IMAGE: An Open-Source, Extensible Framework for Deploying Accessible Audio and Haptic Renderings of Web Graphics
Bibliographic record
Abstract
For accessibility practitioners, creating and deploying novel multimedia interactions for people with disabilities is a nontrivial task. As a result, many projects aiming to support such accessibility needs come and go or never make it to a public release. To reduce the overhead involved in deploying and maintaining a system that transforms web content into multimodal renderings, we created an open source, modular microservices architecture as part of the IMAGE project. This project aims to design richer means of interacting with web graphics than is afforded by a screen reader and text descriptions alone. To benefit the community of accessibility software developers, we discuss this architecture and explain how it provides support for several multimodal processing pipelines. Beyond illustrating the initial use case that motivated this effort, we further describe two use cases outside the scope of our project to explain how a team could use the architecture to develop and deploy accessible solutions for their own work. We then discuss our team’s experience working with the IMAGE architecture, informed by discussions with six project members, and provide recommendations to other practitioners considering applying the framework to their own accessibility projects.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.013 | 0.007 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".