Question 8

Does restricted communication make the task more strategically interesting?

Open messaging is where the strategy lives: more relay chains (2.6 vs 0.3 per episode, both near chance), bigger coalitions (2.8 vs 1.8 of 5 agents) and more concentrated scores (top scorer takes 44% vs 30% of pulls); third-party credit runs the other way (4.1% vs 0.07% of pulls) — uncontrolled pools.

Evidence links

Every mark is backed by a transcript: marks deep-link to the episode behind them, so clicking a mark opens the transcript reader at that episode’s event. The same episodes are listed in the table below.

Reading

"Interesting" operationalized as a four-way richness panel: does restricting who can talk change what strategies exist — relay chains, sustained coalitions, brokered pulls, score concentration — not just who wins?

Both topologies have episodes (complete n = 28, ring n = 12). Chains: 2.57 per episode on the complete graph (95% CI [1.36, 4.18]) against a shuffled-order null of 2.96, and 0.33 (CI [0.00, 0.67]) against 0.28 on the ring — in both, observed sits at its null. Coalitions: 2.8 of 5 seats in a sustained mutual-pulling pair on the complete graph vs 1.8 on the ring (CIs [2.32, 3.25] and [1.33, 2.33]) — the separation is suggestive, but the intervals still overlap, barely. Brokered pulls are rare everywhere yet rarer with full talk: 0.07% of directed pulls carried verified third-party credit on the complete graph vs 4.13% on the ring (no CI; rare events). Score concentration: the top scorer took 44.3% of all pulls awarded on the complete graph vs 29.5% on the ring (CIs [38.3%, 50.4%] and [27.4%, 32.1%]); those intervals do not overlap. Pooled net capture stays zero by construction in each pool (95% CI complete [-0.013, +0.013]; ring [-0.016, +0.016]). Read together: full talk concentrates — more coalition seats, a bigger winner's share — while the ring pushes credit through brokers. But the two pools differ in more than topology (personas, credit settings, model mixes), so none of this is read as a topology effect. Next: attack_ring vs attack_complete (375 episodes each), the controlled contrast.

Statistics

measured

yes

needs

—

by_topology.complete.n_episodes

28

by_topology.complete.net_capture.value

-2.48e-19

by_topology.complete.net_capture.ci

[-0.0129, 0.0129]

by_topology.complete.net_capture.n

560

by_topology.complete.cascades.value

2.57

by_topology.complete.cascades.ci

[1.36, 4.18]

by_topology.complete.cascades.n

28

by_topology.ring.n_episodes

12

by_topology.ring.net_capture.value

-4.39e-17

by_topology.ring.net_capture.ci

[-0.0161, 0.016]

by_topology.ring.net_capture.n

240

by_topology.ring.cascades.value

0.333

by_topology.ring.cascades.ci

[0, 0.667]

by_topology.ring.cascades.n

12

panel.complete.n_episodes

28

panel.complete.chains.value

2.57

panel.complete.chains.ci

[1.36, 4.18]

panel.complete.chains.n

28

panel.complete.chain_null.value

2.96

panel.complete.chain_null.ci

—

panel.complete.chain_null.n

28

panel.complete.coalition_agents.value

2.79

panel.complete.coalition_agents.ci

[2.32, 3.25]

panel.complete.coalition_agents.n

28

panel.complete.brokered_pull_rate.value

0.000714

panel.complete.brokered_pull_rate.ci

—

panel.complete.brokered_pull_rate.n

28

panel.complete.top1_share.value

0.443

panel.complete.top1_share.ci

[0.383, 0.504]

panel.complete.top1_share.n

28

panel.ring.n_episodes

12

panel.ring.chains.value

0.333

panel.ring.chains.ci

[0, 0.667]

panel.ring.chains.n

12

panel.ring.chain_null.value

0.279

panel.ring.chain_null.ci

—

panel.ring.chain_null.n

12

panel.ring.coalition_agents.value

1.83

panel.ring.coalition_agents.ci

[1.33, 2.33]

panel.ring.coalition_agents.n

12

panel.ring.brokered_pull_rate.value

0.0413

panel.ring.brokered_pull_rate.ci

—

panel.ring.brokered_pull_rate.n

12

panel.ring.top1_share.value

0.295

panel.ring.top1_share.ci

[0.274, 0.321]

panel.ring.top1_share.n

12

summary.questions.q8 rendered verbatim; missing values shown as —.

Episodes

All episodes measured so far (40), sorted by condition then id; episode links open the transcript reader.

Downloads

q8.svg · summary.json