DigiGreen/human_preference_eval_dataset
Digital Green
Automatic scores do not always match what a person would prefer to read. This is a dataset of human judgements comparing pairs of answers, so you can tune or check automatic scoring against real preferences.
QUICK INFO
SOLUTION TYPE
Models, data & tools
TECHNOLOGY CATEGORY
Benchmarks & evaluations
AREA OF WORK
Research & scientific knowledge
ACCESS
Free · Open source
DEPLOYMENT
Self-hosted / on-premise · Downloadable
SOURCE REVIEWED
August 17, 2026
What it helps with
- Which answer would a person prefer
- Check automatic scoring against human judgement
- Paired answer comparisons rated by people
- Tune a scoring model to human preferences
- Test whether scores match what readers like
- Human rated answer pairs to download
Scope & audience
WHO IT'S FOR
Scientist / researcher · Developer / AI builder
AREA OF WORK
Research & scientific knowledge
COMMODITY / SCOPE
Cross-commodity
Access & technical details
ACCESS
Anyone can get it
INTERFACE
Model download / weights · Dataset download
DEPLOYMENT
You run it yourself
LANGUAGES
Not stated by provider
Featured media
Source information
This listing was compiled from publicly available source material. Verify current details with the provider.
PROVIDER DOCUMENTATION
Reviewed August 2026
Explore more like this
NALEF Food Safety
VerbaNexAI Lab
Models, data & tools
Before trusting an AI system on a farming or food task you need a way to check it. Predicts cucumber crop phenological growth stage among five classes from field images, ranked by macro F1 score.
Free
Cloud-hosted
Benchmarks & evaluations
NALEF Food Safety
research-develop
research-and-scientific-knowledge
buildable-or-downloadable-component
benchmarks-and-evals
Free
Cloud-hosted
August 17, 2026
- What growth stage is my cucumber crop
- Classify cucumber growth stage from field photos
- Test a model on crop stage prediction
- Compare models on cucumber images
- Five stage cucumber growth benchmark
SNAPMe
USDA Agricultural Research Service, via Ag Data Commons
Models, data & tools
Before trusting an AI system on a farming or food task you need a way to check it. Computer vision models predicting foods, ingredients and nutrients from photographs of meals, snacks and beverages paired with dietary records.
Free
Self-hosted / on-premise · Downloadable
Benchmarks & evaluations
SNAPMe
research-develop
research-and-scientific-knowledge
buildable-or-downloadable-component
benchmarks-and-evals
Free
Self-hosted / on-premise · Downloadable
August 17, 2026
- How many calories are in this dish
- Identify foods in a meal photo
- Work out ingredients from a picture
- Test a model on food photographs
- Compare nutrient estimates with dietary records
- Food photo benchmark for nutrition models
Is this your Resource?
Contact us to claim this listing and add details, screenshots or a demo.