Pith. sign in

Introduction to and hands-on use cases with hathitrust research center’s extracted features 2.0 dataset

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

dataset 1

citation-polarity summary

fields

cs.IR 1

years

2025 1

verdicts

CONDITIONAL 1

roles

dataset 1

polarities

background 1

representative citing papers

Vector embedding of multi-modal texts: a tool for discovery?

cs.IR · 2025-09-10 · conditional · novelty 4.0

Using ColPali embeddings of 3,600 textbook page images, cosine similarity beats dot product, Euclidean, and Manhattan distances on top-5 retrieval, but only reaches 0.51 precision@5 without a text-only baseline.

citing papers explorer

Showing 1 of 1 citing paper.

  • Vector embedding of multi-modal texts: a tool for discovery? cs.IR · 2025-09-10 · conditional · none · ref 5

    Using ColPali embeddings of 3,600 textbook page images, cosine similarity beats dot product, Euclidean, and Manhattan distances on top-5 retrieval, but only reaches 0.51 precision@5 without a text-only baseline.