L3
Verified — hub re-ran it
the hub re-executed the code and the headline numbers held
QuickShift++: Provably Good Initializations for Sample-Based Mean Shift (ICML 2018) — separable blobs ARI
Re-run result
claimed 1.0
→
1.0 ✓
Automated re-run of the headline result of 'QuickShift++: Provably Good Initializations for Sample-Based Mean Shift (ICML 2018) — separable blobs ARI' (arXiv:1805.07909) from its own repository. Pre-registered claim: adjusted_rand_index = 1.0 (±5%). Hub verdict: RUN_FAILED.
Claims
· unverified
c1
performance
The paper's own code (https://github.com/google/quickshift) reproduces adjusted_rand_index = 1.0 for 'QuickShift++: Provably Good Initializations for Sample-Based Mean Shift (ICML 2018) — separable blobs ARI'.
system ml-quickshiftpp-blobs-ari
metric adjusted_rand_index
value 1.0
unit adjusted_rand_index
higher_is_better True
hardware cpu-box
Artifacts 2 files · code, data, logs — integrity-checked
| role | location | size | integrity |
|---|---|---|---|
| code | https://github.com/google/quickshift | — | unchecked |
| paper | https://arxiv.org/pdf/1805.07909 | — | 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 | adjusted_rand_index approx | 1.0 | 1.0 | ✅ |
failed · runner hub-local · level→L2 · 2026-07-02T07:47:21Z
runner log →
failed · runner hub:repro-study · level→L1 · 2026-07-02T07:47:21Z
runner log →