Tootfinder

TIEG-Youpu Solution for NeurIPS 2022 WikiKG90Mv2-LSC
Feng Nie, Zhixiu Ye, Sifa Xie, Shuang Wu, Xin Yuan, Liang Yao, Jiazhen Peng, Xu Cheng
https://arxiv.org/abs/2603.28512 https://arxiv.org/pdf/2603.28512 https://arxiv.org/html/2603.28512
arXiv:2603.28512v1 Announce Type: new
Abstract: WikiKG90Mv2 in NeurIPS 2022 is a large encyclopedic knowledge graph. Embedding knowledge graphs into continuous vector spaces is important for many practical applications, such as knowledge acquisition, question answering, and recommendation systems. Compared to existing knowledge graphs, WikiKG90Mv2 is a large scale knowledge graph, which is composed of more than 90 millions of entities. Both efficiency and accuracy should be considered when building graph embedding models for knowledge graph at scale. To this end, we follow the retrieve then re-rank pipeline, and make novel modifications in both retrieval and re-ranking stage. Specifically, we propose a priority infilling retrieval model to obtain candidates that are structurally and semantically similar. Then we propose an ensemble based re-ranking model with neighbor enhanced representations to produce final link prediction results among retrieved candidates. Experimental results show that our proposed method outperforms existing baseline methods and improves MRR of validation set from 0.2342 to 0.2839.
toXiv_bot_toot

Polymarket partners with Chainalysis to deploy detection models to "surface patterns consistent with insider knowledge in prediction markets" and other tools (Bloomberg)
https://www.bloomberg.com/news/articles/2026-0…

Seven Social Sins
Wealth without work.
Pleasure without conscience.
Knowledge without character.
Commerce without morality.
Science without humanity.
Worship without sacrifice.
Politics without principle.
— Frederick Lewis Donaldson
https://en.wikipedia.org/wiki/Seven_So

We’re kicking off our workshop on Structure and Interpretation with a keynote by Manfred Thaller: “Extracting and Communicating Historical Knowledge via ‘Graphs.’ Pipedreams of a Disbeliever in Hermeneutics.”
#ComputationalHumanities #DigitalHumanities

We’re kicking off our workshop on Structure and Interpretation with a keynote by Manfred Thaller: “Extracting and Communicating Historical Knowledge via ‘Graphs.’ Pipedreams of a Disbeliever in Hermeneutics.”
#ComputationalHumanities #DigitalHumanities

"The Commodification of Sensitive Open Data" @ Katina Magazine
https://katinamagazine.org/content/article/open-knowledge/2026/the-commodification-of-sensitive-open-data
"Governments enable corporations to…

heise | Persönliches Wissensmanagement: Die besten Tools und Techniken für Einsteiger
Personal Knowledge Management hilft, Notizen und persönliches Wissen besser zu sammeln, zu ordnen und zu nutzen. Wir erklären das Konzept und empfehlen Tools.

RE: https://mastodon.social/@404mediaco/116307878290848654
This is an incredibly good decision.
Wikipedia is an incredible authority. It needs to stay that way. that means that the way it produces knowledge need to not be entangled with the LLMs that use that knowledge.

Hey cool, flowers to myself: Starting this week, I will be Acting Professor at Ruhr-University #Bochum holding the chair of Anthropology of Knowledge.
This will be for the summer term and lots of fun, esp. in teaching controversy mapping, reading extraction, and discussing post-socialist economies.

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