kamae, an open-source Python library that bridges this gap by translating PySpark preprocessing pipelines into equivalent Keras models. Kamae provides a suite of configurable Spark transformers and estimators, each mapped to a corresponding Keras layer, enabling consistent, end-to-end preprocessing across the ML lifecycle. Framework's utility is illustrated on real-world use cases, including MovieLens dataset and Expedia's Learning-to-Rank pipelines. The code is available at https://github.com/ExpediaGroup/kamae.

Amazon Prime Day is now four days. The Prime Day deals started dropping last month, reached a fever pitch today, and will go on through Friday. We'll be dangerously caffeinated and working in shifts covering 20 hours a day through the end. The WIRED Reviews team only recommends deals on products we've actually tested and approved, and which are actually discounted. If you're looking for up-to-the-minute coverage of deals, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. Deals on computers, routers, monitors, tablets, keyboards, and more. The Google Pixel Tablet (7/10, WIRED Recommends) is a good Android tablet. Where it really shines, though, is its ability to be paired with the charging speaker dock to transform into a smart speaker when you aren't using it as a tablet. Right now, only the tablet version is on sale, and it's a good price if you want to buy it for the sharp screen and overall solid performance. Enjoy simple, set-and-forget Wi-Fi courtesy of Amazon's Eero mesh systems. The tri-band Eero Pro 6E (7/10, WIRED Recommends) adds 6 GHz to the familiar 2.4-GHz and 5-GHz bands, for fast and dependable Wi-Fi. The Eero Plus subscription is expensive ( 10 per month or 100 per year) but includes comprehensive parental controls, advanced security, ad blocking, and even a password manager and VPN service. As the budget pick in our best mesh Wi-Fi systems guide, the Deco X20 is already a bargain. This Wi-Fi 6 dual-band mesh (2.4-GHz and 5-GHz) is easy to set up and delivered solid results in my tests. It's not the speediest mesh, but if your internet connection is 500 Mbps or less, it's likely enough.

Amazon Prime Day is now almost a week. Prime Day started today and will go on for three more days. We'll be dangerously caffeinated and working shifts 20 hours a day from now through Friday, July 11. The WIRED Reviews team has been prepping for weeks to bring you real savings on the very best tech, and we only recommend products we've actually tested and approved. If you're looking for up-to-the-minute coverage of check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. Deals on computers, routers, monitors, tablets, keyboards, and more. The Google Pixel Tablet (7/10, WIRED Recommends) is a good Android tablet. Where it really shines, though, is its ability to be paired with the charging speaker dock to transform into a smart speaker when you aren't using it as a tablet. Right now, only the tablet version is on sale, and it's a good price if you want to buy it for the sharp screen and overall solid performance. Enjoy simple, set-and-forget Wi-Fi courtesy of Amazon's Eero mesh systems. The tri-band Eero Pro 6E (7/10, WIRED Recommends) adds 6 GHz to the familiar 2.4-GHz and 5-GHz bands, for fast and dependable Wi-Fi. The Eero Plus subscription is expensive ( 10 per month or 100 per year) but includes comprehensive parental controls, advanced security, ad blocking, and even a password manager and VPN service. As the budget pick in our best mesh Wi-Fi systems guide, the Deco X20 is already a bargain. This Wi-Fi 6 dual-band mesh (2.4-GHz and 5-GHz) is easy to set up and delivered solid results in my tests. It's not the speediest mesh, but if your internet connection is 500 Mbps or less, it's likely enough. Each router has two gigabit Ethernet ports, and the vaselike design blends in easily on shelves or tables. This tri-band Wi-Fi 6E mesh system from TP-Link scores a place in our best mesh Wi-Fi systems guide. Easy to set up and configure through the mobile app, each unit has one 2.5 Gbps Ethernet port and two gigabit ports. It offers fast speeds at close range on the 6-GHz band, but was also fast on 5 GHz, and offered a decent range on 2.4 GHz. There are optional subscriptions for parental controls and enhanced security. Cheap laptops don't have to be terrible, and the HP Chromebook Plus x360 proves it. While there are more premium Chromebooks out there, none sell for so little on discount. It has a 14-inch 1080p screen, and unlike some Chromebooks at this price, it also comes with enough RAM and storage.

The sale event of the summer is here, and the Amazon Prime Day Kindle deals (and other Amazon device deals!) are ones you can count on being great to shop. As someone who tests Amazon gear for a living--Echo speakers, Kindles, Amazon's smart plugs, you name it--I'm always tracking what in Amazon's lineup is worth buying. I have a ton of favorites, from the best of the best, like the Kindle Paperwhite and Echo Show 8, to the Kindle Scribe and Echo Spot. It's the perfect time to shop all of those and more. Not only is everything in this guide WIRED-tested and WIRED-approved, but it's on sale right now. Try our Absolute Best Amazon Prime Day Deals roundup and Prime Day liveblog.

