
AC
Alex Chan (Newcastle University), Mohamed Tarraf (Newcastle University), Alex Yakovlev (Newcastle University), Rishad Shafik (Newcastle University)
· 1 min read
ResearcharXiv cs.LG
From Constraints to Causality: Petri net Encodings for Explaining Binary Neural Network Inference
arXiv:2611.22396v1 Announce Type: cross
Abstract: Binary Neural Networks (BNNs) are attractive for resource-constrained hardware and on-device components in autonomous systems. However, their discrete, non-linear behaviour makes them difficult to analyse and trust in safety-relevant settings. Existing approaches based on SAT and Satisfiability Modulo Theories can verify a BNN's input-output properties, but treat it as a monolithic constraint system, which reveal only whether a property holds and not how the computation reaches its result. In this paper, we present an early work that provides a complementary, discrete-event view. We give a compositional translation from the inference semantics of a fixed, trained BNN to a 1-safe Petri net (PN), where each computation step is an explicit transition, so that a firing sequence is a causal trace of the BNN's decision. On a worked example, we establish faithfulness via exhaustive input-output equivalence against a reference implementation, and show how contrasting firing sequences localises where a single-feature change alters the prediction. Finally, we outline two directions this opens: a correctness-of-translation theorem, and a causal-trace analysis of where two trained BNNs diverge in their decisions, a structural question that constraint-based verifiers cannot express.
Original source
This story was published by arXiv cs.LG and written by Alex Chan (Newcastle University), Mohamed Tarraf (Newcastle University), Alex Yakovlev (Newcastle University), Rishad Shafik (Newcastle University). SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


