Information Leakage at Population Scale: An Evaluation of the Polymarket Insider-Relevant Subpopulation, 2020-2026
Maksym Nechepurenko · 2026 · Preprint · SSRN / arXiv
Abstract
We carry the deadline-resolved Information Leakage Score framework from a single-case proof of concept to a population-scale evaluation across 12,708 Polymarket markets, October 2020 to April 2026. Scaling reveals that the framework's effective domain is materially narrower than initial framing suggested, and the principal obstacle is resolution semantics. Only 88 candidate markets yield computable scores; only one of 32 FFIC markets is in scope, and 14 are unclassifiable due to genuine resolution-criterion ambiguity. A hazard-decay baseline correction yields heterogeneous results across categories, while a Weibull preference in the pooled post-2024 cell reflects category mixture rather than within-cell duration dependence. The implication is that detection of informed flow requires refinement on the resolution-typology and score-baseline axes, not only score computation.
Related tracks
Cite this work
@online{nechepurenko2026_populationleakage,
author = {Nechepurenko, Maksym},
title = {Information Leakage at Population Scale: An Evaluation of the Polymarket Insider-Relevant Subpopulation, 2020-2026},
date = {2026-04-29}, doi = {10.2139/ssrn.6686819}, url = {https://ssrn.com/abstract=6686819},
eprint = {2605.00459}, eprinttype = {arxiv}, pubstate = {preprint}
}