Metraipolis › archive › dc_ca24e262a3d2
Measuring the collaboration, not the agent — arXiv:2611.06487
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06487
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:21:24.311Z
- SHA-256 of the archived text
9f949b3c6f77946d1ebe6b3e51f8ac6992f6ce546e0328d22b15816fee7f9192- Stable URL of this page
https://metraipolis.com/documento/dc_ca24e262a3d2
How to cite
Measuring the collaboration, not the agent — arXiv:2611.06487 — arXiv (en), https://arxiv.org/abs/2611.06487 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca24e262a3d2 (Metraipolis archive dc_ca24e262a3d2, sha256 9f949b3c6f77946d1ebe6b3e51f8ac6992f6ce546e0328d22b15816fee7f9192)
BibTeX
@misc{dcca24e262a3d2,
title = {Measuring the collaboration, not the agent — arXiv:2611.06487},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06487},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca24e262a3d2; sha256 9f949b3c6f77946d1ebe6b3e51f8ac6992f6ce546e0328d22b15816fee7f9192},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06487. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Benchmarks for visualization agents score the agent alone; the human only supplies reference answers. For high-dimensional data this misses what matters: the knowledge of which variables count is held by on-site experts, not by the model, so the useful question is how well an analyst and an agent do together. We study one specific form of collaboration, the agent proposes a view, the analyst accepts, rejects, or modifies it, and those judgments are kept for later sessions, and propose five measures for it: complementarity, intervention efficiency, appropriate reliance, knowledge retention, and agency. The first four are computed from interaction logs alone. We test the measures, not people: in a testbed for parallel-coordinates design on public manufacturing data (UCI SECOM), with a simulated analyst whose behavior we control, all four are computable and respond to the controlled differences. Whether they reveal anything about real analysts is the next step; we release the testbed for it. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2611.06487 — 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 2026-11-05T18:15:33.981Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).