MétaCan
Menu
Back to cohort
Record W4400508625 · doi:10.1002/wfs2.1528

Forensic intelligence: Expanding the potential of forensic document examination

2024· article· en· W4400508625 on OpenAlexaffabout
Ciara Devlin, Marie Morelato, Simon Baechler

Bibliographic record

VenueWiley Interdisciplinary Reviews Forensic Science · 2024
Typearticle
Languageen
FieldComputer Science
TopicDigital and Cyber Forensics
Canadian institutionsUniversité du Québec à Trois-Rivières
Fundersnot available
KeywordsHandwritingForensic scienceForensic examinationForensic identificationIdentification (biology)Crime sceneCriminal investigationIntelligence analysisComputer scienceField (mathematics)Data sciencePsychologyArtificial intelligenceCriminologyComputer securityForensic engineeringEngineeringHistoryArchaeology

Abstract

fetched live from OpenAlex

Abstract Forensic document examination is characterized by its longevity, diversity, and evolution over time. Predominantly, published research within this field has focused on handwriting examination, the articulation of forensic conclusions, and the development of technical instrumental advancements, focusing on the use of document examination in the resolution of casework. This is a persistent and common problem within forensic science that Kirk identified in 1963 and that other authors have reaffirmed more recently. Ultimately, this has resulted in the potential of forensic intelligence, remaining relatively underexplored in the field of document examination. Forensic intelligence is a different way to view and analyze traces, shifting the focus from the traditional identification of source and activity, to instead identifying trends in criminal activity to assist in the reduction, prevention, and proactive disruption of crime. Despite a distinct disparity between these strands of research, there has been a persevering evolution toward the implementation of a systematic forensic intelligence method for the examination of fraudulent identity documents. Since its initial inception into the research community, this method has expanded and been implemented across Europe, and Canada, with tests also being conducted in Australia. These first tangible steps toward a forensic intelligence capacity within document examination have also inspired new work using forensic intelligence and systematic comparisons within the field of handwriting examination, as well as the recognition of the transversal potential of this method, with it being applied to both physical and digital documents. In this review, the fields of document examination and forensic intelligence will first be introduced, along with a subsequent examination of the research that has led to the creation of a forensic intelligence model within the field of document examination. It should be noted that this review has largely been limited to a review of research that has been published in English and French due to the language of the authors. This article is categorized under: Crime Scene Investigation > From Traces to Intelligence and Evidence Forensic Chemistry and Trace Evidence > Emerging Technologies and Methods Crime Scene Investigation > Epistemology and Method

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 imitation

Not 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.

metaresearch head score (Codex)0.010
metaresearch head score (Gemma)0.017
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.010
Threshold uncertainty score0.054

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.017
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0060.003
Science and technology studies0.0010.006
Scholarly communication0.0070.010
Open science0.0020.005
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0050.002

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.

Opus teacher head0.023
GPT teacher head0.310
Teacher spread0.287 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

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".

Quick stats

Citations7
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueWiley Interdisciplinary Reviews Forensic ScienceSame topicDigital and Cyber ForensicsFrench-language works237,207