Beyond Explanation: Evidentiary Rights for Algorithmic Accountability

• URL: http://arxiv.org/abs/2603.22716v1
• Date: Tue, 24 Mar 2026 02:12:20 GMT
• Title: Beyond Explanation: Evidentiary Rights for Algorithmic Accountability
• Abstract summary: Algorithmic accountability scholarship has focused heavily on explanation, helping affected parties understand why decisions were made.<n>We argue this focus is insufficient. Explanation without evidentiary access does not enable meaningful contestation.<n>We propose evidentiary rights as the missing procedural component, and develop counterfactual interrogation rights.
• Score: 0.3196233350675362
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Algorithmic accountability scholarship has focused heavily on explanation, helping affected parties understand why decisions were made. We argue this focus is insufficient. Explanation without evidentiary access does not enable meaningful contestation. A person told "your risk score was 0.73" understands the decision but cannot verify the score, test alternatives, or produce counter-evidence. We introduce a taxonomy of contestation failures, showing that most accountability interventions address only one failure mode (opacity) while leaving four others unaddressed. Drawing on analysis of 168 legal cases spanning algorithmic decision-making contexts, we find that contestation faces a two-gate structure: a procedural gate (evidentiary access) and a doctrinal gate (substantive liability rules). Among litigated cases, those without evidence access almost never succeed (9%); those with access succeed at rates approaching 97% in domains without liability shields. Where doctrinal immunities apply (e.g., Section 230), even full evidentiary scrutiny produces no liability. This association almost certainly reflects selection effects; our empirical contribution is diagnostic rather than causal. The data identify where contestation fails among observable cases, not whether providing access would change outcomes for currently-excluded cases. We propose evidentiary rights as the missing procedural component, and develop counterfactual interrogation rights that allow affected parties to probe decision systems with modified inputs and observe whether outcomes change, without requiring disclosure of model internals. This reframes algorithmic accountability from a transparency problem to a procedural rights problem.

Related papers

• Visualizing Uncertainty-to-Action Composition for Human Oversight [0.3823356975862005]
  Most uncertainty visualizations encode uncertainty in model outputs, leaving users to discern the most appropriate course of action.<n>We introduce an uncertainty-to-action binding framework that composes multiple uncertainty conditions into a single oversight response.<n>We also present ActionCue, a process-transparency visualization that renders that composition explicit.
  arXiv  Detail & Related papers  (2026-08-17T11:28:41Z)
• The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation [68.98390038721963]
  We show that multi-agent discussion erases up to 72% of issue-critical facts.<n>This loss is consequential: retained evidence can reconstruct the issue misleadingly, final stances remain anchored in base-model priors, and a single malicious agent can inject misinformation into the shrinking shared context.<n>We call for evaluations that measure which facts, uncertainties, and legitimate disagreements survive interaction.
  arXiv  Detail & Related papers  (2026-06-02T02:15:40Z)
• Explainable AI Isn't Enough! Rethinking Algorithmic Contestability [3.135152720206845]
  We propose an operational definition of contestability as a natural complement to recourse.<n>We identify three types of evidence warranting reversal according to the decision maker's own ethical standards.<n>We argue that these render decisions normatively indefensible and thus successfully contestable.
  arXiv  Detail & Related papers  (2026-05-15T15:14:13Z)
• Fairness under uncertainty in sequential decisions [14.392931077157906]
  Algorithmic approaches alone cannot resolve structural inequalities.<n>Many real machine learning applications are online and sequential, with prior decisions informing future ones.<n>This paper introduces a taxonomy of uncertainty in sequential decision-making.
  arXiv  Detail & Related papers  (2026-04-23T14:17:58Z)
• Alternative Fairness and Accuracy Optimization in Criminal Justice [0.0]
  We develop a simple modification to standard group fairness.<n>We minimize a weighted error loss while keeping differences in false negative rates within a small tolerance.<n>This makes solutions easier to find, can raise predictive accuracy, and surfaces the ethical choice of error costs.
  arXiv  Detail & Related papers  (2025-11-06T16:24:43Z)
• Partial Identification Approach to Counterfactual Fairness Assessment [50.88100567472179]
  We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence.<n>Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.
  arXiv  Detail & Related papers  (2025-09-30T18:35:08Z)
• A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences [76.73731245899454]
  We propose a transparent law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience.<n>Inspired by this schema, we introduce the challenging task, which takes a textual case description and outputs a hierarchical structure justifying the final decision.<n>This benchmark paves the way for transparent and accountable AI-assisted law reasoning in the Intelligent Court''
  arXiv  Detail & Related papers  (2025-03-02T10:26:54Z)
• Peer-induced Fairness: A Causal Approach for Algorithmic Fairness Auditing [0.0]
  The European Union's Artificial Intelligence Act takes effect on 1 August 2024. High-risk AI applications must adhere to stringent transparency and fairness standards. We propose a novel framework, which combines the strengths of counterfactual fairness and peer comparison strategy.
  arXiv  Detail & Related papers  (2024-08-05T15:35:34Z)
• Auditing Fairness under Unobserved Confounding [56.61738581796362]
  We show that, surprisingly, one can still compute meaningful bounds on treatment rates for high-risk individuals.<n>We use the fact that in many real-world settings we have data from prior to any allocation to derive unbiased estimates of risk.
  arXiv  Detail & Related papers  (2024-03-18T21:09:06Z)
• Causal Fairness for Outcome Control [68.12191782657437]
  We study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable. In this paper, we first analyze through causal lenses the notion of benefit, which captures how much a specific individual would benefit from a positive decision. We then note that the benefit itself may be influenced by the protected attribute, and propose causal tools which can be used to analyze this.
  arXiv  Detail & Related papers  (2023-06-08T09:31:18Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.