A real-world deployment of the COACH prompting system
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The loss of cognition associated with dementia affects an individual's ability to participate in even the most fundamental activities of daily living (ADL). Assistive technology for cognition (ATC) has shown potential to support ADL completion, but few devices have undergone real-world deployments. The COACH is an existing ATC that has been shown in supervised trials to support older adults with dementia through the ADL of hand washing. This paper presents the results of a study of the COACH in a long-term, real-world, community-based deployment. The COACH was installed in a washroom at the Toronto Memory Program. The COACH was configured to run in an unsupervised state, interacting with users when they were not progressing through the task. Video was collected from an overhead camera, and was manually annotated to determine the system's capabilities. The trials were conducted from February to May, 2012. Twenty participants contributed forty-one hand washing trials. Results suggest that the COACH was able to identify completed task steps with 46.6% accuracy and the participants' true performance with 54.9% accuracy. This study clarifies the need for more robust, accurate and generalized user tracking, including the use of three-dimensional tracking, gesture, grip and rotation detection.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it