SearcharxivSearch

arXiv subjects

Marinella Quaranta

Publications and source records attributed to Marinella Quaranta.

2 recordsLinked to original sources

Extracting ODRL Policies from Business Process Models: A Graph Traversal Approach to Compliance-by-Extraction

Organisations maintain large corpora of process models expressed in the Business Process Model and Notation (BPMN), yet the normative content encoded in those models, the obligations, permissions, and prohibitions that govern participant behaviour, remains inaccessible to policy infrastructure. The Open Digital Rights Language (ODRL) is the emerging lingua franca of machine-readable policy, but authoring ODRL at scale is slow, expert-intensive work, and generation by large language models introduces well-documented risks of structural invalidity. We present a pipeline that resolves this gap by extracting ODRL policies automatically from BPMN XML, grounded in the observation that BPMN control flow encodes deontic modalities by construction. The pipeline traverses the BPMN process graph, classifies each task as an odrl:Duty or odrl:Permission via a reachability check, and introduces a novel treatment of intermediate catch events as odrl:Prohibition rules with lifting constraints, capturing waiting semantics that prior approaches have dropped. The result is a compliance-by-extraction approach in which auditable, interoperable ODRL policies are derived directly from the process models organisations already maintain. The implementation and a live demonstration are available at https://github.com/manabcodes/bpmn2odrl and https://bpmn.linkeddata.es/.

cs.DB

ChatGPT Unveils Its Limits: Principles of Law Deliver Checkmate

This study examines the performance of ChatGPT with an experiment in the legal domain. We compare the outcome with it a baseline using regular expressions (Regex), rather than focusing solely on the assessment against human performance. The study reveals that even if ChatGPT has access to the necessary knowledge and competencies, it is unable to assemble them, reason through, in a way that leads to an exhaustive result. This unveils a major limitation of ChatGPT. Intelligence encompasses the ability to break down complex issues and address them according to multiple required competencies, providing a unified and comprehensive solution. In the legal domain, one of the most crucial tasks is reading legal decisions and extracting key passages condensed from principles of law (PoLs), which are then incorporated into subsequent rulings by judges or defense documents by lawyers. In performing this task, artificial intelligence lacks an all-encompassing understanding and reasoning, which makes it inherently limited. Genuine intelligence, remains a uniquely human trait, at least in this particular field.

cs.AI