Rigorous Assessment of Model Inference Accuracy using Language Cardinality

TL;DR

This paper introduces a deterministic, combinatorics-based method for accurately assessing the inference quality of models like finite automata, overcoming biases of traditional statistical approaches.

Contribution

It presents a novel systematic approach using analytic combinatorics to evaluate model accuracy without relying on statistical estimators.

Findings

The method reduces bias and uncertainty in accuracy assessment.

It effectively evaluates models inferred from real-world benchmarks.

Experimental results validate the approach's consistency and applicability.

Abstract

Models such as finite state automata are widely used to abstract the behavior of software systems by capturing the sequences of events observable during their execution. Nevertheless, models rarely exist in practice and, when they do, get easily outdated; moreover, manually building and maintaining models is costly and error-prone. As a result, a variety of model inference methods that automatically construct models from execution traces have been proposed to address these issues. However, performing a systematic and reliable accuracy assessment of inferred models remains an open problem. Even when a reference model is given, most existing model accuracy assessment methods may return misleading and biased results. This is mainly due to their reliance on statistical estimators over a finite number of randomly generated traces, introducing avoidable uncertainty about the estimation and being sensitive to the parameters of the random trace generative process. This paper addresses this problem by developing a systematic approach based on analytic combinatorics that minimizes bias and uncertainty in model accuracy assessment by replacing statistical estimation with deterministic accuracy measures. We experimentally demonstrate the consistency and applicability of our approach by assessing the accuracy of models inferred by state-of-the-art inference tools against reference models from established specification mining benchmarks.