Research on the Review and Processing of Evidence for Public Interest Litigation Based on Computer Vision Technology
Bibliographic record
Abstract
This paper analyzes public interest litigation and its salient features, and organizes the audit rules for the electronic transformation of litigation evidence.Aiming at the phenomenon of varying text length in litigation evidence, a joint CTC-Attention decoding model (HCADecoder) based on bigram hybrid labeling is proposed.Based on the existing research on computer vision technology for target number prediction, the stacked object occlusion problem existing in special scenes is proposed, and an algorithm for predicting the number of stacked objects combining planar density map and depth map is proposed.Combined with the public interest litigation evidence document corpus dataset, we analyze the recognition of basic elements of litigation evidence by text label recognition algorithm, and select the commonly used precision rate P, recall rate R and F1 value to evaluate the recognition results of basic elements.Subdivide the text length of litigation evidence and analyze the recognition accuracy of each algorithm on different text lengths.Bring the text label recognition algorithms into real cases to analyze the element extraction.For this paper, we propose monocular image target counting algorithm, which is brought into different scenarios for performance testing.This paper proposes text label recognition algorithm with evidence image target counting algorithm for litigation evidence text image recognition with mean value at 80%.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".