Metraipolis › archive › dc_a637fef9809f

Reproducible macroscopic dynamics in a closed-loop human-AI learning system — arXiv:2608.30946

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30946
License (as archived)
CC0-1.0
Archived
2026-10-17T08:39:32.034Z
SHA-256 of the archived text
a6529cd6186135a3306319e54b7110567dd2c5e12104aee02018290c613aaebd
Stable URL of this page
https://metraipolis.com/documento/dc_a637fef9809f

How to cite

Reproducible macroscopic dynamics in a closed-loop human-AI learning system — arXiv:2608.30946 — arXiv (en), https://arxiv.org/abs/2608.30946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a637fef9809f (Metraipolis archive dc_a637fef9809f, sha256 a6529cd6186135a3306319e54b7110567dd2c5e12104aee02018290c613aaebd)
BibTeX
@misc{dca637fef9809f,
  title = {Reproducible macroscopic dynamics in a closed-loop human-AI learning system — arXiv:2608.30946},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30946},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a637fef9809f; sha256 a6529cd6186135a3306319e54b7110567dd2c5e12104aee02018290c613aaebd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Closed-loop human-AI systems generate high-dimensional behavioural trajectories whose collective dynamics remain obscure. Using 297,915 learners' adaptive-tutoring histories, we define semantic order variables before model fitting and test them in user-disjoint cohorts. The state exhibits reproducible basin-like flow and operationally defined, state-heterogeneous metastable-like kinetics. A construction-matched null distinguishes normalised-memory relaxation from a reproducible excess field. A four-term conditional mechanism recovers population drift (r = 0.946; learner-bootstrap 95% CI, 0.935-0.955). Predictive event-level self-supervised learning recovers the state and learned-plane flow; null-referenced corrections retain directional, partial-amplitude excess-field structure without full calibration. Shuffled-order training reverses learned-plane flow on ordered trajectories; support-alignment randomisation selectively reduces inward transport. Both axes remain linearly accessible without state supervision. Without cross-model fitting, the models share leading population drift (r = 0.866; learner-bootstrap 95% CI, 0.857-0.875) and persistence ordering; residual directions remain model-specific. These results identify an externally anchored leading-order effective field linking empirical dynamics, an interpretable mechanism and neural computation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Adaptation and Self-Organizing Systems (nlin.AO).
Pagina del lavoro: https://arxiv.org/abs/2608.30946 — 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 2026-10-17T08:13:26.854Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).