Metraipolis › archive › dc_e4db88a2bbc5

ScAn-Bench: Evaluating Scaling Analysis Methodology — arXiv:2609.35707

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35707
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:19.686Z
SHA-256 of the archived text
15c3e01b0955c0253d69c7ce17bf72cac6fff0f167cbe1d548b8b2553736390e
Stable URL of this page
https://metraipolis.com/documento/dc_e4db88a2bbc5

How to cite

ScAn-Bench: Evaluating Scaling Analysis Methodology — arXiv:2609.35707 — arXiv (en), https://arxiv.org/abs/2609.35707 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e4db88a2bbc5 (Metraipolis archive dc_e4db88a2bbc5, sha256 15c3e01b0955c0253d69c7ce17bf72cac6fff0f167cbe1d548b8b2553736390e)
BibTeX
@misc{dce4db88a2bbc5,
  title = {ScAn-Bench: Evaluating Scaling Analysis Methodology — arXiv:2609.35707},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35707},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e4db88a2bbc5; sha256 15c3e01b0955c0253d69c7ce17bf72cac6fff0f167cbe1d548b8b2553736390e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35707. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent progress in machine learning is driven by large-scale foundation models, where scaling laws and finding optimal scaling prescriptions for architecture, data, and hyperparameters are key in advancing the state-of-the-art. Therefore, it is surprising that no systematic study evaluates the methodology to obtain scaling laws and prescriptions across different model types. To shed light on this crucial blind spot and facilitate future research, we introduce the surrogate benchmarks ScAn-Bench-LLM and ScAn-Bench-VLM based on 4524 and 8024 checkpoints of language and vision-language model pipelines. On our benchmarks, we perform the first systematic evaluation of both data acquisition and extrapolation methodology for scaling analysis across different data modalities.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35707 — 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 2026-10-07T22:14:28.505Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).