Figure 1

Distribution of cosine similarity scores between the query vector and each of the Medline abstract vectors, indicating the 10,000th (blue diamond) 50,000th (red diamond) and 100,000th (green diamond) ranked abstract.
Distribution of cosine similarity scores between the query vector and each of the Medline abstract vectors, indicating the 10,000th (blue diamond) 50,000th (red diamond) and 100,000th (green diamond) ranked abstract.