Tootfinder

Mastodon 4.4, now available, has a small setting that’s a big deal. See Administration/Server Settings/Discovery, “Allow external sites to see your Mastodon server as a traffic source”.
It means that every time you post a link to a site, that site is going to see as many hits as the number of instances that you have followers on, and those hits are going to be labeled as coming from Mastodon.
This is going to seriously increase Fediverse visibility. Get your instance admin to tur…

Later this year, the Trump administration will release its
5-year offshore drilling plan proposal,
which is expected to target the East Coast, West Coast, Gulf of Mexico, and Arctic Ocean for
new oil drilling.
This will launch a 60-day comment period and public hearings across the country.
Surfrider has a long and proud history of defending U.S. coasts,
including stopping the first Trump administration’s offshore drilling plans.
We are ready for t…

Congress Sells Out Our Ocean in the Largest Fossil Fuel Giveaway in U.S. History
Congress Sells off the Ocean as Part of the Big Beautiful Bill

I know that America is currently unwell and knowing it "theoretically" is one thing, having lots of colleagues and friends professionally affected is another, having our server's admin, one of the kindest, most generous people that I know, physically attacked, and their finger broken, by the LAPD, is another altogether.
https://neuromatch.soci…

I’m really glad Mastodon 4.4.0 will allow server admins to opt into sending the Referer header, and I hope admins of large instances will turn it on.
https://github.com/mastodon/mastodon/releases/tag/v4.4.0-beta.1
I also hope that third-party mobil…

Surprise (non) : "il semblerait que les Tesla sans chauffeur se comportent sur le macadam comme n’importe quel chauffard."
#Tesla
https://www.

RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
Isaac Marroqui Penalva, Enrique Tom\'as Mart\'inez Beltr\'an, Manuel Gil P\'erez, Alberto Huertas Celdr\'an
https://arxiv.org/abs/2506.19892

RepuNet: A Reputation System for Mitigating Malicious Clients in DFL
Decentralized Federated Learning (DFL) enables nodes to collaboratively train models without a central server, introducing new vulnerabilities since each node independently selects peers for model aggregation. Malicious nodes may exploit this autonomy by sending corrupted models (model poisoning), delaying model submissions (delay attack), or flooding the network with excessive messages, negatively affecting system performance. Existing solutions often depend on rigid configurations or addition…

Yeah, this is not surprising…
“Airlines and Trump Administration Backpedal on Protections for Travelers With Wheelchairs”
https://www.nytimes.com/2025/06/20/travel/wheelchair-flights-delta-united-american.html
Archive: …

Airlines Challenge Protections For Travelers With Wheelchairs
A landmark rule to expand the rights of disabled air travelers has been hamstrung by a lawsuit from major airlines and delayed enforcement by the Transportation Department.

Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
Jan Danek, Zdenek Becvar, Adam Janes
https://arxiv.org/abs/2505.22149

Real-World Modeling of Computation Offloading for Neural Networks with Early Exits and Splits
We focus on computation offloading of applications based on convolutional neural network (CNN) from moving devices, such as mobile robots or autonomous vehicles, to MultiAccess Edge Computing (MEC) servers via a mobile network. In order to reduce overall CNN inference time, we design and implement CNN with early exits and splits, allowing a flexible partial or full offloading of CNN inference. Through real-world experiments, we analyze an impact of the CNN inference offloading on the total CNN …

Prediction Gaps as Pathways to Explanation: Rethinking Educational Outcomes through Differences in Model Performance
Javier Garcia-Bernardo, Eva Jaspers, Weverthon Machado, Samuel Plach, Erik Jan van Leeuwen
https://arxiv.org/abs/2506.22993

Prediction Gaps as Pathways to Explanation: Rethinking Educational Outcomes through Differences in Model Performance
Social contexts -- such as families, schools, and neighborhoods -- shape life outcomes. The key question is not simply whether they matter, but rather for whom and under what conditions. Here, we argue that prediction gaps -- differences in predictive performance between statistical models of varying complexity -- offer a pathway for identifying surprising empirical patterns (i.e., not captured by simpler models) which highlight where theories succeed or fall short. Using population-scale admin…

Conformal Safety Shielding for Imperfect-Perception Agents
William Scarbro, Calum Imrie, Sinem Getir Yaman, Kavan Fatehi, Corina S. Pasareanu, Radu Calinescu, Ravi Mangal
https://arxiv.org/abs/2506.17275

Conformal Safety Shielding for Imperfect-Perception Agents
We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimensional observations. We propose a shield construction that provides run-time safety guarantees under perception errors by restricting the actions available to an agent, modeled as a Markov decision process, as a function of the state estimates. Our construction uses conformal prediction for the perception component, which…