Constarium
← Search

Table · dataset · 2026

ai4data/devdatabench

Listed in Hugging Face Datasets

DevDataBench A benchmark for retrieval over structured statistical metadata, built from the World Bank Data360 indicator catalog.

Description

Each document is a metadata record whose fields (definition, methodology, geographic and temporal coverage, unit, source, ...) answer different kinds of queries. Queries are facet-targeted and multilingual; documents are in English, so the task is cross-lingual retrieval.

See the paper Field Order Should Not Matter: Permutation-Invariant Fine-Tuning… See the full description on the dataset page: huggingface.co/datasets/ai4data/devdatabench.

Links

Where it is published

Documentation and papers

Catalogue records · 1

Topics

Stated by source
text
Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetsai4data/devdatabench14 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:textsource · Hugging Faceconnector:huggingface@1.0.0
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0