M2b · mcts-m2b.m2b-est-greedy

Estonia, greedy, 20 years

20 simulations of 20 rounds from the 2026 position. Estonia decides by the greedy method; the shock and upside library, drawn at random each round.

Model 0.2.0 · graph 0.2.0 · parameters 0.1.1 · seeds 1–20 · elasticity sampled within each bracket

Every simulation · Compare with another experiment · More experiments like this

Not a forecast

Simulations of a structural model with seed parameter values, to compare methods and test the model. Other nations stay at their 2026 ratings throughout.

Outcome across simulations

The median at 2046, with the 10th to the 90th percentile of the 20 simulations under it.

Capability index: 11.97 (+0.48); From 11.49; 10.93 to 12.79
Rank by index: 29; From 33; 24 to 35
Domains at Tier 1: 0; From 0; 0 to 1
Tier rank: 22; From 27; 18 to 22

Capability index by round

Rank by index, by round

Every objective at the position and at the horizon
Objective	2026	10th percentile	Median	90th percentile	Better
Capability indexprimary	11.49	10.93	11.97	12.79	higher
Rank by index	33	24	29	35	lower
Tier rank	27	18	22	22	lower
Domains at Tier 1	0	0	0	1	higher
Score sum	817.9	784.5	859.2	917.6	higher
Goal-weighted score	817.9	784.5	859.2	917.6	higher
Resilient score	817.9	856.0 (mean score sum over the simulations)			higher

The capability index is the mean of the three dimensions, each the mean of its domains, each the mean of its groups. Tiers are Pareto layers within each domain; the tier rank orders nations by domains held at Tier 1, then Tier 2, and so on. The goal-weighted score is the score sum unless the experiment sets a goal. The primary objective is the one the experiment is judged on; every other objective is reported beside it.

Credits

What each round’s credits went on in the median simulation. Across all simulations, build took 8 per cent, buy took 58 per cent, partner took 34 per cent of the 1,202 credits a simulation spent on actions.

Report

Written from the simulation record by the loop's narrator. Every figure names the query it came from, in square brackets.

Batch mcts-m2b. Model 0.2.0, graph 0.2.0, parameters 0.1.1. 20 simulations, seeds 1 to 20; probes on 5. 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

Estonia played 20 rounds from 2026 under the greedy method, with stochastic events, 20 times. Its capability index moved from 11.49 to a median of 11.97 (+0.48), with 90 per cent of simulations between 10.77 and 13.28 [experiment_objectives].

Starting position

In 2026 the nation ranks 33 on the index against the frozen field, holds 0 of nine domains at Tier 1 and has a tier rank of 27. Its base income is 390 credits a year, calibrated so that its 2026 position is affordable with headroom for investment.

What was decided

A simulation spent a median of 1,210 credits on actions. The five groups that took most were Semiconductors & Advanced Computing (buy, 138 credits, 11.5 per cent); Space Technologies (partner, 116 credits, 9.6 per cent); Economic Output & Productivity (buy, 99 credits, 8.2 per cent); Energy Technologies (buy, 64 credits, 5.3 per cent); Development Cooperation & Global Assistance (buy, 63 credits, 5.3 per cent) [experiment_decisions_by_group]. By mode: buy 57 per cent, partner 34 per cent, build 10 per cent [experiment_decisions_by_group]. Concentration of spending (HHI) had a median of 0.056, and the most repeated action appeared in 60 per cent of rounds.

The leading domain by period: rounds 1 to 5, Critical Technology; rounds 6 to 10, Critical Technology; rounds 11 to 15, Critical Technology; rounds 16 to 20, Critical Technology [experiment_spend_by_period].

The method's chosen action was within 5 per cent of its best alternative in 97 per cent of actions and ahead by more than 25 per cent in 0 per cent [experiment_decision_margins].

What the world did

A median simulation saw 3 shocks and 1 upside events. The most damaging per firing were S09 (3 firings in 3 simulations, −35.8 points each); S04 (11 firings in 9 simulations, −34.1 points each); S03 (10 firings in 9 simulations, −33.9 points each) [experiment_shocks]. Upside events fired 17 times across all simulations [experiment_shocks].

