AI-Atlas score
| Machine Learning | 71 |
|---|---|
| Computer Vision | 63 |
| Data Science | 63 |
| NLP & LLMs | 69 |
| AI Agents | 59 |
| MLOps | 37 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Deep, repeated, well-engineered work in this domain.
23 public repositories → 9 with AI work, evaluated. The other 14 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
22% of Atlas Score
The repository presents a machine learning study to characterize FIB-4 false negatives in MASLD using NHANES data, employing XGBoost, SHAP, clustering, and LLMs to identify phenotypes and develop an improved triage score (FIB-4 Plus).
18% of Atlas Score
LUFY is a web application that processes legal documents to provide plain-language summaries, risk assessments, and question-answering in multiple Indian languages using a RAG-based pipeline with map-reduce for long documents.
16% of Atlas Score
Schema Surgeon is an agent system for NoSQL schema correction, providing an environment where a language model agent can learn to fix schema drift using actions like renaming keys and casting types. It includes three progressively difficult tasks, a dense reward function, and a baseline LLM agent for evaluation.
14% of Atlas Score
This repository provides a browser-based application that estimates heart rate and heart-rate variability from a webcam using remote photoplethysmography (rPPG). It implements signal processing pipelines for extracting blood volume pulse signals and computing HRV metrics, with optional blood pressure estimation via a user-provided TensorFlow.js model.
12% of Atlas Score
Patch Sloth is an end-to-end machine learning application that scans lockfiles for deferred CVEs and provides a second-opinion severity score using fine-tuned LLMs and TabPFN models, accompanied by a CLI, API, and deployment instructions.
12% of Atlas Score
The repository investigates shortcut learning in multimodal skin lesion classification by training and evaluating image-only, metadata-only, and fusion models, and running experiments to assess reliance on demographic shortcuts. It includes data preprocessing, model definitions, training loops, evaluation metrics, and multiple experiment scripts for analysis.
