Downloads · 30 days
0
jinu0633/recognition-paths-recognizers
recognition-paths-recognizers is a machine learning model from jinu0633. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Three small recognizers for Horn entailment, trained on the same synthetic distribution and evaluated on the same frozen Hankel tables (jinu0633/hankel-tables): set/ (invariance by architecture), seqaug/ (invariance b…
Downloads · 30 days
0
Access
Public
Updated Sep 6, 2026
Repo size
9.1 MB
Likes
1
Public
Click a slice to open those files.
.safetensors9.1 MB · 95%
From the Hugging Face model README
Three small recognizers for Horn entailment, trained on the same synthetic
distribution and evaluated on the same frozen Hankel tables
(jinu0633/hankel-tables): set/ (invariance by architecture), seq_aug/
(invariance by data augmentation), seq_fixed/ (neither); *_s1, *_s2,
*_s3 are further seeds and seq_aug_long a three-times-budget run. Each folder has
its own model card with the evaluation numbers. Source and theory:
github.com/Kairose-master/proof-path-invariance and
github.com/Kairose-master/recognition-paths.