The groups that lost most to shocks, per simulation: Information Environment & Strategic Communication −2.05; Fiscal Capacity & Public Finance −1.90; Trade Facilitation & Logistics −1.86; Economic Leverage & Dependence −1.79 [experiment_shock_damage_by_group].

The edges that carried most change through the graph, per simulation: Semiconductors & Advanced Computing to Artificial Intelligence (+3.17 points); Semiconductors & Advanced Computing to Economic Leverage & Dependence (+1.20 points); Space Technologies to Space Operations (+1.22 points) [experiment_propagation_by_edge].

Where it ended

At 2046 the median rank is 29 (5th to 95th percentile 22 to 37), the median count of Tier 1 domains 0 (0 to 2) and the median tier rank 22; the resilient score, the mean score sum over simulations, is 856 [experiment_objectives].

Tier 1 probability changed most in: human capital (0 to 35 per cent of simulations) [experiment_tiers_by_round].

Why

Without shocks the index ends +0.989 higher on average, so the shocks cost about 0.989 index points [experiment_probe_attribution].

Holding instead of following this method changes the index by −1.633: 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 −0.017 and −0.013, for example 2039 partner Trade Facilitation & Logistics (13 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 +0.589 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

The simulation furthest from the median (seed 8) ends −2.00 from it, with 6 shocks and 0 upside events [experiment_outlier_simulations].

Comparison

This is the baseline (hold) experiment, or there is none for this nation in the batch.

No backcast comparison: this experiment does not start from a historical position [experiment_against_history].

What each decision and shock was worth

Counterfactual probes on the first 5 seeds: the same simulations with one thing changed, paired seed by seed. A removed decision or shock is taken out and the other decisions replayed unchanged, so the difference is that item's worth.

Probe	Index	Score sum	Tier 1	For example
Hold instead of the method	−1.633	−120.8	−0.60
No shocks	+0.989	+71.8	+0.60
Replay of the recorded actions (must change nothing)	0.000	0.0	0.00
Without the 1st largest decision	−0.014	−1.1	0.00	2039 partner Trade Facilitation & Logistics (13 credits)
Without the 2nd largest decision	−0.013	−1.0	0.00	2039 buy Space, Aerospace & Defence Infrastructure (13 credits)
Without the 3rd largest decision	−0.017	−1.0	0.00	2039 partner Export Capability & Sophistication (13 credits)
Without the 4th largest decision	−0.017	−1.1	0.00	2039 buy Artificial Intelligence (13 credits)
Without the 5th largest decision	−0.017	−1.1	0.00	2039 buy Development Cooperation & Global Assistance (13 credits)
Without the 1st largest shock	+0.589	+42.4	+0.40	2039 S03 (-46.5 points)
Without the 2nd largest shock	+0.401	+28.2	0.00	2038 S03 (-31.4 points)
Without the 3rd largest shock	+0.275	+19.9	0.00	2033 S04 (-23.2 points)

Simulations

Three simulations told round by round, each on its own page: the one nearest the median index at the horizon, and those nearest the 10th and the 90th percentile. Every one of the 20 is listed with its outcome on the simulations page.

All 20 simulations

Events

How often each shock and upside event began across the simulations. Shocks come from the ten downside scenarios and upside events from the ten upside ones, at their yearly likelihood.

Event	Kind	Simulations	Mean round	Points
AI labour shock S08	Shock	55 per cent	10.4	−28.4
Regional war spillover S03	Shock	45 per cent	12.9	−33.9
Hybrid coercion S04	Shock	45 per cent	7.8	−34.1
Breadbasket failure S06	Shock	40 per cent	9.5	−16.9
Global funding seizure S02	Shock	30 per cent	10.3	−21.8
Market access opening S12	Upside	20 per cent	8.2	+10.5
Trade bloc rupture S01	Shock	15 per cent	4.0	−22.0
Automated discovery step S17	Upside	15 per cent	15.3	+22.0
Middle East settlement S14	Upside	15 per cent	5.0	+7.3
Cryptographic trust break S09	Shock	15 per cent	9.7	−35.8
Legitimacy rupture S05	Shock	15 per cent	6.3	−13.1
Core disaster S07	Shock	10 per cent	9.0	−13.8
Water-efficient food leap S16	Upside	10 per cent	5.0	+3.0
Chronic disease advance S19	Upside	10 per cent	13.0	+13.6
Debt service reset S11	Upside	5 per cent	4.0	+2.4
Clean power threshold S15	Upside	5 per cent	16.0	+13.6
Outbreak defence succeeds S20	Upside	5 per cent	3.0	+26.1

Groups across simulations

Every capability group: its position, and its median and spread at the horizon across the simulations, with what the method spent on it.

