DLinear (LTSF-Linear) — ETTh1 horizon-96 MSE (real author training script; CPU/long-train probe)

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

Re-run result

claimed 0.375 → 0.3841443955898285 ✓

Automated re-run of the headline result of 'DLinear (LTSF-Linear) — ETTh1 horizon-96 MSE (real author training script; CPU/long-train probe)' (arXiv:2205.13504) from its own repository. Pre-registered claim: mse_etth1_h96 = 0.375 (±15%). Hub verdict: TIMEOUT.

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

Claims

· unverified c1 performance

The paper's own code (https://github.com/cure-lab/LTSF-Linear) reproduces mse_etth1_h96 = 0.375 for 'DLinear (LTSF-Linear) — ETTh1 horizon-96 MSE (real author training script; CPU/long-train probe)'.

system ts-dlinear-etth1 metric mse_etth1_h96 value 0.375 unit mse_etth1_h96 higher_is_better True hardware cpu-box

Artifacts 2 files · code, data, logs — integrity-checked

role	location	size	integrity
code	https://github.com/cure-lab/LTSF-Linear	—	unchecked
paper	https://arxiv.org/pdf/2205.13504	—	unchecked

Verification runs 3 run(s) · mode script · 1 machine-checked assertions

passed · runner hub:repro-study · level→L3 · 2026-07-02T11:39:48Z

claim	check	expected	actual
c1	mse_etth1_h96 approx	0.375	0.3841443955898285	✅

runner log →

failed · runner hub-local · level→L2 · 2026-07-02T07:47:22Z runner log →

timeout · runner hub:repro-study · level→L2 · 2026-07-02T07:47:22Z runner log →