Metraipolis › archive › dc_253bf0b68e42

Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions — arXiv:2609.14917

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14917
License (as archived)
CC0-1.0
Archived
2026-10-15T23:17:10.551Z
SHA-256 of the archived text
d1692dbfe83434454994296a43c457aa4c46cbd5b2c408ef38e06bdd6d4f2241
Stable URL of this page
https://metraipolis.com/documento/dc_253bf0b68e42

How to cite

Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions — arXiv:2609.14917 — arXiv (en), https://arxiv.org/abs/2609.14917 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_253bf0b68e42 (Metraipolis archive dc_253bf0b68e42, sha256 d1692dbfe83434454994296a43c457aa4c46cbd5b2c408ef38e06bdd6d4f2241)
BibTeX
@misc{dc253bf0b68e42,
  title = {Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions — arXiv:2609.14917},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14917},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_253bf0b68e42; sha256 d1692dbfe83434454994296a43c457aa4c46cbd5b2c408ef38e06bdd6d4f2241},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14917. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce document embedding geometry as a quantitative observable of conceptual reorganization and develop a counterfactual ablation framework for measuring how individual concepts influence the organization of scientific knowledge, providing a quantitative framework for detecting scientific revolutions. The observable is defined by the geometric perturbation induced when removing documents associated with a candidate concept from the embedding space before and after its historical emergence. Statistical validation is performed using five historical case studies spanning physics, mathematics, and machine learning: special relativity, Gödel's incompleteness theorems, the Higgs mechanism, deep learning, and the attention mechanism underlying transformer architectures. Across the historical case studies, the framework identifies measurable geometric signatures associated with conceptual reorganization, while the validation studies expose important limitations arising from document assignment and sparse historical data. These results establish embedding geometry as a medium for quantifying conceptual reorganization, providing a new approach for studying how scientific fields restructure over time.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Digital Libraries (cs.DL) ; Computation and Language (cs.CL); Machine Learning (cs.LG); History and Philosophy of Physics (physics.hist-ph); Physics and Society (physics.soc-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.14917 — 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 2026-10-15T22:51:10.030Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).