SirStone 32a5e72fac Gun mixing (TMHorizon+BitBrain) vs DrussGT: clean negative, no dodge disruption ...

4 arms x 7 runs vs real DrussGT. mix alternates the two guns 476 times/7 runs
(liveness OK) but our bullets are no more varied (power sd / aim-offset sd flat)
and DrussGT's dodge quality is unchanged (miss/tick mix-pat +0.03, p=0.66; MDE
3.8%). mix wins 24/49 = the 49% baseline; the user's 6/10 has P=0.353 at 49%.
New tools/ab/ab_dodge_analyze.py splits the validated per-shot dodge instrument
by arm and adds gun-switch/power/bearing liveness; fixtures committed.

2026-09-24 23:07:05 +02:00

..

adr

docs(adr): Evo_Bot neuroevolution gun architecture (#63)

2026-08-24 00:02:47 +02:00

agents

chore: add agent skills configuration

2026-08-15 19:26:43 +02:00

papers

feat(ModularBot): 6 guns, pattern matcher, melee modules, adversarial bots

2026-09-20 00:59:53 +02:00

research

docs(research): portability audit of DrussGT 3.1.4159

2026-09-20 23:44:42 +02:00

bitbrain_algorithm.md

docs: reverse-engineer the BitBrain algorithm from its C source; assess as a gun

2026-09-24 20:17:08 +02:00

bitbrain_gate_test.md

BitBrain gate test: fine-grained aim correction vs naive + Pattern (offline)

2026-09-24 21:23:29 +02:00

bitbrain_gun_verdict.md

BitBrain verdict: clean negative at 30 runs/arm; analyzer gets MC + Mann-Whitney + MDE

2026-09-24 23:02:59 +02:00

drussgt_dodge_vs_power.md

DrussGT dodge vs fired power: no movement response once range is controlled

2026-09-24 21:22:38 +02:00

env_reference.md

env_reference: the ring mover was NEVER measured offline - correct a false label

2026-09-24 21:44:17 +02:00

feature_ab_results.md

Ram: finisher-only by default, and the bullet-rain abort now measures real energy

2026-09-22 08:14:03 +02:00

gun_mix_disruption.md

Gun mixing (TMHorizon+BitBrain) vs DrussGT: clean negative, no dodge disruption

2026-09-24 23:07:05 +02:00

gun_rack_analysis.md

selector: arrival-accuracy tie-break measured NEGATIVE; randomness is load-bearing

2026-09-22 01:07:12 +02:00

gun_rack_summary.md

selector: arrival-accuracy tie-break measured NEGATIVE; randomness is load-bearing

2026-09-22 01:07:12 +02:00

lead_capture_by_range.md

lead capture by range: we under-lead (0.40->0.135) — a RANGE effect, not a power one

2026-09-24 22:47:18 +02:00

melee_vs_1v1_racks.md

Melee vs 1v1 racks: mechanism built, but NO gun-level payoff - do not split

2026-09-22 08:08:43 +02:00

offline_harness_trust.md

Offline harness: audited, calibrated against live, and one real bug fixed

2026-09-24 21:40:38 +02:00

ramming_negative_result.md

Ram: finisher-only by default, and the bullet-rain abort now measures real energy

2026-09-22 08:14:03 +02:00

rl-algorithm-choice.md

chore: rename CLAUDE.md → AGENTS.md, move research doc to docs/

2026-08-27 18:11:56 +02:00

selector_negative_value.md

SHIPPED: the default rack is now Pattern-only (+49% hit rate, +66% damage on the boss)

2026-09-22 02:10:07 +02:00

tracker_death_events.md

tracker: corpses do not exist - revert the fix and retire the workaround

2026-09-21 22:41:11 +02:00