reproducibility
wandb
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
- 11k
- Python
- MIT
- 9 h ago
lightning-hydra-template
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
- 5.4k
- Python
- 5 mo ago
EvalAI
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
- 2k
- Python
- 7 d ago
benchmark_VAE
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
- 2k
- Python
- Apache-2.0
- 2 y ago
bernstein
Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
- 1.2k
- Python
- Apache-2.0
- 16 h ago
RecSys2019_DeepLearning_Evaluation
This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.
- 992
- Python
- AGPL-3.0
- 3 y ago
RigorPilot-Skills
README-first research reproduction skills with bounded execution, auditable evidence, and byte-preserving README annotations.
- 489
- Python
- MIT
- 21 h ago
FPF
FPF (First Principles Framework) Library: methods and pattern languages for open-ended development and a shared culture of thinking and acting among people and AI agents. Use individual methods or combine them to solve difficult problems and expand capabilities.
- 547
- CC-BY-4.0
- 8 h ago
Paper-Replications-and-Experiments
From-scratch PyTorch replications of classic and SOTA AI/ML papers: transformers, attention, GANs, diffusion, CLIP, LoRA, MoE, plus SFT/GRPO post-training experiments.
- 431
- Jupyter Notebook
- Apache-2.0
- 2 wk ago
RL-pricing
A reproducibility lab for trading AI: published RL and LLM trading claims re-tested under a pre-registered protocol, with a causal benchmark and a live track.
- 341
- Python
- MIT
- 2 d ago
ai-decision-system
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: typed model answers, policy-gated approvals, A/B ship gates, release gates.
- 358
- Python
- MIT
- 2 d ago
VeriInk
Verifiable handwriting synthesis for feedback-driven model improvement and RSI research. Seeded examples, artifact checks and auditable data handoffs.
- 290
- Python
- 3 wk ago
dna-seq-gatk-variant-calling
This Snakemake pipeline implements the GATK best-practices workflow
- 268
- Python
- MIT
- 3 y ago
datajoint-python
Relational Workflows: where database schemas define executable data pipelines.
- 198
- Python
- Apache-2.0
- 2 d ago
VeriRepro
VeriRepro: Evidence-grounded reproduction for computational papers.
- 194
- Python
- Apache-2.0
- 4 wk ago
nix-flake-helium-browser
Nix Flake for Helium browser. Auto updates, Policy support, NixOS module, Home-manager module
- 122
- Nix
- 3 d ago
python-ml-research-template
A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/CLAIRE-Labo/no-representation-no-trust
- 121
- Shell
- MIT
- 18 mo ago
ml-project-template
ML project template facilitating both research and production phases.
- 115
- Python
- 7 y ago
dna-seq-varlociraptor
A Snakemake workflow for calling small and structural variants under any kind of scenario (tumor/normal, tumor/normal/relapse, germline, pedigree, populations) via the unified statistical model of Varlociraptor.
- 90
- Python
- MIT
- 2 d ago
agent-harness
- 1
- 0
- other
- 4 mo ago
EvalArc Evidence Lab
Find agent regressions behind a better score.
Runs in the browser on Hugging Face
- 0
- mit
- 5 d ago
DeepSeek Prompt Parity
Inspect tool history, exact prompts and input contracts
Runs in the browser on Hugging Face
- 0
- mit
- 4 wk ago
EMNLP_Cost-Aware-Protocol-Routing
- 0
- 26
- mit
- 3 wk ago
tracegrpo
- 0
- 0
- 7 wk ago
dropout-decay
- 0
- 0
- mit
- 6 mo ago










