{
"question": "does round39 regress CLI decode vs reconstructed round38 on the same machine now?",
"baseline": "same linked objects with pre-round39 ngram.cpp.o and baseline runtime shader directory",
"candidate": "current CLI copied and current shader directory snapshot",
"cases": [
{
"prompt": "data/m5_val_prompts/prompt_albedo_11k.txt",
"n_prompt": 10180,
"n_gen": 32,
"warmup_order": [
"baseline",
"candidate"
],
"measured_order": [
"baseline",
"candidate",
"candidate",
"baseline",
"baseline",
"candidate"
]
},
{
"prompt": "data/m5_val_prompts/prompt_2048tok_ops.txt",
"n_prompt": 1984,
"n_gen": 128,
"measured_order": [
"baseline",
"candidate",
"candidate",
"baseline"
]
}
],
"decision": "report adjacent-pair ratios and medians; repeated >2% slowdown is regression evidence; isolated/noisy differences remain inconclusive; no broad zero-regression claim",
"conditions": "all agent cpu suites complete; live service stopped; one model process; identical env except shader path; no source writes during runs",
"limits": "local only, 12 model launches, per-run timeout180s; no servo/telemetry overhead claim"
}