Tootfinder

"everything is brittle and at the mercy of anyone angry enough to poke it"
As a magnet, sticker, mug or more.
Get yours: https://davidaugust.threadless.com/designs/warehouse-fire/accessories/sticker
h/t @…

A working paper uses an LLM to analyze political discourse on X, finding that anger is the dominant emotion expressed by US users, especially those over 65 (Tim Harford/Financial Times)
https://www.ft.com/content/914d0e31-231c-4663-9b39-c81d80187aef

Answering the dilemma of cycle lane versus shared space planning through an agent-based simulation experiment and accessibility equity analysis
https://link.springer.com/article/10.1007/s44327-026-00200-8

Answering the dilemma of cycle lane versus shared space planning through an agent-based simulation experiment and accessibility equity analysis - Discover Cities
This paper explores a vital dilemma about the future of urban road infrastructure: whether to dedicate space for each sustainable transport mode, such as m

People that "want a phone call" instead of just answering a simple question in email.
➡️ Don't want a paper trail
➡️ Are unable to put their thoughts into written words
➡️ Don't know how or are too lazy to type
#thismeetingcouldhavebeenanemail

“How many people does it take to screw in a lightbulb?
The answer – in SAPN’s case study – is an electrician, a plumber and software techs, who now all need to work together to ensure the home management system can control the proverbial lights.”
https://

📢 Online-Veranstaltung: „Wissenschaft zwischen Wahrheit und Fake – Wenn der Publikationswahn die Demokratie angreift"
🗓 Di, 12.05.2026, 17–19 Uhr per BBB
💻 https://talk.hshl.de/b/for-leg-xnu-btx
Paper Mills, KI-Fälschungen, „Publish or Perish": Wie schützen wir die Integrität…

GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum
Shuwen Xu, Yao Xu, Jiaxiang Liu, Chenhao Yuan, Wenshuo Peng, Jun Zhao, Kang Liu
https://arxiv.org/abs/2603.28533 https://arxiv.org/pdf/2603.28533 https://arxiv.org/html/2603.28533
arXiv:2603.28533v1 Announce Type: new
Abstract: Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reasoning generalization. Specifically, existing approaches often restrict agent exploration: prompting-based methods lack autonomous navigation training, while current training pipelines usually confine reasoning to predefined trajectories. To this end, this paper proposes \textit{GraphWalker}, a novel agentic KGQA framework that addresses these challenges through \textit{Automated Trajectory Synthesis} and \textit{Stage-wise Fine-tuning}. GraphWalker adopts a two-stage SFT training paradigm: First, the agent is trained on structurally diverse trajectories synthesized from constrained random-walk paths, establishing a broad exploration prior over the KG; Second, the agent is further fine-tuned on a small set of expert trajectories to develop reflection and error recovery capabilities. Extensive experiments demonstrate that our stage-wise SFT paradigm unlocks a higher performance ceiling for a lightweight reinforcement learning (RL) stage, enabling GraphWalker to achieve state-of-the-art performance on CWQ and WebQSP. Additional results on GrailQA and our constructed GraphWalkerBench confirm that GraphWalker enhances generalization to out-of-distribution reasoning paths. The code is publicly available at https://github.com/XuShuwenn/GraphWalker
toXiv_bot_toot

My response: The paper, all experimental items, the entire experiment code AND the analysis code and raw results are all publicly available online. But I can only answer concrete, specific questions.