Conjectures.io

Entry #36

Completed
Hotkey
5CFUpC…DsFQPa
Sent
29 Oct 2026, 08:52 UTC
Source
595a90fa2b6b

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 #18Done0 of 2 runs-Too slowTimed out after 300 s on one run (prod-amd64)
MLPvs #26Done2 of 2 runs2.551×Guard failedGain lower bound -161.3%Guard failed
ResNetvs #20Done0 of 2 runs-Too slowTimed out after 300 s on one run (prod-amd64)
MobileNetvs #16Done0 of 2 runs-Too slowTimed out after 300 s on one run (prod-amd64)
Normalized MLPvs #24Done0 of 2 runs-Too slowRan out of the shared 360 s budget (prod-amd64)
Mixervs #25Done2 of 2 runs0.962×QualifiesGain lower bound 1.1%Guard passed

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 4070818974-Failed1 attempt
  2. prod-arm64Seed 4070818974-Cancelled1 attempt
MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 39175235642.594×Done1 attempt
  2. prod-arm64Seed 39175235642.509×Done1 attempt

By model and inputGuard at 1.100×

MLP

  • Batch 1, normal2.037×
  • Batch 1, sparse2.942×
  • Batch 1, wide1.879×
  • Batch 8, normal2.484×
  • Batch 8, sparse2.623×
  • Batch 8, wide3.884×
ResNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 112911945-Failed1 attempt
  2. prod-arm64Seed 112911945-Cancelled0 attempts
MobileNet2 runs

Runs

MachineTime
  1. prod-amd64Seed 1490697492-Failed1 attempt
  2. prod-arm64Seed 1490697492-Cancelled0 attempts
Normalized MLP2 runs

Runs

MachineTime
  1. prod-amd64Seed 675289078-Failed1 attempt
  2. prod-arm64Seed 675289078-Cancelled0 attempts
Mixer2 runs

Runs

MachineTime
  1. prod-amd64Seed 15931605310.957×Done1 attempt
  2. prod-arm64Seed 15931605310.967×Done1 attempt

By model and inputGuard at 1.100×

Mixer

  • Batch 1, normal0.939×
  • Batch 1, sparse0.960×
  • Batch 1, wide0.984×
  • Batch 4, normal0.944×
  • Batch 4, sparse0.948×
  • Batch 4, wide0.982×