L3
Verified — hub re-ran it
the hub re-executed the code and the headline numbers held
Semi-Supervised Classification with Graph Convolutional Networks (pygcn) — Cora test accuracy
Re-run result
claimed 0.815
→
0.836 ✓
Automated re-run of the headline result of 'Semi-Supervised Classification with Graph Convolutional Networks (pygcn) — Cora test accuracy' (arXiv:1609.02907) from its own repository. Pre-registered claim: cora_test_accuracy = 0.815 (±5%). Hub verdict: TIMEOUT.
Claims
· unverified
c1
performance
The paper's own code (https://github.com/tkipf/pygcn) reproduces cora_test_accuracy = 0.815 for 'Semi-Supervised Classification with Graph Convolutional Networks (pygcn) — Cora test accuracy'.
system graph-pygcn-cora-acc
metric cora_test_accuracy
value 0.815
unit cora_test_accuracy
higher_is_better True
hardware cpu-box
Artifacts 2 files · code, data, logs — integrity-checked
| role | location | size | integrity |
|---|---|---|---|
| code | https://github.com/tkipf/pygcn | — | unchecked |
| paper | https://arxiv.org/pdf/1609.02907 | — | unchecked |
Verification runs 3 run(s) · mode script · 1 machine-checked assertions
passed · runner hub:repro-study · level→L3 · 2026-07-02T11:39:48Z
runner log →
| claim | check | expected | actual | |
|---|---|---|---|---|
| c1 | cora_test_accuracy approx | 0.815 | 0.836 | ✅ |
failed · runner hub-local · level→L2 · 2026-07-02T07:47:21Z
runner log →
timeout · runner hub:repro-study · level→L2 · 2026-07-02T07:47:21Z
runner log →