Classifying Restatements: An Application of Machine Learning and Textual Analytics
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 Restatements of audited financial statements are used for evaluating reporting quality and audit quality, and for other evaluative purposes. We constructed a machine learning algorithm to classify restatements by management intent based on the language in restatement announcements. Our machine learning classification is as reliable as other commonly used automated methods such as those based on market reaction, restatement direction, and magnitude. Our method does not require a dictionary of words and is applicable when other automated methods are not, for example, when restatements are announced contemporaneously with financial results and when net income is not restated. For large samples, the use of such a classification algorithm is less tedious and less time-consuming, and more consistent, replicable, and scalable than manual classification. Data Availability: Data are available from public sources cited in the text. JEL Classifications: G38; M41; M42; M48.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.004 |
| 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 it