Tootfinder

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
Brandon Jaipersaud, David Krueger, Ekdeep Singh Lubana
https://arxiv.org/abs/2508.05625

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzing model representations, to study various LLM skills such as the ability to model user sentiment and political perspective. Motivated by this, we apply probes to study persuasion dynamics in natural, multi-turn conversations. We leverage insights from cognitive science to train …

Graffiti: Enabling an Ecosystem of Personalized and Interoperable Social Applications
Theia Henderson, David R. Karger, David D. Clark
https://arxiv.org/abs/2508.04889 https://

Graffiti: Enabling an Ecosystem of Personalized and Interoperable Social Applications
Most social applications, from Twitter to Wikipedia, have rigid one-size-fits-all designs, but building new social applications is both technically challenging and results in applications that are siloed away from existing communities. We present Graffiti, a system that can be used to build a wide variety of personalized social applications with relative ease that also interoperate with each other. People can freely move between a plurality of designs -- each with its own aesthetic, feature set…

The LCLStream Ecosystem for Multi-Institutional Dataset Exploration
David Rogers, Valerio Mariani, Cong Wang, Ryan Coffee, Wilko Kroeger, Murali Shankar, Hans Thorsten Schwander, Tom Beck, Fr\'ed\'eric Poitevin, Jana Thayer
https://arxiv.org/abs/2510.04012

The LCLStream Ecosystem for Multi-Institutional Dataset Exploration
We describe a new end-to-end experimental data streaming framework designed from the ground up to support new types of applications -- AI training, extremely high-rate X-ray time-of-flight analysis, crystal structure determination with distributed processing, and custom data science applications and visualizers yet to be created. Throughout, we use design choices merging cloud microservices with traditional HPC batch execution models for security and flexibility. This project makes a unique con…

Tell Kroger: End Habitat Loss in Your Supply Chain https://www.worldanimalprotection.us/take-action/tell-kroger-end-habitat-loss-in-your-supply-chain/

Tell Kroger: End Habitat Loss in Your Supply Chain
Send a letter to Kroger executives urging them to expand the deforestation-free policy to all of its animal products.

CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning
Lauren Deason, Adam Bali, Ciprian Bejean, Diana Bolocan, James Crnkovich, Ioana Croitoru, Krishna Durai, Chase Midler, Calin Miron, David Molnar, Brad Moon, Bruno Ostarcevic, Alberto Peltea, Matt Rosenberg, Catalin Sandu, Arthur Saputkin, Sagar Shah, Daniel Stan, Ernest Szocs, Shengye Wan, Spencer Whitman, Sven Krasser, Joshua Saxe

CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning
Today's cyber defenders are overwhelmed by a deluge of security alerts, threat intelligence signals, and shifting business context, creating an urgent need for AI systems to enhance operational security work. While Large Language Models (LLMs) have the potential to automate and scale Security Operations Center (SOC) operations, existing evaluations do not fully assess the scenarios most relevant to real-world defenders. This lack of informed evaluation impacts both AI developers and those apply…

Language models' activations linearly encode training-order recency
Dmitrii Krasheninnikov, Richard E. Turner, David Krueger
https://arxiv.org/abs/2509.14223 https://…

Language models' activations linearly encode training-order recency
We show that language models' activations linearly encode when information was learned during training. Our setup involves creating a model with a known training order by sequentially fine-tuning Llama-3.2-1B on six disjoint but otherwise similar datasets about named entities. We find that the average activations of test samples for the six training datasets encode the training order: when projected into a 2D subspace, these centroids are arranged exactly in the order of training and lie on a s…

Low-energy spin waves as potential driving force for superconductivity in electron-doped cuprates
Kristine M. L. Krighaar, Jeppe J. Cederholm, Ellen M. S. Schriver, Henrik Jacobsen, Christine P. Lauritzen, Igor Zaliznyak, C\'edric H. Qvistgaard, Ursula B. Hansen, Ahmed Alshemi, Anton P. J. Stampfl, Jean-Claude Grivel, Dongjoon Song, Kim Lefmann, Machteld E. Kamminga

Low-energy spin waves as potential driving force for superconductivity in electron-doped cuprates
In order to fully utilize the technological potential of unconventional superconductors, an enhanced understanding of the superconducting mechanism is necessary. In the best performing superconductors, the cuprates, superconductivity is intimately linked with magnetism, although the details of this remain elusive. In search of clarity in the magnetism-superconductivity relationship, we focus on the electron-doped cuprate Nd1.85Ce0.15CuO(4-delta) (NCCO). NCCO has an antiferromagnetic ground stat…

Is the optimal magnetic rectangle a square?
David Krejcirik
https://arxiv.org/abs/2508.16152 https://arxiv.org/pdf/2508.16152

Is the optimal magnetic rectangle a square?
We are concerned with the dependence of the lowest eigenvalue of the magnetic Dirichlet Laplacian on the geometry of rectangles, subject to homogeneous fields. We conjecture that the square is a global minimiser both under the area or perimeter constraints. Contrary to the well-known magnetic-free analogue, the present spectral problem does not admit explicit solutions. By establishing lower and upper bound to the eigenvalue, we establish the conjecture for weak magnetic fields. Moreover, we re…

Block Designs that Provide Optimal Power in the Cochran-Mantel-Haenszel Test
David Azriel, Adam Kapelner, Abba M. Krieger
https://arxiv.org/abs/2507.08125 …

Block Designs that Provide Optimal Power in the Cochran-Mantel-Haenszel Test
We consider the asymptotic power performance under local alternatives of the Cochran-Mantel-Haenszel test. Our setting is non-traditional: we investigate randomized experiments that assign subjects via Fisher's blocking design. We show that blocking designs that satisfy a certain balance condition are asymptotically optimal. When the potential outcomes can be ordered, the balance condition is met for all blocking designs with number of blocks going to infinity. More generally, we prove that the…

Measuring the Magnetic Field of a Coronal Mass Ejection from Low to Middle Corona
Xingyao Chen, Bin Chen, Sijie Yu, Surajit Mondal, Muriel Zo\"e Stiefel, Peijin Zhang, Dale E. Gary, S\"am Krucker, Marin M. Anderson, Judd D. Bowman, Ruby Byrne, Morgan Catha, Sherry Chhabra, Larry D'Addario, Ivey Davis, Jayce Dowell, Gregg Hallinan, Charlie Harnach, Greg Hellbourg, Jack Hickish, Rick Hobbs, David Hodge, Mark Hodges, Yuping Huang, Andrea Isella, Daniel C. Jacobs, Ghislain Ke…

Measuring the Magnetic Field of a Coronal Mass Ejection from Low to Middle Corona
A major challenge in understanding the initiation and evolution of coronal mass ejections (CMEs) is measuring the magnetic field of the magnetic flux ropes (MFRs) that drive CMEs. Recent developments in radio imaging spectroscopy have paved the way for diagnosing the CMEs' magnetic field using gyrosynchrotron radiation. We present magnetic field measurements of a CME associated with an X5-class flare by combining radio imaging spectroscopy data in microwaves (1--18 GHz) and meter-wave (20--88 M…