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

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

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

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
rolelocationsizeintegrity
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
claimcheckexpectedactual
c1cora_test_accuracy approx0.8150.836
runner log →
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 →