== rounds/memladder-crossover-rotated-2026-09-17/roundA-14sep-binary-27f05a889.jsonl  budget=128  metric=wall  288 ok leg(s), 0 refused
   arm_order=rotating-by-rep
   load_before min/median/max 3.5/5.2/11.6   load_after 3.6/5.2/11.6

-- rotation, as banked --
   arm    pos0  pos1  pos2
   auto     32    32    32
   fold     32    32    32
   force    32    32    32
   BALANCED: every arm in every position equally often (counts [32])

-- paired per-rep difference, fold minus force (positive = force is cheaper) --
        m  reps   fold med  force med  med diff     med %     sign  p
      160    24       1.96       2.21    -0.245   -12.50%    0/24   0.0000
      192    24       2.25       2.23    +0.020    +0.89%   24/24   0.0000
      224    24       2.56       2.26    +0.300   +11.72%   24/24   0.0000
      256    24       2.86       2.28    +0.580   +20.28%   24/24   0.0000

-- crossover --
   fold wins (significant):  [160]
   ties (sign test n.s.):    none
   force wins (significant): [192, 224, 256]
   => crossover is between m=160 and m=192

-- position effect (arm level and rep level divided out; what running Nth is worth) --
        m          pos0           pos1           pos2
      160        +0.05%         -0.07%         -0.08%   pos0-pos1=+0.11%
      192        +0.00%         +0.00%         +0.00%   pos0-pos1=+0.00%
      224        +0.00%         +0.00%         +0.00%   pos0-pos1=+0.00%
      256        +0.00%         -0.02%         -0.01%   pos0-pos1=+0.02%
   The levels are centred, so the READABLE quantity is the GAP: pos0-pos1 is what
   the first slot cost the arm that held it, and is the term a fixed order banks.
   (a FIXED-order round carries pos0-minus-pos1 as a systematic term it cannot see:
    on this driver until 17 Sep 2026 that term sat entirely on `fold`, which ran first)