Metraipolis › archive › dc_e0879e47df43

Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench — arXiv:2611.03727

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03727
License (as archived)
CC0-1.0
Archived
2026-11-04T18:53:44.957Z
SHA-256 of the archived text
89e2e5196f25b2f0bc0257971d7e69a26203c93138811c29f3a01215841c34c8
Stable URL of this page
https://metraipolis.com/documento/dc_e0879e47df43

How to cite

Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench — arXiv:2611.03727 — arXiv (en), https://arxiv.org/abs/2611.03727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0879e47df43 (Metraipolis archive dc_e0879e47df43, sha256 89e2e5196f25b2f0bc0257971d7e69a26203c93138811c29f3a01215841c34c8)
BibTeX
@misc{dce0879e47df43,
  title = {Auditing a Model-Hub Benchmark: Data Quality, Training Budgets, and Side Information in HuggingBench — arXiv:2611.03727},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03727},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0879e47df43; sha256 89e2e5196f25b2f0bc0257971d7e69a26203c93138811c29f3a01215841c34c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Benchmarks built from model hubs combine interaction data, knowledge graphs (KGs) and resource documentation, but valid files do not ensure that these artifacts describe the same objects. Treating the release as a data product, we audit HuggingBench (SIGIR 2025), a benchmark for recommending Hugging Face resources, through data validation, a replication of its eleven recommendation methods and controlled experiments with three training seeds. In three of its four external KGs, the files pass key and range checks but violate the item-entity identity constraint on which KG recommenders rely. Correcting this join improves every KG-based method in every seed, by up to 73% in mean Recall@10, and consistently reverses ten of 27 comparisons between KG configurations. The protocol matters as well: the 100-epoch budget ends before early stopping in seven to eight of 29 validation-selected settings, and 21 of 23 such setting-seed pairs improve with a longer budget. The released item text, which no reported method uses, is the strongest signal: closed-form linear models with text and the item graph exceed the best reported Recall@10 by 18% while fitting in minutes on a CPU. Checks of other recommendation releases show that individually valid releases of one dataset can use incompatible identifiers. We release corrected files, mappings, validators and logs, and derive practices for preserving identity and provenance across the artifacts of benchmarks and model lakes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03727 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:35:37.387Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).