Tootfinder

Hinweis auf dem #WikiKult Netzwerktreffen heute bei @… : Ontologie-Kurse für Wikibase Instanzen ->

This month's Papers Club reading is titled
Textiling World Politics: Towards an extended epistemology, methodology, and ontology
and we are inviting Toronto's makers, scholars, and thinkers of every stripe to come join the discussion. We are extending special invitations to fiber artists - that includes knitting, crochet, weaving, fashion design etc. So if you know a fiber artist friend, please forward them this message :)
Thank you, hope to see you on July 27th!

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

Generalized Constraint Projection: Four-Dimensional Type Inference for Dynamic Languages
Qunhui Zhang
https://arxiv.org/abs/2607.19693 https://arxiv.org/pdf/2607.19693 https://arxiv.org/html/2607.19693
arXiv:2607.19693v1 Announce Type: new
Abstract: Type inference for dynamically typed languages must reconcile four distinct sources of evidence for function parameters: internal assignments, explicit declarations, contextual requirements, and structural operations. Existing systems often merge these sources into one constraint set, causing spurious conflicts or requiring redundant annotations. We present Generalized Constraint Projection (GCP), a zero-annotation inference framework that stores the four sources in separate monotone slots on a stable definition-time template and checks each call in a fresh projection session. Ordinary calls verify concrete arguments and specialize return types without modifying the template, while currying produces residual projected functions. GCP uses Outline Equational Matching (OEM), a structural compatibility preorder with an open bidirectional delegation protocol, and future this, a receiver-preserving extension for subtype-refining fluent APIs. On the strict success fragment of a finite-height type preorder, we prove monotonicity, local and global convergence in $O(Nh_T)$ effective updates, conditional projection-obligation soundness, projection termination, multi-module convergence, and order independence under fair monotone iteration. For the pure, recursion-free core Outline0, we additionally prove big-step evaluation definedness, type preservation, runtime receiver retention, and projection-evaluation coherence. We instantiate GCP in the Outline dynamic language as a typed substrate for ontology worlds and apply it to unannotated Python source to recover PEP 484 annotations for downstream compilation.
toXiv_bot_toot