Application of Artificial Intelligence in the automatic identification and classification repetitive demand resolution incident in the Brazilian Court of Justice
Bibliographic record
Abstract
One of the areas of knowledge with several possibilities for applying artificial intelligence is Law. Recent changes in Brazilian legislation have facilitated the use of information technology resources to streamline the progress and judgment of cases, such as repetitive demand resolution incident (IRDRs). The aim of this paper is to develop and apply an AI method that can identify and relate new lawsuits with consolidated repetitive judgments (IRDRs). The datasets used in this research are judges' repetitive judgment documents, and consolidated in IRDRs. Court documents are transformed into weighted vectors. The construction of the weights in the vector is based on the co-occurrence of the terms, calculated from the combination of the term frequency-inverse document frequency and their similarity in the corpus of the same IRDR. Artificial neural networks are trained with these vectors to recognize whether new lawsuits are related to an IRDR. As the methodology obtained 93% accuracy, 97% precision, and 93% in recall in the simulations, the method can streamline the work of the Court of Justice, seeking to solve society’s conflicts as quickly as possible. Although the method can be used in several scenarios, the simulations were carried out in judicial documents.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".