Batch cycle-003. Model 0.2.0, graph 0.2.0, parameters 0.1.1. 30 simulations, seeds 1 to 30; probes on 10. Every figure is a distribution over simulations of a structural model with seed parameter values; it shows what the model implies under these settings, not what will happen. Other nations are frozen at their 2026 ratings. No reconstructed historical data is used in this experiment.
Headline
Poland played 30 rounds from 1996 under the scripted method, with scripted events, 30 times. Its capability index moved from 9.92 to a median of 9.79 (−0.13), with 90 per cent of simulations between 9.78 and 9.80 [experiment_objectives].
Starting position
In 1996 the nation ranks 47 on the index against the frozen field, holds 0 of nine domains at Tier 1 and has a tier rank of 56. Its base income is 305 credits a year, calibrated so that its 2026 position is affordable with headroom for investment.
What was decided
A simulation spent a median of 1,535 credits on moves. The five groups that took most were Transport Infrastructure (build, 134 credits, 8.7 per cent); Energy Infrastructure (build, 114 credits, 7.4 per cent); Communications & Digital Infrastructure (build, 114 credits, 7.4 per cent); National Resilience & Crisis Management (build, 84 credits, 5.5 per cent); Land Power (build, 77 credits, 5.0 per cent) [experiment_decisions_by_group]. By mode: build 77 per cent, buy 19 per cent, partner 4 per cent [experiment_decisions_by_group]. Concentration of spending (HHI) had a median of 0.062, and the most repeated action appeared in 53 per cent of rounds.
The leading domain by period: rounds 1 to 5, Governance & Integrity; rounds 6 to 10, Strategic Infrastructure; rounds 11 to 15, Strategic Infrastructure; rounds 16 to 20, Strategic Infrastructure; rounds 21 to 25, Strategic Infrastructure; rounds 26 to 30, National Security [experiment_spend_by_period].
What the world did
A median simulation saw 5 shocks and 1 upside events. The most damaging per firing were S10 (30 firings in 30 simulations, −32.3 points each); S03 (30 firings in 30 simulations, −28.0 points each); S07 (30 firings in 30 simulations, −11.7 points each) [experiment_shocks]. Upside events fired 30 times across all simulations [experiment_shocks].
The groups that lost most to shocks, per simulation: Trade Facilitation & Logistics −3.05; Fiscal Capacity & Public Finance −2.94; Economic Leverage & Dependence −2.21; Labour & Employment −2.21 [experiment_shock_damage_by_group].
The edges that carried most change through the graph, per simulation: Transport Infrastructure to Trade Facilitation & Logistics (+0.58 points); Advanced Education to Research Talent & Knowledge Creation (+0.53 points); Energy Infrastructure to Advanced Manufacturing (+0.42 points) [experiment_propagation_by_edge].
Where it ended
At 2026 the median rank is 48 (5th to 95th percentile 48 to 48), the median count of Tier 1 domains 0 (0 to 0) and the median tier rank 38; the resilient score, the mean score sum over simulations, is 713 [experiment_objectives].
Why
Without shocks the index ends +1.543 higher on average, so the shocks cost about 1.543 index points [experiment_probe_attribution].
Holding instead of following this method changes the index by −1.132: that is the method's worth against doing nothing [experiment_probe_attribution].
Removing any single one of the five largest actions changes the index by between −0.023 and −0.008, for example 2007 build Transport Infrastructure (16 credits) [experiment_probe_attribution]. The largest actions by credits come late, when income is highest, and are rarely the most valuable.
Removing the largest shock of a simulation raises the index by +0.533 on average [experiment_probe_attribution].
The replay probe reproduces the simulations exactly (index change 0.000000), so the attributions are clean [experiment_probe_attribution].
Surprises
tier_jump (warn): largest gain in one domain within five years: 5 tiers (30 simulations above 2); tiers are reported, not an objective.
retired_words (warn): e4-pol/report.md: 'simulations' 1 time(s), first near line 38; use 'simulations'.
The simulation furthest from the median (seed 2) ends −0.01 from it, with 5 shocks and 1 upside events [experiment_outlier_simulations].
Comparison
This is the baseline (hold) experiment, or there is none for this nation in the batch.
Against history (a hold-out nation): from a reconstructed index of 9.92 the model ends at 9.79, where the 2026 ratings put it at 12.39. Group scores miss by 2.88 points on average, against 2.48 for assuming nothing changed (skill −0.16); the change in each domain has the right sign in 22 per cent of domains. Furthest below history: information and influence (−3.71); furthest above: strategic infrastructure (−1.16) [experiment_against_history]. The starting position is reconstructed, so part of the error is the reconstruction's.