Supplemental Information for: Overcoming the laws-in-translation problem: Comparing techniques to translate legal texts
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 benefits of computerized translations are their speed, accessibility, and cost. The risk is whether they are sufficiently precise for a given need. This note assesses the options available to translate legal text for socio-legal research. We evaluate three tools—DeepL, Google, Microsoft—and assess each one’s ability to translate similar legal content enacted by the Brazilian, Chinese, French, Japanese, and Mexican governments. We demonstrate that machine translators are reliable and effective, particularly at higher levels of generality. They are fallible, however, and each is prone to making critical errors that may jeopardize research. We show that employing human translators to edit automated translations produces high-quality translations in one-third the time and at a fraction of the cost. This methodological contribution promises to enrich socio-legal research by establishing a translation protocol that is affordable, rigorous yet simple, and transparent. We propose that scholars use this method for comparative socio-legal research.
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 | 0.002 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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