datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
narrow-model-safety-eval
Narrow Model Safety Evaluation — Protein Dual-Use Risk Dataset
Summary: Annotations, results, and evaluation data for a proof-of-concept framework assessing dual-use risk in narrow scientific AI models. Two lines of work: (1) structure-level metrics — FSPE, FSI, and Physical Realizability Tier — on eight published protein toxins and mechanism-matched benign controls (ESM-2, ProteinMPNN); (2) mechanism generalization — a leave-one-mechanism-out panel measuring what an… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/narrow-model-safety-eval.SpaceOmicsBench-v3
SpaceOmicsBench v3
A Multi-Omics AI Benchmark for Spaceflight Biomedical Data
SpaceOmicsBench v3 provides standardized ML and LLM evaluation infrastructure for spaceflight biomedical data from 4 human spaceflight missions (NASA Twins Study, Inspiration4, JAXA cfRNA, Axiom-2).
Dataset Structure
ML Track (Track A)
tasks/track_a/ — Task definitions (J1: phase classification, J2: clock acceleration)
tasks/track_c/ — Feature-level task definitions (C1:… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/SpaceOmicsBench-v3.en-es-tatoebaThis dataset contains 276,265 parallel sentence pairs in Spanish ↔ English, intended for experiments in machine translation and sequence-to-sequence fine-tuning.
Sentences come from short conversational contexts and represent everyday informal language.
This version includes filtering for short sentence length (3–15 words), deduplication, and TSV formatting.
https://colab.research.google.com/drive/1VRv_bsy9_ys_jyNo79hD8OmlfqF0eCPu?usp=sharing
biothreat-eval
BioThreat-Eval Dataset
Aggregate evaluation results from BioThreat-Eval: a systematic pipeline for evaluating
how frontier language models handle dual-use biological knowledge queries. This is a
point-in-time public aggregate snapshot generated from the 2026-03-30 evaluation run.
Risk Classification (6 Models, 93 Queries Each)
How to read this table. The colours are a triage heuristic, not an evaluation
result. The attack-chain base probabilities behind them are… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/biothreat-eval.verify-or-trust
Verify-or-Trust — benchmark data
Data artifacts for the Verify-or-Trust benchmark: does an LLM
correctly allocate verification when orchestrating a fallible biology foundation model? The harness (code,
Apache-2.0) lives on GitHub; this dataset hosts the inputs it consumes.
At a glance
Field
Value
Primary artifact
substrates/gears_norman.csv
Dataset rows
4,008 decidable (perturbation, gene) edges
Live-verification asset
cells/norman_subset.h5ad with… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/verify-or-trust.evo2-spaceflight-vep
Evo2 Zero-Shot VEP Scores for Spaceflight Radiation-Response Genes
Pre-computed zero-shot variant effect prediction scores from the Evo2 genomic foundation model (7B parameters) across 10 spaceflight radiation-response genes (215,001 scored variants).
Code: github.com/jang1563/evo2-spaceflight-vep
Dataset Description
Each row is a single variant (SNV or indel) scored by Evo2 using an 8,192 bp context window with reverse-complement averaging.
Columns… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/evo2-spaceflight-vep.cbrn-physics-features
CBRN Physics Features
Pre-computed physics-informed distributional features for pathogen-agnostic biological threat detection in gene expression data.
Overview
This dataset contains per-sample and per-group features computed from the shape of gene expression distributions rather than the identity of individual genes. The four core features — Gini coefficient, Shannon entropy, normalized entropy, and Zipf exponent — are platform-agnostic: they require no gene… See the full description on the dataset page: https://huggingface.co/datasets/jang1563/cbrn-physics-features.