DocuScope Write & Audit as an early feedback machine ingenre-based writing
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
Abstract The recent addition of Write & Audit, to the DocuScope family offers the promise of helping students revise their own texts by providing early feedback before submitting a draft. This potential is examined in the context of proposal writing, a quintessential example of genre writing. Actual standards brought to bear on students’ drafts were developed from a long-standing proposal writing course and applied to a small, stratified sample of proposals in the Michigan Corpus of Upper-level Student Papers (MICUSP). Early feedback focused on the element of proposal themes using Write & Audit’s analysis of topical progression and information focus, and a template for early feedback was developed. The strengths and limitations of Write & Audit as an early feedback machine are examined with the conclusion that it may indeed have the potential to provide early feedback to writers working in specific genres, helping them to see what they have done and what they might still want to do before turning in a draft.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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