Metraipolis › archive › dc_aa61efcd3642

Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy — arXiv:2609.24470

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.24470
License (as archived): CC0-1.0
Archived: 2026-10-09T22:05:56.753Z
SHA-256 of the archived text: c6ae53b4c67ed8eaaa62114f61ed363b17e9091bdcd3d07bff49b4e57ce721f9
Stable URL of this page: https://metraipolis.com/documento/dc_aa61efcd3642

How to cite

Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy — arXiv:2609.24470 — arXiv (en), https://arxiv.org/abs/2609.24470 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa61efcd3642 (Metraipolis archive dc_aa61efcd3642, sha256 c6ae53b4c67ed8eaaa62114f61ed363b17e9091bdcd3d07bff49b4e57ce721f9)

BibTeX

@misc{dcaa61efcd3642,
  title = {Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy — arXiv:2609.24470},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24470},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa61efcd3642; sha256 c6ae53b4c67ed8eaaa62114f61ed363b17e9091bdcd3d07bff49b4e57ce721f9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24470. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA) response may be paired with a spatial output that guides a downstream stage. A supervisor reads the language answer, while a downstream workflow such as segmentation or region review consumes the point-set output. We call this transition from inspecting the answer to relying on its point action the language-to-action hand-off. A silent failure occurs when the answer is correct while the paired action misses annotated objects needed downstream, so answer-based oversight clears a region whose action is unreliable. We introduce Spatial Action Review, a visual analytics dashboard for auditing this failure mode in electron microscopy (EM) mitochondria analysis. It links paired answer-action records through an answer-action ledger, a task-by-dataset risk map, and an image-region audit view, connecting aggregate patterns to image evidence while an adjustable action-reliability gate supports re-audit. The review ends in a human-AI hand-off, where a supervisor records whether the action is accepted, escalated, held under a stricter gate, or flagged for model revision. Across 541 image regions from an EM-adapted Qwen3-VL case-study run, point actions fail the gate in 54.4% of records with a correct VQA response, and 27.4% of all records are silent failures. A correct answer is associated with only a 5.8-percentage-point higher probability of a reliable action, with a bootstrap interval spanning zero; the point-biserial correlation between answer correctness and object coverage is 0.061. This weak coupling persists across five model conditions on 753 matched image regions. Spatial Action Review makes answer-action mismatches visible and ties them to image evidence and a recorded decision before MLLM outputs enter autonomous scientific workflows.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.24470 — 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 2026-10-09T21:45:21.042Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).