Metraipolis › archive › dc_5ce7a27217bd

Fluency Without Evidence: Constraint-First Design and the Limits of Self-Report in AI-Assisted Learning — arXiv:2609.37880

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37880
License (as archived)
CC0-1.0
Archived
2026-10-07T17:27:41.660Z
SHA-256 of the archived text
ebb5131cba16c90cabac606075af9ec106300fe0ad3a2915d4f61ef665ad29bc
Stable URL of this page
https://metraipolis.com/documento/dc_5ce7a27217bd

How to cite

Fluency Without Evidence: Constraint-First Design and the Limits of Self-Report in AI-Assisted Learning — arXiv:2609.37880 — arXiv (en), https://arxiv.org/abs/2609.37880 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ce7a27217bd (Metraipolis archive dc_5ce7a27217bd, sha256 ebb5131cba16c90cabac606075af9ec106300fe0ad3a2915d4f61ef665ad29bc)
BibTeX
@misc{dc5ce7a27217bd,
  title = {Fluency Without Evidence: Constraint-First Design and the Limits of Self-Report in AI-Assisted Learning — arXiv:2609.37880},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37880},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ce7a27217bd; sha256 ebb5131cba16c90cabac606075af9ec106300fe0ad3a2915d4f61ef665ad29bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37880. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A generative AI teaching partner should support reasoning over supplying conclusions; however, this has not been tested against learning in an authentic course. Drawing on design-based research, we specify the position as a conjecture map and report a first design cycle in two graduate-level research methods courses. Students used an AI teaching partner employing a constraint-first sequence requiring them to state and justify positions before receiving questions. Pre- and post-measures of AI literacy, critical thinking, and metacognitive awareness were collected alongside interaction records. AI literacy increased, concentrating in understanding AI, whereas critical thinking, awareness, and knowledge did not change. Since changes were limited to self-report measures, they may reflect growth in confidence instead of capacity. Interaction records, meanwhile, showed brief exchanges, uneven enactment of the constraint-first sequence, and missing records. These findings show why AI-supported learning requires interaction records to provide a more defensible basis for AI-supported designs than self-reports.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.37880 — 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 2026-10-07T16:58:50.341Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).