Find a group

Domain

73 of 73 groups

Capability group	Domain	2026	2046	Change	Levels invested	Credits
Semiconductors & Advanced Computing	Critical Technology	2.50	12.03 11.16 to 12.76	+9.53	10.48	138
Space Technologies	Critical Technology	2.67	10.26 9.35 to 11.21	+7.59	8.19	116
Artificial Intelligence	Critical Technology	8.33	14.87 13.53 to 15.70	+6.54	4.47	50
Technical & Vocational Skills	Human Capital	13.00	18.23 17.74 to 18.86	+5.23	5.48	58
Energy Technologies	Critical Technology	4.80	9.90 8.81 to 10.88	+5.10	5.90	64
Development Cooperation & Global Assistance	Information & Influence	7.50	12.39 11.22 to 13.51	+4.89	5.94	63
Advanced Materials & Manufacturing	Critical Technology	5.14	10.01 9.15 to 10.89	+4.87	5.46	60
Sensing, Timing & Navigation	Critical Technology	4.60	9.42 8.55 to 10.17	+4.82	4.56	49
Economic Output & Productivity	Production & Innovation	10.00	14.34 13.20 to 15.08	+4.34	5.60	99
Trade Policy & Market Access	Trade & Investment	13.50	16.80 15.52 to 17.72	+3.30	4.29	46
Connectivity, Cyber & Trust Technologies	Critical Technology	10.80	13.88 12.56 to 14.72	+3.08	4.10	47
Alliances & Security Cooperation	Information & Influence	13.50	16.53 15.52 to 17.32	+3.03	4.19	43
Diplomatic Statecraft & Global Networks	Information & Influence	10.00	12.79 11.57 to 13.69	+2.79	3.69	48
Space, Aerospace & Defence Infrastructure	Strategic Infrastructure	5.67	8.43 7.69 to 9.66	+2.76	3.22	49
Biotechnology & Health Technologies	Critical Technology	7.40	9.85 8.83 to 10.68	+2.45	3.04	35
Investment Attraction & Projection	Trade & Investment	11.33	13.41 12.23 to 14.20	+2.08	3.42	42
Lifelong Learning & Reskilling	Human Capital	14.33	16.19 15.44 to 17.40	+1.86	2.52	29
Culture, Language & Education Diplomacy	Information & Influence	8.40	10.25 9.15 to 11.33	+1.85	2.84	32
Export Capability & Sophistication	Trade & Investment	11.67	13.02 11.70 to 13.78	+1.35	2.72	33
Space Operations	National Security	4.00	5.05 4.38 to 5.56	+1.05	0.00	0
Robotics & Autonomous Systems	Critical Technology	8.25	9.01 8.12 to 10.40	+0.76	1.09	13
Economic Leverage & Dependence	Trade & Investment	11.67	12.22 10.71 to 13.39	+0.55	0.85	10
Strategic Strike & Missile Defence	National Security	6.00	6.54 5.34 to 7.69	+0.54	0.00	0
Technology Adoption & Diffusion	Production & Innovation	14.50	15.00 14.31 to 16.21	+0.50	1.61	20
Research Talent & Knowledge Creation	Human Capital	12.67	12.77 11.82 to 13.53	+0.10	0.37	7
Nuclear Deterrence	National Security	0.00	0.02 0.01 to 0.30	+0.02	0.00	0
Trade Facilitation & Logistics	Trade & Investment	13.00	12.95 11.50 to 13.91	−0.05	1.64	20
Air Power	National Security	4.50	4.42 3.69 to 4.85	−0.08	0.00	0
Advanced Education	Human Capital	14.33	14.15 13.27 to 15.51	−0.18	0.63	11
Global Value Chain Position	Trade & Investment	13.00	12.74 11.77 to 13.65	−0.26	1.01	12
Sovereign Capital & External Financial Power	Financial Strength	9.80	9.50 8.08 to 10.57	−0.30	0.49	6
Advanced Manufacturing	Strategic Infrastructure	10.00	9.58 8.33 to 10.72	−0.42	0.00	0
Health System Capability	Human Capital	14.00	13.56 12.96 to 14.48	−0.44	0.00	0
Population Health	Human Capital	13.67	13.22 12.72 to 13.91	−0.45	0.00	0
Quantum Technologies	Critical Technology	5.50	5.03 4.44 to 5.47	−0.47	0.00	0
Foundational Education	Human Capital	16.50	16.01 15.62 to 16.66	−0.49	0.00	0
Transparency, Oversight & Accountability	Governance & Integrity	16.33	15.82 14.91 to 16.23	−0.51	0.00	0
