1 results

executable-benchmark

inall models datasets apps agents people projects

Datasets

All datasets matching “executable-benchmark”

jingyongai /executable-knowledge-lifecycles-benchmark Executable Knowledge Lifecycles Benchmark This dataset is the frozen semantic benchmark for Experiments 1A and 1B of Executable Knowledge Lifecycles as Dynamical Control in Agent Systems. It tests whether an untrusted natural-language parser can be placed behind a typed, model-external compilation boundary without acquiring validation authority. Version: 0.2.6-exp.1-final Version DOI: 10.5281/zenodo.21361204 Source release: GitHub v0.2.6-exp.1-final Release collection:… See the full description on the dataset page: https://huggingface.co/datasets/jingyongai/executable-knowledge-lifecycles-benchmark.texttext-classificationn<1K0 likes14 downloads2mo agoHugging Face