Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Code-Driven Law NO, Normware SI!

Giovanni Sileno

TL;DR

The paper addresses the challenge of aligning computational systems with human legal and social norms by arguing that code-driven and data-driven approaches alone are insufficient for justice and governance. It introduces normware as an explicit third design level—both as artifacts and as processes—that regulates, qualificationally anchors, and shapes expectations within socio-technical systems. By distinguishing normware artifacts (regulatory directives, terminology, and expectations) from normware processes (regulation, conflict resolution, and higher-order governance), the work offers a conceptual framework to design, analyze, and audit computational systems embedded in legal contexts. The proposed perspective emphasizes governance, pluralism, and accountability, suggesting practical research directions in specifying normware and resolving conflicts to enable legitimate normative interventions in computational infrastructures.

Abstract

With the digitalization of society, the interest, the debates and the research efforts concerning "code", "law", "artificial intelligence", and their various relationships, have been widely increasing. Yet, most arguments primarily focus on contemporary computational methods and artifacts (inferential models constructed via machine-learning methods, rule-based systems, smart contracts), rather than attempting to identify more fundamental mechanisms. Aiming to go beyond this conceptual limitation, this paper introduces and elaborates on "normware" as an explicit additional stance -- complementary to software and hardware -- for the interpretation and the design of artificial devices. By means of a few examples, I will argue that a normware-centred perspective provides a more adequate abstraction to study and design interactions between computational systems and human institutions, and may help with the design and development of technical interventions within wider socio-technical views.

Code-Driven Law NO, Normware SI!

TL;DR

The paper addresses the challenge of aligning computational systems with human legal and social norms by arguing that code-driven and data-driven approaches alone are insufficient for justice and governance. It introduces normware as an explicit third design level—both as artifacts and as processes—that regulates, qualificationally anchors, and shapes expectations within socio-technical systems. By distinguishing normware artifacts (regulatory directives, terminology, and expectations) from normware processes (regulation, conflict resolution, and higher-order governance), the work offers a conceptual framework to design, analyze, and audit computational systems embedded in legal contexts. The proposed perspective emphasizes governance, pluralism, and accountability, suggesting practical research directions in specifying normware and resolving conflicts to enable legitimate normative interventions in computational infrastructures.

Abstract

With the digitalization of society, the interest, the debates and the research efforts concerning "code", "law", "artificial intelligence", and their various relationships, have been widely increasing. Yet, most arguments primarily focus on contemporary computational methods and artifacts (inferential models constructed via machine-learning methods, rule-based systems, smart contracts), rather than attempting to identify more fundamental mechanisms. Aiming to go beyond this conceptual limitation, this paper introduces and elaborates on "normware" as an explicit additional stance -- complementary to software and hardware -- for the interpretation and the design of artificial devices. By means of a few examples, I will argue that a normware-centred perspective provides a more adequate abstraction to study and design interactions between computational systems and human institutions, and may help with the design and development of technical interventions within wider socio-technical views.

Paper Structure

This paper contains 31 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Outline of the paper
  3. Types of law: a more nuanced distinction
  4. Text-guided law?
  5. Uncertainties in data-driven law
  6. Uncertainties in code-driven law
  7. Setting an alternative technological agenda
  8. Naive computational justice, and its limits
  9. Expecting wrongs, errors, redirections
  10. Normware as artifacts
  11. Directives concerning regulation
  12. Imperative programs
  13. Declarative programs
  14. Directives concerning qualification
  15. Directives concerning expectations
  16. ...and 16 more sections

Figures (3)

  • Figure 1: Examples of first-order control: e.g. a user or developer provides a goal in the form of an instruction and the computer performs an action executing the associated operation. This association is hard-coded or logically derived in code-driven systems, or selected by some machine-learning method in data-driven systems.
  • Figure 2: Second-order control: the tactical goal is used to select an action amongst a pool of available actions, but the tactical goal in itself is selected from a pool of other goals depending on a strategic goal. The strategic goal captures a motivational context driving what the system is striving for.
  • Figure 3: Plural second-order control: competing directives at strategic and tactical levels are aggregated/simplified by resolution mechanisms, which in turn may be resulting from previous resolution actions.