SirRoboGarage

melee_bitbrain_ab

MELEE A/B: BitBrain vs shipped Pattern rack — repo's first melee measurement (null)

2026-09-26 00:35:44 +02:00

bitbrain_vs_tmhorizon_ab_bands.txt

BitBrain vs TMHorizon vs Pattern: live A/B on shipped TFIL (null result)

2026-09-25 23:55:21 +02:00

bitbrain_vs_tmhorizon_ab_report.txt

BitBrain vs TMHorizon vs Pattern: live A/B on shipped TFIL (null result)

2026-09-25 23:55:21 +02:00

bitbrain_vs_tmhorizon_ab_session.json

BitBrain vs TMHorizon vs Pattern: live A/B on shipped TFIL (null result)

2026-09-25 23:55:21 +02:00

dodge_vs_power_report.txt

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

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

dodge_vs_power_results.json

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

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

exact_geometry_gate_report.txt

j133 ledger: appended 'Missed fires + the label question' (catch 98.888->100%, 746/67065 shots were blind: 456 by the server +3*power bonus, 290 by our own same-tick damage; exact label still -0.230, state-conditional model -0.347 -> the observable state is the constraint) + report fixtures

2026-09-26 12:22:31 +02:00

gauntlet_bitbrain_vs_pattern_report.txt

gauntlet: BitBrain vs Pattern across 32 legacy opponents (does not generalize)

2026-09-26 00:55:57 +02:00

gauntlet_bitbrain_vs_pattern_session.json

gauntlet: BitBrain vs Pattern across 32 legacy opponents (does not generalize)

2026-09-26 00:55:57 +02:00

gun_mix_ab_report.txt

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

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

gun_mix_dodge_report.txt

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

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

gun_mix_dodge_results.json

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

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

headon_longrange_ab_report.txt

HeadOn (no-lead) vs Pattern LIVE at long range: clean negative, offline ruler killed

2026-09-24 23:52:49 +02:00

headon_longrange_bands.txt

HeadOn (no-lead) vs Pattern LIVE at long range: clean negative, offline ruler killed

2026-09-24 23:52:49 +02:00

headon_longrange_live_results.json

HeadOn (no-lead) vs Pattern LIVE at long range: clean negative, offline ruler killed

2026-09-24 23:52:49 +02:00

label_inversion_three_way_report.txt

j133 ledger: appended 'Missed fires + the label question' (catch 98.888->100%, 746/67065 shots were blind: 456 by the server +3*power bonus, 290 by our own same-tick damage; exact label still -0.230, state-conditional model -0.347 -> the observable state is the constraint) + report fixtures

2026-09-26 12:22:31 +02:00

lead_capture_by_range_output.txt

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

lead_capture_by_range_results.json

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

learned_surfer_gate_report.txt

learned movement: danger-map alignment diagnostic (corr(P(arrival bin), P(hit|bin)) = -0.342) in the gate + ledger

2026-09-26 10:45:26 +02:00

learned_surfer_gate.json

j128 learned movement: state-conditional counted-SBC wave danger (TR_MOVEMENT=learned, default-off), offline gate + pre-registered panel arms

2026-09-26 10:42:10 +02:00

outcome_label_gate_report.txt

j130 learned movement outcome label: live panel results (no arm beats strafe; label swap is a dead heat; gap is information) + Gate A report

2026-09-26 11:35:47 +02:00

state_window_gate_report.txt

State-window gate: a temporal window of wave-relative states does NOT beat a single state

2026-09-25 08:43:36 +02:00

state_window_gate.json

State-window gate: a temporal window of wave-relative states does NOT beat a single state

2026-09-25 08:43:36 +02:00

strafe_fire_catch_report.txt

j134 fire fix: share ONE fire_tracker across tfil/ring/strafe/learned/surf (TR_FIRE_FIX, default on); env-gated TR_FIRE_DIAG alignment trace

2026-09-26 12:40:19 +02:00

tfil_commit_ab_report_runs7.md

TFIL: measure the commitment A/B on 490 live DrussGT rounds - no effect

2026-09-24 20:24:34 +02:00

tfil_commit_ab_report_runs14.md

TFIL: measure the commitment A/B on 490 live DrussGT rounds - no effect

2026-09-24 20:24:34 +02:00

tfil_commit_ab_results_runs7.json

TFIL: measure the commitment A/B on 490 live DrussGT rounds - no effect

2026-09-24 20:24:34 +02:00

tfil_commit_ab_results_runs14.json

TFIL: measure the commitment A/B on 490 live DrussGT rounds - no effect

2026-09-24 20:24:34 +02:00

tfil_commit_default.golden

TFIL: remove the virtual centre pillar from the shipped default; register j102 env reads

2026-09-25 22:02:00 +02:00

tfil_heat_pillar_ab_bands.txt

TFIL heat-time + virtual pillar: live A/B (6 arms x 70 rounds) - neither change beats the pre-change mover

2026-09-25 22:23:11 +02:00

tfil_heat_pillar_ab_mechanism.txt

TFIL heat-time + virtual pillar: live A/B (6 arms x 70 rounds) - neither change beats the pre-change mover

2026-09-25 22:23:11 +02:00

tfil_heat_pillar_ab_report.txt

TFIL heat-time + virtual pillar: live A/B (6 arms x 70 rounds) - neither change beats the pre-change mover

2026-09-25 22:23:11 +02:00

tfil_heat_pillar_ab_results.json

TFIL heat-time + virtual pillar: live A/B (6 arms x 70 rounds) - neither change beats the pre-change mover

2026-09-25 22:23:11 +02:00

tmcomposites_gate.json

TMComposites gate: per-gun confidence faithful for 3 guns; no pair composes

2026-09-25 22:04:39 +02:00