PaTAS: A parallel ‘trust meter’ for safer, more reliable AI predictions

Kari Jaaskelainen

26 Nov 2025 — 1 min read

Accuracy isn’t the same as reliability. Meet PaTAS—a “trust meter” that runs in parallel with neural networks to quantify how much you should trust each prediction, using Subjective Logic.

How it works: PaTAS adds Trust Nodes and Trust Functions that propagate trust about inputs, parameters, and activations. A Parameter Trust Update learns which weights are reliable, while an Inference‑Path Trust Assessment (IPTA) estimates per‑example trust at inference.
Why it matters: Produces interpretable, symmetric, and convergent trust scores; exposes reliability gaps in poisoned, biased, noisy, or adversarial data; and flags when model confidence diverges from actual reliability.
What they found: Across real‑world and adversarial tests, PaTAS distinguishes benign from adversarial inputs and complements accuracy with clear uncertainty signals.

Bottom line: PaTAS makes trust a first‑class signal throughout the AI lifecycle—from training to deployment—so decisions in safety‑critical settings can be audited, compared, and improved.

Paper: https://arxiv.org/abs/2511.20586v1

Paper: https://arxiv.org/abs/2511.20586v1

Register: https://www.AiFeta.com

AI TrustworthyAI Reliability NeuralNetworks Safety AdversarialML Uncertainty Explainability SubjectiveLogic MLOps

Beyond URLs: Metadata That Makes LLMs Train Faster

Smarter LLMs, Faster—thanks to metadata What if training a large language model didn't just rely on text, but on the context around it? This study shows that adding fine-grained metadata—not just URLs—can meaningfully speed up pretraining and improve quality. * Beyond URLs: detailed quality signals (e.

Escaping the Verifier: Learning to Reason via Demonstrations

LLMs can learn to reason—without task verifiers Many real-world problems don’t have automatic checkers to grade answers, even though we have lots of expert solutions. RARO (Relativistic Adversarial Reasoning Optimization) shows how to train reasoning skills from those examples alone. How it works: * A policy (the model) tries

VacuumVLA: A Two-in-One Robot Hand That Grips and Suctions

Robots guided by Vision-Language-Action (VLA) AI are getting better at everyday tasks—but most still use simple two-finger grippers. That limits them on smooth, flat, or handleless objects. VacuumVLA is a low-cost robot hand that merges a standard two-finger gripper with a vacuum suction cup. The robot can switch between

ChatDRex: No‑Code, Conversational AI for Drug Repurposing

Meet ChatDRex Finding new uses for approved drugs can save years and millions. But making those predictions usually takes teams of specialists and a tangle of tools. ChatDRex changes that. It’s a conversation-based, no‑code, multi‑agent system that lets clinicians and researchers ask complex bioinformatics questions in plain

Read more

Beyond URLs: Metadata That Makes LLMs Train Faster

Escaping the Verifier: Learning to Reason via Demonstrations

VacuumVLA: A Two-in-One Robot Hand That Grips and Suctions

ChatDRex: No‑Code, Conversational AI for Drug Repurposing