Records
Published experiments, each sealed to the code that produced it
Reproduction of jwkirchenbauer/lm-watermarking: watermark detection with OPT-1.3B
K-Veritas Team
Independent reproduction · Artifact evaluation · Security and cryptography
Reproduction of FlagOpen/FlagEmbedding: BGE-base-en-v1.5 on BEIR SciFact, NFCorpus and FiQA
K-Veritas Team
Independent reproduction · Artifact evaluation · Natural language processing
Reproduction of locuslab/wanda: pruning OPT-1.3B with Wanda and magnitude
K-Veritas Team
Independent reproduction · Artifact evaluation · Machine learning
Reproduction of Lightning-AI/lightning-thunder: Hugging Face LLM generation, eager vs Thunder
K-Veritas Team
Independent reproduction · Benchmark or leaderboard entry · Programming languages and compilers
Reproduction of linkedin/Liger-Kernel: fused linear cross entropy, RMSNorm and SwiGLU benchmarks
K-Veritas Team
Independent reproduction · Artifact evaluation · Systems and performance
Reproduction of jiaweizzhao/GaLore: LLaMA-60M pre-training on C4 with GaLore
K-Veritas Team
Independent reproduction · Artifact evaluation · Machine learning
Reproduction of state-spaces/mamba: Mamba-370M zero-shot evaluation
K-Veritas Team
Independent reproduction · Artifact evaluation · Natural language processing
Reproduction of facebookresearch/schedule_free: Schedule-Free AdamW on MNIST
K-Veritas Team
Independent reproduction · Artifact evaluation · Machine learning
Reproduction of microsoft/BitNet: BitNet b1.58 2B CPU inference throughput
K-Veritas Team
Independent reproduction · Artifact evaluation · Natural language processing
Reproduction of vllm-project/vllm: offline throughput of Qwen2.5-1.5B-Instruct
K-Veritas Team
Independent reproduction · Artifact evaluation · Systems and performance
Reproduction of pytorch/torchtitan: Llama 3 debug-model pretraining on one GPU
K-Veritas Team
Independent reproduction · Artifact evaluation · Natural language processing
Reproduction of karpathy/llama2.c: 15M-parameter Llama 2 trained on TinyStories
K-Veritas Team
Independent reproduction · Benchmark or leaderboard entry · Natural language processing
Reproduction of Broadcom/csg-htsim: NDP sequential all-to-all on a 1024-node fat tree
K-Veritas Team
Independent reproduction · Artifact evaluation · Networking
Reproduction of hiyouga/LlamaFactory: Qwen3-4B LoRA supervised fine-tuning example
K-Veritas Team
Independent reproduction · Artifact evaluation · Natural language processing
Reproduction of huggingface/lighteval: SmolLM2-1.7B-Instruct on ARC-Challenge and HellaSwag
K-Veritas Team
Independent reproduction · Benchmark or leaderboard entry · Natural language processing
Reproduction of attractivechaos/plb2: four CPU benchmarks in seven languages
K-Veritas Team
Independent reproduction · Benchmark or leaderboard entry · Programming languages and compilers