host:   Darwin 25.5.0 / docker 29.7.2 / 11cpu
image:  pfk-fixture-good
tool:   0.1.0.dev0 (74982e8)
runs:   8 attempted, 8 with a report
command: uv run --project . preflightkit test --format json --config measurements/set-darwin-arm64/.sweep/3.yaml
label:   loaded

duration
  wall is the whole process; tool is what the run itself timed; phases in ms
  run  exit  wall s  tool s  probe_image_preparation  dependencies  target_start  baseline  calibration  experiment  teardown
  ---  ----  ------  ------  -----------------------  ------------  ------------  --------  -----------  ----------  --------
    1     0    3.89    3.49                     1152             0           576       258          625         589       285
    2     0    3.42    3.08                     1081             0           421       233          379         701       263
    3     0    3.60    3.25                     1270             0           453       306          170         716       331
    4     0    4.00    3.67                     1223             0           461       253          771         669       289
    5     0    4.04    3.63                     1166             0           453       283          699         720       298
    6     0    3.91    3.59                     1108             0           553       322          675         643       278
    7     0    4.21    3.89                     1547             0           464       308          709         600       251
    8     0    4.05    3.73                     1259             0           523       321          807         567       247
  med          3.96    3.61                     1194             0           462       294          687         656       281

resolution
  ok is ratio >= 10 (MIN_JITTER_RATIO as this build has it)
  run  jitter   source  n    p50    max  ratio   ok              target  load1
  ---  ------  -------  -  -----  -----  -----  ---  ------------------  -----
    1   1.060  sidecar  5   7.00  15.61   6.60   no  readiness_fallback  40.09
    2   0.240  sidecar  5   6.73  11.46  28.04  yes  readiness_fallback  40.09
    3   0.275  sidecar  5   7.82  22.68  28.50  yes  readiness_fallback  41.76
    4   0.737  sidecar  5   6.96   8.12   9.45   no  readiness_fallback  41.70
    5   0.365  sidecar  5  12.27  20.31  33.65  yes  readiness_fallback  42.69
    6   0.320  sidecar  5   7.61  17.23  23.81  yes  readiness_fallback  42.69
    7   0.470  sidecar  5  12.79  29.04  27.23  yes  readiness_fallback  42.47
    8   2.798  sidecar  5   9.37  11.59   3.35   no  readiness_fallback  42.59
  med   0.417               7.72         25.52                                

teardown floor
  the other half of the same question: what this daemon costs to stop, in ms. A run only calibrates when a budget is close enough to need it, so not_calibrated is a normal row, not a missing measurement
  run  n  floor  stddev  k  threshold          status
  ---  -  -----  ------  -  ---------  --------------
    1  -      -       -  -          -  not_calibrated
    2  -      -       -  -          -  not_calibrated
    3  -      -       -  -          -  not_calibrated
    4  -      -       -  -          -  not_calibrated
    5  -      -       -  -          -  not_calibrated
    6  -      -       -  -          -  not_calibrated
    7  -      -       -  -          -  not_calibrated
    8  -      -       -  -          -  not_calibrated
  med         -                                      

