From Constraints to Causality: Petri net Encodings for Explaining Binary Neural Network Inference
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.
Authors
- Alex Chan (ORCID: https://orcid.org/0000-0001-7617-1066)
- Alex Yakovlev (ORCID: https://orcid.org/0000-0003-0826-9330)
- Rishad Shafik (ORCID: https://orcid.org/0000-0001-5444-537X)
- Mohamed Tarraf (ORCID: https://orcid.org/0009-0006-4505-8670)
Institutions
- Newcastle University (GB)
Publication Details
- Journal
- Electronic Proceedings in Theoretical Computer Science
- Published
- 2026-11-17
- DOI
- https://doi.org/10.4204/eptcs.457.1
- Primary Topic
- Formal Methods in Verification
- Type
- article
- Field-Weighted Citation Impact
- 0.00