Initiative file / Judicial
OIJ–TEC AI research for criminal analysis
Evidence record v2
29 / 31
- Institution
- Judicial Branch
- Editorial classification
- Ecosystem and capabilities
- Initiative type
- Research
- Documented phase
- In development
- Relationship to AI in the source
- Explicit relationship to AI
- Execution evidence
- Confirmed
- First evidence
- Last verified
- Next review: Sep 21, 2026
Documented scope
What it is
Active research and development project between OIJ and the Costa Rica Institute of Technology to create image-recognition, automatic case-categorization and location-based incident-prediction systems using machine learning and deep learning.
Objective stated by the institution
Develop three AI software systems for image recognition, automatic case categorization and location-based incident prediction in support of efforts against organized crime.
Known timeline
Only milestones with an explicit date in the sources or editorial review are shown.
- First evidence
- Latest editorial verification
- Next scheduled review
Evidence reading
Each dimension is assessed separately. Undetermined marks an evidence gap; not applicable means the dimension does not correspond to the documented object.
What is confirmed
- The TEC record lists the project as active from January 1, 2024 through December 31, 2026.
- The three workstreams are image recognition, automatic case categorization and location-based incident prediction.
- Judiciary minutes document loaned equipment for model training and testing, confirming development but not production operation.
What could not be determined
- No evidence was found for production deployment, integration into routine decisions or an operational start date.
- Accuracy, false-positive, external-validation and group-level performance metrics are not published for recognition and prediction.
- No complete public documentation was found on legal basis, data categories, retention, human review or appeal mechanisms.
Documented results
Results are published only when a source traceably attributes them to this initiative.
In March 2025 the Judiciary presented a tattoo-analysis model and described specific-image search as a developed capability.
Evidence matrix
Sources and traceability
Sources state which claims they support, their origin and the date on which they were consulted.
- [1]AI-based systems for recognition, categorization and incident prediction
- Publisher
- Tecnológico de Costa Rica
- Source type
- Official primary source
- Published
- Consulted
Supports: existence · stated objective · execution · AI technique
- [2]Forum on benefits and challenges of AI in judicial work
- Publisher
- Poder Judicial
- Source type
- Official primary source
- Published
- Consulted
Supports: existence · execution · AI technique · reported result
- [3]Minutes on equipment loan for OIJ–TEC project training and testing
- Publisher
- Poder Judicial
- Source type
- Official primary source
- Published
- Consulted
Supports: existence · execution
Open questions
- Did any of the three systems move from research into a pilot or operational use within OIJ?
- What quality, bias, human-review and traceability controls will apply before any investigative use?
Context
This research is distinct from the ENIA commitment attributed to ICE for homicide prediction and from the SUPERCOP police system. No reviewed source supports merging those three initiatives. The record remains ecosystem R&D, not verified operational adoption.
Related projects
Verified adoptionPilot
Verified:
Document classification for debt collection
Judicial Branch pilot plan to automatically classify documents received by the Specialized Debt Collection Court of Pérez Zeledón. The official source confirms the use of artificial intelligence and reports faster case processing.
- Initiative type
- AI system
- Pilot start
Verified adoptionOperational
Verified:
ML model for budget execution forecasting
Machine-learning model used by the Judicial Branch to predict budget execution from its historical behavior. The institution’s 2019 accountability report documents its use and associated savings.
- Initiative type
- AI system
- Operational start
Verified adoptionOperational
Verified:
Anonymization with Nymiz
Artificial-intelligence tool implemented by the Judicial Branch to depersonalize rulings and protect sensitive data. The institution identifies Nymiz as the platform used and documents its application in the process.
- Initiative type
- AI component
- Operational start