The anatomy of a top result.

Forward index · top stems on this page

document length 903 body tokens  ·  max tf 21 (film)  ·  vocabulary 549 distinct stems  ·  title 4 stems

Score breakdown

Re-derived from the same tf·idf cosine values, boost factors, and PageRank multipliers the live ranker just used. weighted = body + title × 2.0 · final = weighted × phrase × pagerank.

1. cosine(query, body) tf·idf body · 5 resolved stems0.6814
2. cosine(query, title) × 2.0 title boost ×2.0 applied1.9201
3. weighted subtotal cosBody + 2.0 × cosTitle2.6015
4. × phrase multiplier ≥2 stems within 5-token window×3.0
5. × pagerank multiplier PageRank not computed for this page · ×1.0×1.0000
6. final score weighted × phrase × pagerank7.8046

Per-query-stem · how each term contributes

1. film wid 1258 · df 162 body tf 21 title tf 0 idf 0.889
2. ghost wid 0587 · df 10 body tf 16 title tf 1 idf 4.907
3. dog wid 0375 · df 13 body tf 15 title tf 1 idf 4.528
4. samurai wid 0588 · df 3 body tf 15 title tf 1 idf 6.644
5. user wid 1045 · df 289 body tf 10 title tf 0 idf 0.054

Outlinks (1)

• https://hitcslj.github.io/TestPages/Movie.htm