Research-reproduction Agent: PDF → factor code → backtest → Red Team → reproducibility score. Part of the alpha-kit stack.
Complete PyTorch reproduction of Google's TITANS, MIRAS, and NL neural memory papers. 52 tests, 87% coverage, Docker support.
Official implementation of "RefP2C: Reflective Paper-to-Code Development Enabled by Fine-Grained Verification".
Clean-room reimplementation of the Huxley-Gödel Machine (arXiv:2510.21614): a self-improving coding agent with CMP + Thompson-Sampling tree search, validated in $0 simulation and live on SWE-bench (mini-swe-agent + gpt-5.4).
Multi-agent LLM trading framework reproduced from scratch — finds drawdown reduction but no alpha across 2022/2024 regimes
Simulation reproducing PoA2 (Proof of Authority and Association): active consensus-layer trust computation coupling blockchain finalization with federated-learning aggregation for IIoT intrusion detection
Mouse Dynamics-Based Intrusion Detection using Recurrence Plots and Vision Transformers
Contains files for my reproduction of experiments from Harnik et al.'s "To Zip or not to Zip" (2013) paper.
Simulation reproducing PureChainShield: 1D-CNN+BiLSTM edge intrusion detection with PureChain PoA2 blockchain consensus for smart EV charging security
Independent SetFit reproduction and paper-code audit: ten-seed CR results, deterministic few-shot pipeline, trained MPNet release, terminal model lab, tests, and self-contained research site.
FaithfulRAG reproduction for knowledge conflict and context-faithful generation with Llama-3.1-8B
implementing Quantum Bayes Classifiers (QBCs) for image classification tasks using MNIST and Fashion-MNIST datasets, based on the research by Ming-Ming Wang and Xiao-Ying Zhang. The project includes Naïve QBC, SPODE-QBC, TAN-QBC, and Symmetric-QBC, simulated on MindQuantum.
Reproduction of a quantum-resistand secure federated learning framwork using NTRU lattice-based encryption for privacy-preserving medical AI on the Winconsin Breast Cancer Dataset
Simulation reproducing SDA-FL (Summary-Driven Asynchronous Federated Learning): two-phase Byzantine filtering + relevance-weighted staleness aggregation for IoT FL
Add a description, image, and links to the research-reproduction topic page so that developers can more easily learn about it.
To associate your repository with the research-reproduction topic, visit your repo's landing page and select "manage topics."