Quality Assessment and Accessibility Mapping in an Image-Based Geocrowdsourcing Testbed
Bibliographic record
Abstract
Geocrowdsourcing is a significant new focus area in mapping for people with disabilities. It utilizes public data contributions that are difficult to capture with traditional mapping workflows. Along with the benefits of geocrowdsourcing are critical drawbacks, including reliability and accuracy. A geocrowdsourcing testbed has been designed to explore the dynamics of geocrowdsourcing and quality assessment and produce temporally relevant navigation obstacle data. These reports are then used for route planning, obstacle avoidance, and spatial awareness. Recently, the geocrowdsourcing testbed has been modified to focus on the contribution of images and short descriptions, rather than the more lengthy previous reporting process. The quality assessment workflow of the geocrowdsourcing testbed is contrasted with a modified quality assessment workflow, implemented in the simpler and quicker image-based reporting paradigm. General quality assessment of data position and temporal characteristics is still possible, while general data attributes and detail are now supplied by a moderator from the contributed image. The derivation of obstacle location from multiple intersected image direction vectors does not produce reliable results, but an approach using buffered convex hulls works dependably. This simpler, quicker geocrowdsourcing workflow produces geocrowdsourced obstacle data and quality assessment estimates for location, time, and attribute accuracy.
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 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 | 0.007 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".