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

Bag of Tricks for Efficient Text Classification (fastText, Joulin et al.) — AG News accuracy

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

Automated re-run of the headline result of 'Bag of Tricks for Efficient Text Classification (fastText, Joulin et al.) — AG News accuracy' (arXiv:1607.01759) from its own repository. Pre-registered claim: ag_news_accuracy = 92.5 (±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/donghyeonk/fastText1607) reproduces ag_news_accuracy = 92.5 for 'Bag of Tricks for Efficient Text Classification (fastText, Joulin et al.) — AG News accuracy'.
system nlp-fasttext1607-agnews-acc metric ag_news_accuracy value 92.5 unit ag_news_accuracy higher_is_better True hardware cpu-box
Artifacts 2 files · code, data, logs — integrity-checked
rolelocationsizeintegrity
code https://github.com/donghyeonk/fastText1607 — unchecked
paper https://arxiv.org/pdf/1607.01759 — 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 · 2026-07-02T07:47:21Z runner log →
timeout · runner hub:repro-study · level→L2 · 2026-07-02T07:47:21Z runner log →