Empirical Evaluation of Deadline-Resolved Information Leakage on Documented Polymarket Insider Cases

This paper reports an end-to-end empirical evaluation of the deadline-Information Leakage Score (ILS^dl) extension introduced in the companion methodology paper. The deadline-ILS extends the original ILS to deadline-resolved prediction-market contracts — the dominant structural form of publicly documented insider trading on Polymarket. We anchor the evaluation in the 2026 U.S.–Iran conflict cluster of the ForesightFlow Insider Cases (FFIC) inventory, the largest documented deadline cluster in the public-reporting record. The evaluation has four parts: per-category exponential-hazard rate estimation for the time-to-event distribution; a single-case ILS^dl computation on the cleanest applicable FFIC market; cross-market wallet analysis across two cluster contracts; and the methodological refinements that the evaluation surfaces.

The hazard-rate estimation produces an adequate exponential fit for military-geopolitics markets (KS p = 0.609, half-life 2.3 days) and a preliminary fit for corporate-disclosure markets (n = 5). The regulatory-decision category is rejected as bimodal (p = 0.013) and requires sub-categorization. On the largest applicable FFIC contract ("US forces enter Iran by April 30," $269M cumulative volume), the article-derived T_event anchor yields ILS^dl = +0.113 versus a resolution-anchored proxy value of −0.331: a 0.444 shift in magnitude on opposite sides of zero, demonstrating that the extension distinguishes signal from proxy artefact. The pre-event drift is mild rather than concentrated, and short-window variants (30-min, 2-h) are exactly zero, ruling out a last-minute informed spike. Cross-market wallet analysis identifies 332 wallets active in both major Iran-cluster markets, but the available trade history covers only the resolution-settlement window; the cross-market signal is therefore settlement arbitrage rather than pre-event coordination, and converting this diagnostic into a coordination-signal diagnostic requires continuous per-trade collection from T_open.

We treat the present evaluation as a methodological proof of concept supported by a single illustrative case, not a population-level evaluation. Five concrete refinements bound any future scaling: a positive-τ requirement, regulatory sub-categorization, corporate-disclosure sample expansion, continuous CLOB price collection, and continuous per-trade collection from T_open. Both data resources used here — the FFIC inventory and the resolution-typology classification of the 911,237-market Polymarket corpus — are released as separate datasets at https://github.com/ForesightFlow/datasets.