Early Childhood Development	Human Capital	16.00	15.45 14.98 to 16.19	−0.55	0.00	0
Public Integrity & Anti-Corruption	Governance & Integrity	15.50	14.95 14.05 to 15.38	−0.55	0.00	0
Justice System & Fundamental Rights	Governance & Integrity	15.25	14.69 13.47 to 15.20	−0.56	0.00	0
Land Power	National Security	9.25	8.60 7.43 to 9.53	−0.65	0.00	0
Intelligence & Assessment	National Security	11.67	10.96 8.90 to 12.21	−0.71	0.00	0
Internal Security & Order	Governance & Integrity	14.67	13.95 12.64 to 14.57	−0.72	0.00	0
Digital & AI Competence	Human Capital	16.50	15.76 15.30 to 16.47	−0.74	0.04	1
Joint Command, Projection & Sustainment	National Security	8.67	7.90 6.33 to 8.82	−0.77	0.00	0
Regulatory Governance & Strategic Controls	Governance & Integrity	14.33	13.56 12.78 to 14.40	−0.77	0.00	0
Resource Infrastructure	Strategic Infrastructure	6.75	5.97 4.96 to 7.01	−0.78	0.00	0
Maritime Power	National Security	6.00	5.22 3.85 to 6.27	−0.78	0.00	0
Political Institutions & Civic Participation	Governance & Integrity	16.00	15.21 14.42 to 15.89	−0.79	0.00	0
Force Generation & Mobilisation	National Security	13.33	12.51 11.12 to 13.40	−0.82	0.00	0
Cyber & Electromagnetic Operations	National Security	12.00	11.17 8.98 to 12.34	−0.83	0.00	0
National Resilience & Crisis Management	Governance & Integrity	14.20	13.37 12.12 to 14.13	−0.83	0.00	0
Fiscal Capacity & Public Finance	Financial Strength	14.75	13.91 12.16 to 15.28	−0.84	0.00	0
Innovation & Commercialisation	Production & Innovation	12.50	11.60 10.68 to 12.49	−0.90	0.00	0
Social Infrastructure	Strategic Infrastructure	13.91	13.00 11.48 to 13.96	−0.91	0.00	0
Labour & Employment	Production & Innovation	13.75	12.83 11.59 to 14.05	−0.92	0.00	0
Financial Infrastructure	Strategic Infrastructure	13.25	12.23 10.88 to 13.08	−1.02	0.00	0
Government Effectiveness & Public Administration	Governance & Integrity	17.40	16.37 14.83 to 17.39	−1.03	0.00	0
Diaspora & Global Communities	Information & Influence	11.50	10.47 9.07 to 11.21	−1.03	0.00	0
Communications & Digital Infrastructure	Strategic Infrastructure	14.86	13.81 12.37 to 14.91	−1.05	0.00	0
Structural Transformation & Complexity	Production & Innovation	12.67	11.60 10.78 to 12.43	−1.07	0.00	0
Financial Stability & Crisis Management	Financial Strength	13.67	12.58 11.30 to 13.38	−1.09	0.00	0
Financial Regulation & Integrity	Financial Strength	14.25	13.15 12.09 to 13.95	−1.10	0.00	0
Financial System Depth & Access	Financial Strength	12.00	10.89 9.80 to 11.66	−1.11	0.00	0
Energy Infrastructure	Strategic Infrastructure	8.88	7.75 6.13 to 9.41	−1.13	0.00	0
Industrial & Sectoral Base	Production & Innovation	11.50	10.36 9.07 to 11.30	−1.14	0.00	0
Business Dynamism & Entrepreneurship	Production & Innovation	14.75	13.60 12.74 to 14.41	−1.15	0.00	0
Agriculture & Food Infrastructure	Strategic Infrastructure	11.50	10.34 9.06 to 11.48	−1.16	0.00	0
Water, Sanitation & Waste Infrastructure	Strategic Infrastructure	11.80	10.59 9.22 to 11.78	−1.21	0.00	0
Monetary & Currency Capability	Financial Strength	14.00	12.77 11.58 to 13.68	−1.23	0.00	0
Transport Infrastructure	Strategic Infrastructure	12.00	10.69 9.11 to 12.04	−1.31	0.00	0
Information Environment & Strategic Communication	Information & Influence	12.00	10.66 8.79 to 11.81	−1.34	0.26	3
Digital & Services Trade	Trade & Investment	14.00	12.38 10.74 to 13.71	−1.62	0.00	0

