Metraipolis › archive › dc_6b2be28cdcee

Do Machine Learning Models Predict? — arXiv:2611.12332

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.12332
License (as archived): CC0-1.0
Archived: 2026-11-10T18:44:03.442Z
SHA-256 of the archived text: 11e5c33b69443384bc3bec939e88cf894035a71ebe0f65e37c8c94bd7d5423f5
Stable URL of this page: https://metraipolis.com/documento/dc_6b2be28cdcee

How to cite

Do Machine Learning Models Predict? — arXiv:2611.12332 — arXiv (en), https://arxiv.org/abs/2611.12332 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b2be28cdcee (Metraipolis archive dc_6b2be28cdcee, sha256 11e5c33b69443384bc3bec939e88cf894035a71ebe0f65e37c8c94bd7d5423f5)

BibTeX

@misc{dc6b2be28cdcee,
  title = {Do Machine Learning Models Predict? — arXiv:2611.12332},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12332},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b2be28cdcee; sha256 11e5c33b69443384bc3bec939e88cf894035a71ebe0f65e37c8c94bd7d5423f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12332. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Machine learning (ML) models are said to predict. Philosophers draw a line between accommodation and prediction, depending on whether or not the evidence a theory succeeds on was used in constructing it. Does this distinction survive when a theory is replaced by an ML model? We argue so, yet the dividing line becomes fuzzy. Whether an output of an ML model counts as an accommodation or as a prediction hinges upon the relationship between the patterns the input instantiate and those on which the model was selected through its training. Once this relation is taken into account, most successful outputs of ML models, we suggest, bear a strong accommodation character. We further trace the consequences of our account for confirmation, novelty, and scientific realism.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.12332 — 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 2026-11-10T18:37:37.689Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).