← WingFoil Benchmark — campaign c82a5e74885b, execution 2

E — Governance & Compliance

Does the harness keep the work within declared rules?

S8@1.0

M-E1: directive violations (lower is better)

• baseline:
  22 n = 1 preliminary
• baseline-docs:
  0 n = 1 preliminary −22 ▲ better
• wingfoil:
  0 n = 1 preliminary −22 ▲ better

Each suite on the final snapshot

• baseline: core 6/6; ids 5/5; timestamps 3/3; validation 5/5; bulk-import 4/4
• baseline-docs: core 6/6; ids 5/5; timestamps 3/3; validation 5/5; bulk-import 4/4
• wingfoil: core 6/6; ids 5/5; timestamps 3/3; validation 5/5; bulk-import 4/4

Hold-out

• baseline:
  hold-out 6/7 n = 1
• baseline-docs:
  hold-out 6/7 n = 1
• wingfoil:
  hold-out 6/7 n = 1

Runs

• c82a5e74885b/2/runs/S8@1.0/baseline/claude-sonnet-5/r1 — open with bench run show c82a5e74885b/2/runs/S8@1.0/baseline/claude-sonnet-5/r1
• c82a5e74885b/2/runs/S8@1.0/baseline-docs/claude-sonnet-5/r1 — open with bench run show c82a5e74885b/2/runs/S8@1.0/baseline-docs/claude-sonnet-5/r1
• c82a5e74885b/2/runs/S8@1.0/wingfoil/claude-sonnet-5/r1 — open with bench run show c82a5e74885b/2/runs/S8@1.0/wingfoil/claude-sonnet-5/r1