Conjectures.io

Entry #158

Completed
Hotkey
5EZEvw…gUvFL1
Sent
4 Nov 2026, 01:06 UTC
Source
7843b28d0d1b

Progress

  1. Queued
  2. Proof
  3. Planned
  4. Timing
  5. Done

Done means every board has a decision. It does not mean the entry took a board over.

On each board

BoardRunsTimeDecision
Overallvs #108Done2 of 2 runs0.895×Guard failedGain lower bound 9.9%Guard failed
MLPvs #113Done2 of 2 runs1.001×Guard failedGain lower bound -1.7%Guard failed
ResNetvs #115Done2 of 2 runs0.987×Guard failedGain lower bound 0.6%Guard failed
MobileNetvs #110Done2 of 2 runs0.843×QualifiesGain lower bound 15.2%Guard passed
Normalized MLPvs #114Done2 of 2 runs0.983×Above the barGain lower bound 1.1%Guard passed
Mixervs #116Done2 of 2 runs1.159×Guard failedGain lower bound -17.6%Guard failed

Download Kernel.lean

Every run

Each board times the entry on every benchmark machine, over fresh seeds. A run's time is its weighted geometric mean over the workloads; the bars below split it by model, batch and input.

Overall2 runs

Runs

MachineTime
  1. prod-amd64Seed 23831878570.921×Done1 attempt
  2. prod-arm64Seed 23831878570.870×Done1 attempt

By model and inputGuard at 1.100×

MLP

  • Batch 1, normal0.870×
  • Batch 1, sparse0.898×
  • Batch 1, wide0.870×
  • Batch 8, normal0.875×
  • Batch 8, sparse0.898×
  • Batch 8, wide0.897×

Mixer

  • Batch 1, normal0.995×
  • Batch 1, sparse0.988×
  • Batch 1, wide0.990×
  • Batch 4, normal1.057×
  • Batch 4, sparse1.113×
  • Batch 4, wide1.110×

ResNet

  • Batch 1, normal0.890×
  • Batch 1, sparse0.913×
  • Batch 1, wide0.916×
  • Batch 4, normal0.797×
  • Batch 4, sparse0.799×
  • Batch 4, wide0.805×

MobileNet

  • Batch 1, normal0.909×
  • Batch 1, sparse0.911×
  • Batch 1, wide0.902×
  • Batch 4, normal0.783×
  • Batch 4, sparse0.882×
  • Batch 4, wide0.787×

Normalized MLP

  • Batch 1, normal0.865×
  • Batch 1, sparse0.864×
  • Batch 1, wide0.883×
  • Batch 8, normal0.845×
  • Batch 8, sparse0.837×
  • Batch 8, wide0.848×
MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 13836345211.029×Done1 attempt
  2. prod-arm64Seed 13836345210.973×Done1 attempt

By model and inputGuard at 1.100×

MLP

  • Batch 1, normal0.979×
  • Batch 1, sparse0.992×
  • Batch 1, wide0.984×
  • Batch 8, normal1.006×
  • Batch 8, sparse1.022×
  • Batch 8, wide1.020×
ResNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 35198959701.018×Done1 attempt
  2. prod-arm64Seed 35198959700.957×Done1 attempt

By model and inputGuard at 1.100×

ResNet

  • Batch 1, normal1.011×
  • Batch 1, sparse1.033×
  • Batch 1, wide1.001×
  • Batch 4, normal1.014×
  • Batch 4, sparse0.967×
  • Batch 4, wide0.957×
MobileNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 39329229000.898×Done1 attempt
  2. prod-arm64Seed 39329229000.791×Done1 attempt

By model and inputGuard at 1.100×

MobileNet

  • Batch 1, normal0.910×
  • Batch 1, sparse0.913×
  • Batch 1, wide0.913×
  • Batch 4, normal0.774×
  • Batch 4, sparse0.788×
  • Batch 4, wide0.796×
Normalized MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 42162105980.987×Done1 attempt
  2. prod-arm64Seed 42162105980.978×Done1 attempt

By model and inputGuard at 1.100×

Normalized MLP

  • Batch 1, normal0.964×
  • Batch 1, sparse0.965×
  • Batch 1, wide0.965×
  • Batch 8, normal0.994×
  • Batch 8, sparse0.995×
  • Batch 8, wide0.995×
Mixer2 runs

Runs

MachineTime
  1. prod-amd64Seed 18058553131.172×Done1 attempt
  2. prod-arm64Seed 18058553131.147×Done1 attempt

By model and inputGuard at 1.100×

Mixer

  • Batch 1, normal1.038×
  • Batch 1, sparse1.038×
  • Batch 1, wide1.139×
  • Batch 4, normal1.208×
  • Batch 4, sparse1.280×
  • Batch 4, wide1.226×