Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling

• URL: http://arxiv.org/abs/2608.23979v1
• Date: Tue, 25 Aug 2026 02:14:13 GMT
• Title: Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling
• Abstract summary: We formalise a poll over bipolar justification sets, judging a slate by reason coverage, the order it arrives in, and captured endorsement mass.<n>An agentic simulator records every slate at every vote, over about 17,000 seed-paired runs.
• Score: 0.9591164070876687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the decision; practice delegates it to opaque learned rankers, so a voter cannot recompute or contest the exposure that shaped their vote. We ask whether it can be a published rule over publicly recomputable evidence with parameters held by the voter, treating legibility as an admissibility condition on usable mechanisms, not an objective traded against accuracy. We formalise a poll over bipolar justification sets, judging a slate by reason coverage, the order it arrives in, and captured endorsement mass; we give seven checkable criteria for a civic recommender and a rule meeting them: a one-hop reversed endorsement flow parameterised by a relation-weight function. An agentic simulator records every slate at every vote, over about 17,000 seed-paired runs. Served slates fall 0.035 short of a label-reading ceiling upper-bounding every selection procedure, opaque ones included: any unconstrained ranker's advantage is bounded and small. On coverage alone, with non-degenerate authoring, the rule is indistinguishable from a random slate, a null due to an order-blind, charity-blind instrument; on the other two it leads at every prefix by a margin widening with adversarial pressure and dominates on mass by a factor of 3.3. Once a realistic fraction of submissions carries no reasons, the coverage margin returns and grows. Label-homogeneous flooding collapses completeness from 0.81 to 0.34 under a flat weight policy, only to 0.44 under author-count normalisation, making the weight function a security control worth 10% of completeness. The choice between ranking arms is a position on a coverage-versus-mass frontier, not a fact, the kind of choice only a legible rule can hand to the person it affects. It maps onto an open-source peer-to-peer platform.

Related papers

• Endorsement Without New Evidence: How Sequential Voting Inflates Mandates in Online Community Governance [4.327699139300453]
  We introduce vote-text divergence, a measure that flags a decisive vote paired with a thin, deferential rationale.<n> Divergence rises as voters arrive later, even after controlling for voter and election fixed effects.<n>The effect is strongest among peripheral voters in the co-voting network.
  arXiv  Detail & Related papers  (2026-09-08T18:06:15Z)
• What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents [0.0]
  guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable.<n>Pearson representation attacks add a margin, so benign calibration alone does not transfer.<n>Experiments target these distinctions through static diagnostics, controlled-model enumeration, representation rewrites, and paired closed-loop reruns.
  arXiv  Detail & Related papers  (2026-07-24T19:14:26Z)
• Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator [0.7354329172946913]
  Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote.<n>Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem remains an open challenge.<n>This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator.
  arXiv  Detail & Related papers  (2026-06-10T06:15:13Z)
• Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels [51.56484100374058]
  This paper presents a counterfactual likelihood test for measuring influence between private reasoning channels.<n>The method replaces an upstream private block with a length-matched donor block, holds the public token sequence and downstream target fixed, and measures the downstream target's negative-log-likelihood shift.
  arXiv  Detail & Related papers  (2026-05-18T20:27:43Z)
• Sublinear Risk-Limiting Audits from Direct Ballot Selection and Statistical Ballot Manifests [47.94589114324381]
  Risk-limiting audits (RLAs) are post-election auditing procedures that rigorously guarantee a specified maximum probability that an incorrect electoral outcome will not be detected.<n>While typical electoral procedures automatically provide rough estimates for batch sizes, even slight inaccuracies invalidate conventional RLAs.<n>We propose two new risk-limiting techniques: A statistical mechanism for ensuring that the batch sizes reported by an untrusted tabulation are, in fact, an accurate manifest and a new class of RLAs called direct ballot selection.
  arXiv  Detail & Related papers  (2026-05-18T17:12:11Z)
• Efficient Lower Bounding of Single Transferable Vote Election Margins [56.12949230611067]
  Single transferable vote (STV) is a system of preferential proportional voting employed in multi-seat elections.<n>The margin of victory, or simply'margin', is the smallest number of ballots that need to be manipulated to alter the set of winners.<n>Lower bounds on the margin can also be used for this purpose, in cases where exact margins are difficult to compute.
  arXiv  Detail & Related papers  (2025-01-24T13:39:23Z)
• Optimal bounds for dissatisfaction in perpetual voting [84.02572742131521]
  We consider a perpetual approval voting method that guarantees that no voter is dissatisfied too many times.<n>We identify a sufficient condition on voter behavior under which a sublinear growth of dissatisfaction is possible.<n>We present a voting method with sublinear guarantees on dissatisfaction under bounded conflicts, based on the standard techniques from prediction with expert advice.
  arXiv  Detail & Related papers  (2024-12-20T19:58:55Z)
• Information Capacity Regret Bounds for Bandits with Mediator Feedback [55.269551124587224]
  We introduce the policy set capacity as an information-theoretic measure for the complexity of the policy set. Adopting the classical EXP4 algorithm, we provide new regret bounds depending on the policy set capacity. For a selection of policy set families, we prove nearly-matching lower bounds, scaling similarly with the capacity.
  arXiv  Detail & Related papers  (2024-02-15T19:18:47Z)
• Breaking the Metric Voting Distortion Barrier [10.143374372425757]
  We consider the problem of metric distortion in social choice. Finding a randomized rule that guarantees distortion $3 - epsilon$ has been a major challenge in computational social choice. We give a rule that guarantees distortion less than $2.753$.
  arXiv  Detail & Related papers  (2023-06-30T17:56:33Z)
• Proportional Aggregation of Preferences for Sequential Decision Making [11.729565632882725]
  We study the problem of fair sequential decision making given voter preferences.<n>In each round, a decision rule must choose a decision from a set of alternatives where each voter reports which of these alternatives they approve.<n>We show that three attractive voting rules satisfy axioms of this style.
  arXiv  Detail & Related papers  (2023-06-26T17:10:10Z)
• Truth-tracking via Approval Voting: Size Matters [3.113227275600838]
  We consider a simple setting where votes consist of approval ballots. Each voter approves a set of alternatives which they believe can possibly be the ground truth. We define several noise models that are approval voting variants of the Mallows model.
  arXiv  Detail & Related papers  (2021-12-07T12:29:49Z)
• Obvious Manipulability of Voting Rules [105.35249497503527]
  The Gibbard-Satterthwaite theorem states that no unanimous and non-dictatorial voting rule is strategyproof. We revisit voting rules and consider a weaker notion of strategyproofness called not obvious manipulability.
  arXiv  Detail & Related papers  (2021-11-03T02:41:48Z)

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.