An Ecologically Valid Approach to Evaluating Online Gatekeepers
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
CAPTCHAs are commonly used as gatekeepers to protect online services from automated bots. Previous CAPTCHA evaluations have solely focussed on whether CAPTCHA challenges are unbreakable by bots but solvable by humans and have ignored a fundamental question: what effect do these gatekeepers have on their human users? Our study proposes a more realistic approach that complements existing CAPTCHA evaluations by measuring CAPTCHA’s effect on the main task that the user wants to complete. Through our experimental setup, we show that failing to correctly answer CAPTCHAs can turn away a significant percentage of legitimate, human users. We also show that these failures have temporary knock-on effects on the quality of tasks that users later perform. Methodologically, our study also reveals limitations of current approaches to batch evaluations of CAPTCHAs that do not accurately capture the effects that ordering and variance in difficulty have on users’ CAPTCHA-solving performance.
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 | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 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