adversarial-validation
adversarial-validation
A tiny framework to perform adversarial validation of your training and test data.
- 25
- Python
- 4 d ago
ai-feed
A 4-stage adversarial research auditor that fetches papers from arXiv & HuggingFace, extracts claims, and uses DeepSeek-R1 to verify them against raw abstracts.A self-correcting research & paper digest pipeline powered by local LLMs & reasoning agents
- 4
- Python
- 6 mo ago
Woman-in-Data-Science
Use patient health data from MIT's GOSSIS(Global Open Source Severity of Illness Score) to do an experiment, in which we want to evaluate the question of which modeling strategy leads to the most effective predictions.
- 2
- Jupyter Notebook
- 6 y ago
doloop-machine
Distributed Collection, Local Intelligence - Stop LLMs from hallucinating with Kong in the Loop architecture
- 1
- Python
- MIT
- 5 mo ago
Online_Transaction_Fraud_Detection
Train CatBoost & XGBoost on 59K data to predict the probability that an online transaction is fraudulent
- 1
- Jupyter Notebook
- 6 y ago
GhostCoder
The AI coding partner that doesn't trust itself. Local inline code hints, adversarial skeptic validation, full session replays, and dynamic GPU auto-scaling.
- 0
- Python
- MIT
- 4 mo ago
ai-brain-claims
Adversarial validation of 10 hypotheses at the AI ↔ context ↔ brain frontier — research site + observatory primitive (Python). 0/10 vindicated, 0/10 cleanly refuted; all in CONTESTED or SPLIT.
- 0
- MDX
- MIT
- 6 mo ago
playground-s6e10
Kaggle Playground S6E10 airline satisfaction: adversarial validation, tree ensembles and out-of-fold stacking.
- 0
- Python
- MIT
- 2 wk ago
auditkit
Grounded answers, control mapping, and audit-ready exports from bounded source material.
- 0
- Python
- MIT
- 8 mo ago
temporal-drift-aware-fraud-detection-with-adversarial-validation
Builds a fraud detection system on IEEE-CIS data that explicitly models temporal distribution shift by training adversarial validators to detect when the production distribution diverges from training data, then dynamically reweights ensemble members (LightGBM, CatBoost, XGBoost) based on their robustness to detected drift regimes.
- 0
- Python
- MIT
- 9 mo ago
HDCS
LLM loop that reasons in a dense technical register — mechanical gates + adversarial judge + reverse-translation for humans. Self-upgrading. Standalone or as a DSH plugin.
- 0
- JavaScript
- 2 mo ago
mts-shad-drift-guardian
Data Drift Guardian — детекция дрейфа и контроль качества данных для ML-моделей: PSI, JS, KS, Вассерштейн, adversarial validation, дашборд Streamlit (итоговый проект 4.0 Школы аналитиков данных МТС, задача №4)
- 0
- HTML
- 2 mo ago
Magnit_retailhack_2026
MAGNIT TECH × НИУ ВШЭ Hackathon 2026. Drift-aware revenue forecasting for new stores: adversarial validation, PSI, CatBoost + Optuna, age-based post-calibration. Place 6th of 28
- 0
- Jupyter Notebook
- 3 mo ago
adversarial-validation-demo
Code for article https://ilias-ant.github.io/blog/adversarial-validation/.
- 0
- Jupyter Notebook
- 3 y ago




