paper-with-me

홈 › Papers

Pointwise-in-Time Explanation for Linear Temporal Logic Rules

2023-06-24 · Noel Brindise, Cedric Langbort

The new field of Explainable Planning (XAIP) has produced a variety of approaches to explain and describe the behavior of autonomous agents to human observers. Many summarize agent behavior in terms of the constraints, or ''rules,'' which the agent adheres to during its trajectories. In this work, we narrow the focus from summary to specific moments in individual trajectories, offering a ''pointwise-in-time'' view. Our novel framework, which we define on Linear Temporal Logic (LTL) rules, assigns an intuitive status to any rule in order to describe the trajectory progress at individual time steps; here, a rule is classified as active, satisfied, inactive, or violated. Given a trajectory, a user may query for status of specific LTL rules at individual trajectory time steps. In this paper, we present this novel framework, named Rule Status Assessment (RSA), and provide an example of its implementation. We find that pointwise-in-time status assessment is useful as a post-hoc diagnostic, enabling a user to systematically track the agent's behavior with respect to a set of rules.

📄 PDF Abstract BibTeX arXiv:2306.13956

Code (2)

n-brindise/live_expl 공식 구현
n-brindise/pointwiseexpl-example 공식 구현

Tasks

Diagnostic

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins

2026-07-01 · Md Rakibul Haque, Shireen Elhabian, Warren Woodrich Pettine arxiv

Forecasting models for health-signal digital twins must preserve the oscillatory, frequency, phase, and state-transition dynamics of physiological signals, yet the pointwise metrics used to benchmark them cannot detect w…

Identifying the Most Explainable Classifier

2019-10-18 · Brett Mullins

We introduce the notion of pointwise coverage to measure the explainability properties of machine learning classifiers. An explanation for a prediction is a definably simple region of the feature space sharing the same l…

BIG-bench Machine LearningPrediction

Guided by Stars: Interpretable Concept Learning Over Time Series via Temporal Logic Semantics

2025-11-06 · Irene Ferfoglia, Simone Silvetti, Gaia Saveri, Laura Nenzi 외 arxiv

Time series classification is a task of paramount importance, as this kind of data often arises in safety-critical applications. However, it is typically tackled with black-box deep learning methods, making it hard for h…

Time Series Classification

Aligned explanations in neural networks

2026-01-07 · Corentin Lobet, Francesca Chiaromonte arxiv

As artificial intelligence increasingly drives critical decisions, the ability to genuinely explain how neural networks make predictions is essential for trust. Yet, most current explanation methods offer post-hoc ration…

Image Classification

Reverse Engineering of Temporal Queries Mediated by LTL Ontologies

2023-05-02 · Marie Fortin, Boris Konev, Vladislav Ryzhikov, Yury Savateev 외

In reverse engineering of database queries, we aim to construct a query from a given set of answers and non-answers; it can then be used to explore the data further or as an explanation of the answers and non-answers. We…