Qwen3-8B · scored

n-gram k=4

reference ngram judged submitted 10-23 07:59 UTC

Passed every gate.

SpecScore0.720geometric mean of the three speedups
solo1.00× one lane; passes 1.19, 1.00, 1.00
team0.62× team lanes busy; passes 0.62, 0.62, 0.59
busy0.60× KV cache nearly full; passes 0.54, 0.60, 0.63
CheckMeasuredLimit
device memory161.5 GiB≤ 165.2 GiB pass
fixed texts' log-probabilities3.3e-07≤ 0.002 pass
sampled replies' likelihood+0.0392 ± 0.0812within ±0.05 at 95% pass
share of first choices-0.0074 ± 0.0150within ±0.01 at 95% pass
greedy agreement0.740none on this task n/a
reply lengths–1 ± 0.05 at 95% pass

Speculation

WorkloadTokens / verify stepSpeedup
solo2.33 1.00
team2.43 0.62
busy2.44 0.60

Speculator: none
Engine: uploaded with the submission

Everything the judge recorded
{
 "ratios": {
  "solo": {
   "passes": [
    1.1934449624614578,
    1.001766468977475,
    1.0012664311932673
   ],
   "ratio": 1.001766468977475
  },
  "team": {
   "passes": [
    0.6172850794680307,
    0.6174045149548547,
    0.5913725759674164
   ],
   "ratio": 0.6172850794680307
  },
  "busy": {
   "passes": [
    0.5418338302107005,
    0.602366329580096,
    0.6329814517356719
   ],
   "ratio": 0.602366329580096
  }
 },
 "specscore": 0.7195113562489343,
 "greedy_agreement": 0.7400580900033107,
 "likelihood": {
  "gap": 0.03917950649813606,
  "se": 0.04142438583557324,
  "candidate": -0.6164535506322344,
  "stock": -0.6556330571303705
 },
 "argmax": {
  "gap": -0.0073887426227801645,
  "se": 0.007656700331747197,
  "candidate": 0.13499154561524865,
  "stock": 0.1423802882380288
 },
 "fidelity": 3.265787269074265e-07,
 "lengths": {
  "solo": {
   "ratio": 1.088491195872755,
   "low": 0.828372359272078,
   "high": 1.348610032473432
  },
  "team": {
   "ratio": 1.109877461242377,
   "low": 0.9317822237661488,
   "high": 1.2879726987186049
  },
  "busy": {
   "ratio": 0.8995692216280452,
   "low": 0.7887977286143495,
   "high": 1.010340714641741
  }
 },
 "memory": {
  "ok": true,
  "peak_mib": 165336.0,
  "allowed_mib": 169119.1
 },
 "acceptance": {
  "solo": 2.325990090186433,
  "team": 2.4261414900383085,
  "busy": 2.4418770169742703
 },
 "limits": {
  "greedy_agreement_floor": null,
  "likelihood_bound": 0.05,
  "argmax_bound": 0.01,
  "fidelity_ceiling": 0.002,
  "length_margin": 0.05,
  "memory_slack_mib": 4096
 },
 "reason": null,
 "score": 0.7195113562489343
}