Settlers / Research

75 pages · Search titles and descriptions

↑ ↓ to navigate · Enter to open · Esc to closeLocal search
Play the game

Protocol run: completed

Paired contrast slot 0 minus slot 1: -0.113 wins per game over 20 seeds (95% interval -0.265 to +0.040).

Planned
80
Attempted
80
Completed
80
Incomplete
0
Unplayed
0
Full retained record and provenance

Run bd18246c-4161-49e7-9391-a2530bdb3434

Status: completed. Experiment: 77be5dcd-ba5e-4fd8-8014-a9aec230ed07. Deterministic paired seeds, every seed played once per rotation.

Planned: 80. Attempted: 80. Completed: 80. Incomplete: 0. Unplayed: 0.

Slot / policyWinsLossesCompletedWin rate95% Wilson intervalMean points
0 / ntuple-leaf-tt27538033.8%24.3%–44.6%7.00
1 / ntuple-leaf36448045.0%34.6%–55.9%7.61
2 / eta13678016.2%9.7%–25.8%6.69
3 / fast476805.0%2.0%–12.2%6.04

Paired contrast slot 0 minus slot 1: -0.113 wins per game over 20 seeds (95% interval -0.265 to +0.040).

Manifest SHA-256: 1f3045c3b9e801f719aa5ed8436dab7910924b58458bd3dbbc7a8f41b0b497c7.

Inventory SHA-256: 8757083f74a5d4cf88e9e931c3b997d7f638920f11a8dd9672930072f3b4ea94.

Artifacts are local under runs/bd18246c-4161-49e7-9391-a2530bdb3434/; no remote durability is claimed until an archive receipt exists.

Intervals are descriptive per competitor slot across completed games; outcomes within a game are dependent. Incomplete games are not losses. The paired contrast is the per-seed win difference between slots 0 and 1 with a normal-approximation interval over seeds.