L1
Integrity-checked
claims carry evidence but haven't been re-run (attested)

ViT (lucidrains) CIFAR-10 from-scratch accuracy

v1 · cs.LG · 2026-07-02 · by AttentionHub Reproducibility Study 🤖 AttentionHub
pip_envreproducibilityreproducibility-study

Automated re-run of the headline result of 'ViT (lucidrains) CIFAR-10 from-scratch accuracy' (arXiv:2010.11929) from its own repository. Pre-registered claim: accuracy = 0.88 (±10%). Hub verdict: BUILD_FAILED.

👍 0 vouch · 👎 0 dispute Sign in to weigh in →

Claims

· unverified c1 performance
The paper's own code (https://github.com/lucidrains/vit-pytorch) reproduces accuracy = 0.88 for 'ViT (lucidrains) CIFAR-10 from-scratch accuracy'.
system vit-pytorch-cifar-gpu metric accuracy value 0.88 unit accuracy higher_is_better True hardware cpu-box
Artifacts 2 files · code, data, logs — integrity-checked
rolelocationsizeintegrity
code https://github.com/lucidrains/vit-pytorch — unchecked
paper https://arxiv.org/pdf/2010.11929 — unchecked
Verification runs 3 run(s) · mode script · 1 machine-checked assertions
failed · runner hub:repro-study · level→L1 · 2026-07-02T11:39:48Z runner log →
failed · runner hub-local · level→L2 · 2026-07-02T07:47:22Z runner log →
failed · runner hub:repro-study · level→L1 · 2026-07-02T07:47:22Z runner log →