Checks

The automated checks run on this experiment before anything was written about it. A warning is a candidate finding for the improvement loop.

passcredits_conservedlargest gap between credits in and credits accounted for: 4.5e-13
passscores_in_boundsscores range 0.000 to 19.280
passno_nans0 missing values in the trajectory and objectives
passprobe_replay_reproducesthe recorded actions played back reproduce the simulation to within 0.0e+00 points (5 simulations)
passledger_balancesthe edge ledger sums to the propagated change to within 1.0e-06 points
passmove_without_shocklargest one-round change in a group with no shock landing: 1.69 points; 0% of simulations have one above 3
passtier_jumplargest gain in one domain within five years: 3 tiers (1 simulations above 2); tiers are reported, not an objective
passall_tier1_from_outside_top10starting rank 33; 0 simulations reach Tier 1 in all nine domains
passsaturation_high0% of simulations end with a group at 20 that did not start there (median 0 groups)
passsaturation_low0% of simulations end with a group at 0 that did not start there (median 0 groups)
passspend_concentrationmedian concentration of spending across groups (HHI) 0.056; most funded group hard.critical_technology.semiconductors_and_advanced_computing
passsame_actionthe most repeated action (group and mode) appears in a median 60% of rounds

Settings and versions

Experiment mcts-m2b.m2b-est-greedy. Every simulation records the model, graph and parameter versions, the scenario, the method and its seed, so it can be reproduced exactly.

Nation: Estonia (EST)
Position: The 2026 ratings of the National Capability Index
Method: Greedy. Each round, the actions with the most value per credit: a level's own worth plus its long-run effect downstream through the graph, less the maintenance it will need, counting only what arrives before the horizon.
Scenario: The shock and upside library, drawn at random each round
Objective: Capability index, the primary objective the experiment is judged on; every other objective is reported beside it
Horizon: 20 rounds, 2026 to 2046
Simulations: 20 seeds, 1 to 20. Every method in the batch faces the same draws for the same seed.
Graph elasticities: Drawn for each simulation, uniformly within each edge’s bracket
Income: Base credits 390.4 a round, moving with the economic groups
Versions: Model 0.2.0, Capability Dependency Graph 0.2.0, parameters 0.1.1
Batch: MCTS M2b, versus greedy with certainty-equivalent playouts (mcts-m2b)
Runtime: 1.4 seconds in all; 982 microseconds a round

Not a forecast: Every figure is a distribution over the simulations of a structural model, reported to compare methods and test the model. None is a prediction of what a nation will do or become.
Structural parameters: Costs, decay, vulnerability and credits are structural seed values with low or medium confidence, set by domain with single-group exceptions. Five groups have no defensible value in a single-nation model and are flagged in the parameter tables.
Other nations are frozen: One nation is simulated at a time. Every other nation stays at its 2026 rating, so rank and tiers are measured against a still field; where the simulated nation rises past others their own tiers are not re-sorted.
Starting depth and mode are defaults: The position is the National Capability Index ratings. How institutionalised each capability is, and how much was built, bought or partnered, have no data behind them yet and start from structural defaults.
Credits are calibrated, not measured: Each nation’s income is set so that its position is affordable with headroom that rises with its fiscal capacity. It is not yet fiscal capacity as a share of GDP.