Files
peltier.io/results/calibration/2026-07-06-comrak-full-calibration.json
T
Claude 73763321c6 bench: automated A/A + regression-injection calibration (Phase 1)
Adds 'bench-runner calibrate': N A/A sessions counted against a <5%
false-positive bar, and N sessions with a synthetic slowdown injected
as a real busy-wait inside the candidate's timed window, counted
against a >=95% detection bar (detected = ratio CI entirely below 1.0).
Bootstrap seed varies per session so resampling noise is not
correlated across the very statistic being validated. JSON evidence
includes per-session CIs, injected wait, acceptance verdict, and env
fingerprint.

First run against the real comrak workload (20+20 sessions, pinned
core): false-positive rate 0.000, detection rate 0.950 -> PASS.
Evidence: results/calibration/2026-07-06-comrak-full-calibration.json.
Closes the SPEC 3.1 acceptance-criteria gap; remaining Phase 1 gaps:
no-net containers, perf profiling, diff-test orchestration, agent IPC.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EcKPWQ3MQD4NdEHwar96u2
2026-07-06 20:20:40 +00:00

228 lines
5.1 KiB
JSON

{
"aa_false_positive_rate": 0.0,
"aa_sessions": [
{
"hi": 1.015998931989443,
"lo": 0.9905153352677495,
"median": 1.0012776949264486
},
{
"hi": 1.0055502756953207,
"lo": 0.981646945965943,
"median": 0.9908293785706317
},
{
"hi": 1.0204094554652672,
"lo": 0.9846287241295675,
"median": 1.002373764499574
},
{
"hi": 1.0047915300411685,
"lo": 0.9860341673780392,
"median": 0.9964988810591069
},
{
"hi": 1.0102726750450453,
"lo": 0.9876236508283872,
"median": 0.9947054654657848
},
{
"hi": 1.0298441811992136,
"lo": 0.9876526600106184,
"median": 1.0086506615393056
},
{
"hi": 1.0099440547974916,
"lo": 0.9822805275362518,
"median": 0.993850347123508
},
{
"hi": 1.00385962045072,
"lo": 0.9848165937114653,
"median": 0.9939030705425225
},
{
"hi": 1.0115679493048169,
"lo": 0.9909357476627676,
"median": 1.0008452273219608
},
{
"hi": 1.013718263355025,
"lo": 0.977768078322329,
"median": 0.9983105725894315
},
{
"hi": 1.0070675650128182,
"lo": 0.9868898707776302,
"median": 0.9979255224721003
},
{
"hi": 1.01473324312686,
"lo": 0.984779294044258,
"median": 0.9942794507746874
},
{
"hi": 1.0484508437256985,
"lo": 0.9663266833242238,
"median": 1.0028654978002207
},
{
"hi": 1.0153007892092838,
"lo": 0.9903096574162721,
"median": 1.0049001338403383
},
{
"hi": 1.0092343435725986,
"lo": 0.9922852873631642,
"median": 1.0034947624362798
},
{
"hi": 1.0125833696661481,
"lo": 0.9858629698133391,
"median": 0.9945866155256149
},
{
"hi": 1.0322221482398073,
"lo": 0.9951458973996147,
"median": 1.0075699560145404
},
{
"hi": 1.009761041226371,
"lo": 0.9898464904505755,
"median": 0.998425451880562
},
{
"hi": 1.016631057133635,
"lo": 0.9805588949385654,
"median": 0.997950429996102
},
{
"hi": 1.0200791563569052,
"lo": 0.9873713898804045,
"median": 1.000136749596359
}
],
"acceptance": {
"detection_ge": 0.95,
"fp_lt": 0.05,
"pass": true
},
"env_fingerprint": {
"aslr": "mode=system-default randomize_va_space=2",
"cpu_model": "Intel(R) Xeon(R) Processor @ 2.80GHz",
"cpu_pinning": "caller-provided (wrap cmd in taskset)",
"governor": "unknown",
"kernel": "6.18.5",
"smt": "0",
"turbo": "unknown"
},
"injected_busy_wait_s": 0.011125513,
"injected_slowdown": 0.05,
"injection_detection_rate": 0.95,
"injection_sessions": [
{
"hi": 0.9705730747977983,
"lo": 0.9384443885194832,
"median": 0.9570129481885624
},
{
"hi": 0.9691260796731174,
"lo": 0.9309798719977085,
"median": 0.9411908680460361
},
{
"hi": 0.9775705854771548,
"lo": 0.9464129998680949,
"median": 0.9569584325473247
},
{
"hi": 0.9738958239067871,
"lo": 0.9490577184781656,
"median": 0.9624758687422929
},
{
"hi": 0.9692636780671424,
"lo": 0.9448230573540036,
"median": 0.9611951204744579
},
{
"hi": 0.960038069546381,
"lo": 0.9412872028306517,
"median": 0.953204396987671
},
{
"hi": 0.970357721583405,
"lo": 0.9312571815624449,
"median": 0.9497958159533386
},
{
"hi": 1.0189632738942447,
"lo": 0.8979330813534421,
"median": 0.9650177023489201
},
{
"hi": 0.9715620167742915,
"lo": 0.9336764011030461,
"median": 0.9512964417642272
},
{
"hi": 0.9768953182714468,
"lo": 0.9385015313970146,
"median": 0.9538566142021077
},
{
"hi": 0.9733246543232819,
"lo": 0.9452506173210715,
"median": 0.9558422793746748
},
{
"hi": 0.968562587511655,
"lo": 0.9364861001420586,
"median": 0.9461689697819208
},
{
"hi": 0.9832173753801465,
"lo": 0.9352025813901989,
"median": 0.9618202496291594
},
{
"hi": 0.9701329322900167,
"lo": 0.9395861281724339,
"median": 0.954612721677948
},
{
"hi": 0.9921703664327655,
"lo": 0.9357083455043089,
"median": 0.958758177852707
},
{
"hi": 0.976082080482069,
"lo": 0.9328145868694007,
"median": 0.947453955805073
},
{
"hi": 0.9795318432851117,
"lo": 0.9317744456440425,
"median": 0.9607784721426458
},
{
"hi": 0.9751440256938523,
"lo": 0.9491637711903045,
"median": 0.9646173778660493
},
{
"hi": 0.9730959153169779,
"lo": 0.928638531103063,
"median": 0.9490375911197446
},
{
"hi": 0.9630989374168489,
"lo": 0.9484798599580982,
"median": 0.9548094809061651
}
],
"runs_per_side": 30,
"sessions": 20,
"threshold": 0.02,
"workload_cmd": "taskset -c 2 sh -c 'targets/comrak/workspace/target/release/comrak < corpora/comrak/progit.md > /dev/null'"
}