The impact of the ACE-V methodology on the forensic analysis of signatures and manuscripts
Bibliographic record
Abstract
This article examines the impact of the implementation of the so-called ACE-V (analysis, comparison, evaluation, and verification) methodology in the field of forensic analysis of signatures and manuscripts. The key components of ACE-V, its application in signature identification and authorship attribution studies, and its effectiveness in comparison to other methods usually noted in forensic reports and defended in court are explored. Experience suggests that ACE-V provides a structured framework that improves accuracy and consistency in the comparison of signatures and manuscripts, and allows findings to be communicated in due form, to maintain a uniform universal language and to offer a greater degree of reliability in conclusions. The ACE-V methodology is distinguished by its rigorous approach to the evaluation of dynamic and graphical features and its ability to provide a clear framework for comparison, signature verification, and for decision making, which can lead to greater accuracy in approach and a reduction in the number of errors and controversies associated with the analysis of signatures and manuscripts. The first appearance of the ACE-V concept was in a 1959 article by Roy Huber, an examiner of questioned documents of the Royal Canadian Mounted Police, and since then it has been used as a reference in different laboratories and manuals of good practices around the world. The methodological approach improves consistency in the application of the analysis criteria, facilitating a more objective comparison between samples and allowing the validation of findings through interlaboratory consultation with other experts and by means of blind peer review, strengthening the reliability of the result. The documented implementation of ACE-V is justified by its ability to address the shortcomings of less structured methods, which often lack a systematic basis for comparison and evaluation. The methodology not only provides a standardized process that can be replicated and reviewed but also improves reproducibility and transparency in forensic analysis.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.281 | 0.384 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.013 | 0.006 |
| Science and technology studies | 0.005 | 0.017 |
| Scholarly communication | 0.025 | 0.014 |
| Open science | 0.007 | 0.015 |
| Research integrity | 0.004 | 0.009 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".