On TikTok, Gyasi Alexander likes to hold "yap sessions" about all sorts of vulnerable topics--self-image issues, anxiety, why you shouldn't romanticize forgiveness. He started posting videos like that last summer, following the end of an 11-year relationship, after a group of friends encouraged him to use the platform as an outlet to talk about his healing process. Lately, though, the 28-year-old retail sales worker who lives in Providence, Rhode Island, has decided to fully embrace, and talk about, his most vulnerable trait--being a yearner. "Yearning is a little bit different from love in that it's more intense," he says. It feels like you're constantly reaching for more.

Amazon Prime Day is here, and the deals are dropping like the bass at a Skrillex show. This year, Amazon has expanded the event to four days, with most of the best Prime Day deals launching in the early hours of Tuesday morning and sitting on the metaphorical shelf through 11:59 pm PT on Friday, July 11. There are tens of thousands of products on sale this week, but comparatively few deserve your time and money. The WIRED Reviews team spends weeks prepping for Prime Day and will be working in shifts for 20 hours a day throughout the event to keep our coverage updated--all so you can score real savings on products we've tested and approved. If you're looking for up-to-the-minute coverage of lightning deals, this year's trending products, and fast sellers, along with what will surely be increasingly unhinged commentary, check out our Amazon Prime Day liveblog, which will run from 5 am to midnight daily. How Does WIRED Spot Deals? We start searching for the best Prime Day deals weeks ...

Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We present an integrated decision support system that combines interactive visualizations with a conversational agent to explain diabetes risk assessments. We propose a hybrid prompt handling approach combining fine-tuned language models for analytical queries with general Large Language Models (LLMs) for broader medical questions, a methodology for grounding AI explanations in scientific evidence, and a feature range analysis technique to support deeper understanding of feature contributions. We conducted a mixed-methods study with 30 healthcare professionals and found that the conversational interactions helped healthcare professionals build a clear understanding of model assessments, while the integration of scientific evidence calibrated trust in the system's decisions. Most participants reported that the system supported both patient risk evaluation and recommendation.

Cooking plays a vital role in everyday independence and well-being, yet remains challenging for people with vision impairments due to limited support for tracking progress and receiving contextual feedback. Object status - the condition or transformation of ingredients and tools - offers a promising but underexplored foundation for context-aware cooking support. In this paper, we present OSCAR (Object Status Context Awareness for Recipes), a technical pipeline that explores the use of object status recognition to enable recipe progress tracking in non-visual cooking. OSCAR integrates recipe parsing, object status extraction, visual alignment with cooking steps, and time-causal modeling to support real-time step tracking. We evaluate OSCAR on 173 instructional videos and a real-world dataset of 12 non-visual cooking sessions recorded by BLV individuals in their homes. Our results show that object status consistently improves step prediction accuracy across vision-language models, and reveal key factors that impact performance in real-world conditions, such as implicit tasks, camera placement, and lighting. We contribute the pipeline of context-aware recipe progress tracking, an annotated real-world non-visual cooking dataset, and design insights to guide future context-aware assistive cooking systems.

Cross-domain recommendation (CDR) aims to address the persistent cold-start problem in Recommender Systems. Current CDR research concentrates on transferring cold-start users' information from the auxiliary domain to the target domain. However, these systems face two main issues: the underutilization of multimodal data, which hinders effective cross-domain alignment, and the neglect of side users who interact solely within the target domain, leading to inadequate learning of the target domain's vector space distribution. To address these issues, we propose a model leveraging Multimodal data and Side users for diffusion Cross-domain recommendation (MuSiC). We first employ a multimodal large language model to extract item multimodal features and leverage a large language model to uncover user features using prompt learning without fine-tuning. Secondly, we propose the cross-domain diffusion module to learn the generation of feature vectors in the target domain. This approach involves learning feature distribution from side users and understanding the patterns in cross-domain transformation through overlapping users. Subsequently, the trained diffusion module is used to generate feature vectors for cold-start users in the target domain, enabling the completion of cross-domain recommendation tasks. Finally, our experimental evaluation of the Amazon dataset confirms that MuSiC achieves state-of-the-art performance, significantly outperforming all selected baselines. Our code is available: https://anonymous.4open.science/r/MuSiC-310A/.