Tootfinder

Listen to in-depth investigation into the growing industry of green technologies and the environmental, social, and political consequences of the mining it requires. – Join us today, 6pm, at the German Mining Museum. Or virtually.
This, again, will be a blast 👐
Link to the event: htt…

Tuesday 21 July, Durham-Raleigh #Accessibility MeetUp (online or IRL in Millersville) will talk about the book, “Digital Accessibility Ethics: #Disability Inclusion in All Things Tech” with @…

Lainey Feingold and DRA11y Turns One - July Event, Tue, Jul 21, 2026, 6:00 PM | Meetup
Durham Raleigh A11y: The Accessibility Meetup - Triangle Style invites you to celebrate its first birthday via a virtual discussion with **Lainey Feingold** about the recen

VirtualSet: Typed Ontology Worlds as an LLM Generation Target for Grounded Queries and Guarded Decisions
Qunhui Zhang
https://arxiv.org/abs/2607.18821 https://arxiv.org/pdf/2607.18821 https://arxiv.org/html/2607.18821
arXiv:2607.18821v1 Announce Type: new
Abstract: Large language models increasingly read and act on enterprise data, but SQL gives a late error signal: hallucinated fields or relations can execute and return plausible wrong answers, while incorrect writes cannot be safely assessed after execution. We present VirtualSet, a live, receiver-typed ontology-world interface and generation target for LLMs. Instead of SQL, the model emits set expressions over entity-edge worlds. Generic Constraint Projection (GCP) checks expressions before execution, while future this preserves concrete receiver types through collection chains, turning invalid fields, edges, receivers, and actions into token-anchored type errors. Type-clean reads use a SQL fast path or bounded stream interpretation, with a parity oracle checking both paths over the exercised operator space. The same substrate supports guarded decisions: actions run first in a simulated world, and world-change events require external approval before actualization. On BIRD, we lift relational schemas into typed worlds and compare VirtualSet with direct SQL while holding the model, evidence, values, zero-shot setting, timeout, glossary, repair/voting, and grader constant where possible. On a frozen 1,072-question split, VirtualSet achieves 67.5% accuracy versus 63.5% for glossary-matched direct SQL with repair and voting ( 4.0 points; McNemar exact p = 0.00117) using deepseek-reasoner. Full-corpus analysis finds no engine mis-computation of a type-clean expression; remaining errors arise from model semantics or gold defects. In a 30-body guard corpus, the write chain intercepts 20/20 hallucinated action bodies with zero false positives. VirtualSet thus remains competitive on SQL's home benchmark while providing pre-execution semantics for guarded decisions.
toXiv_bot_toot

Yesterday, Finnish EV smart charging service Synergi organised a mass 'smart charging' event in Finland, demonstrating 2.5 MW of controllable capacity.
#SmartCharging

#Wikidata WikiProjects Days 2026 is coming up in mid-June! This virtual conference is a great opportunity to learn about @… and contribute to its numerous WikiProjects!
If you are interested in giving a talk, the deadline for submitting a session is 31 May CEST.

"US heatwave threatens 250th anniversary events and World Cup"
#US #USA #America #Football

US heatwave threatens 250th anniversary events and World Cup
Weekend’s high temperatures and humidity ‘virtually impossible’ without climate crisis, researchers say