NISHIO Hirokazu[English][日本語]

Fairness is not a single axis.

nishio.iconFairness is not a single axis. GPT5.iconI agree. Fairness is not something that can be measured by a "single index" but is a multidimensional vector whose weight changes depending on the situation. I will just summarize the main points in a form that can be used in practice.

Typical dimensions of fairness (e.g.)

  • Procedural fairness: transparency, consistency, and accountability of rules.
  • Opportunity (Opportunity): equality of starting points/equal access.
  • Fairness of outcomes (Distributive/Substantive): allocation, disparity, and redistribution.
  • Need/Vulnerability: protection of vulnerable persons and reasonable accommodation.
  • Desert/Merit: How to evaluate efforts and achievements.
  • Relational/Interactional justice: dignity, respect, stigma avoidance.
  • Intergenerational/Temporal: Intergenerational and short/long-term equilibrium.
  • Spatial/Communal: Impact differences by region/community.
  • Individual vs. group: individual unit consistency or group average equilibrium?

When there are multiple axes and weighting of them, fairness is also subjective and varies from person to person because the weighting is influenced by each person's subjective values.

[Fairness is not a single axis. - fairness - Isn't there more than one axis?


This page is auto-translated from /nishio/公正さは単一の軸ではない using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.


(C)NISHIO Hirokazu / Converted from Markdown (en)
Source: [GitHub] / [Scrapbox]