Dontopedia

BM25 scores

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-09.)

BM25 scores has 9 facts recorded in Dontopedia across 5 references, with 2 live disagreements.

9 facts·5 predicates·5 sources·2 in dispute

Mostly:rdf:type(3), computed by(2), used by(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (9)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

combinesCombines(2)

computedFromComputed From(2)

returnsReturns(2)

controlsWeightOfControls Weight of(1)

hasComponentHas Component(1)

usesScoringMethodUses Scoring Method(1)

Other facts (8)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

8 facts
PredicateValueRef
Rdf:typeOutput Array[1]
Rdf:typeScore[2]
Rdf:typeMetric[4]
Computed byBm25 Retrieval[3]
Computed byLinear Kernel[3]
Used bySparse Retrieval Microservice[4]
Computed forTest Document[5]
Compared AgainstTraining Documents[5]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/8036737b-9c5e-4cf6-8fd5-40137132613b
ex:Output-Array
typebeam/b0390377-17cd-4838-999f-26ca02c6c6a4
ex:Score
computedBybeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:bm25-retrieval
computedBybeam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
ex:linear-kernel
typebeam/961aaaa1-3f78-41a4-b639-fb057c9f07c8
ex:Metric
labelbeam/961aaaa1-3f78-41a4-b639-fb057c9f07c8
BM25 scores
usedBybeam/961aaaa1-3f78-41a4-b639-fb057c9f07c8
ex:sparse-retrieval-microservice
computedForbeam/9669963d-f7d7-452d-a9ec-0cf09ed6be1d
ex:test-document
comparedAgainstbeam/9669963d-f7d7-452d-a9ec-0cf09ed6be1d
ex:training-documents

References (5)

5 references
  1. ctx:claims/beam/8036737b-9c5e-4cf6-8fd5-40137132613b
    • full textbeam-chunk
      text/plain1 KBdoc:beam/8036737b-9c5e-4cf6-8fd5-40137132613b
      Show excerpt
      Finally, you can combine the results from both sparse and dense retrievals. One common approach is to use a weighted sum of the scores from both methods. Here's a more complete example: ```python import numpy as np from sklearn.feature_ex
  2. ctx:claims/beam/b0390377-17cd-4838-999f-26ca02c6c6a4
    • full textbeam-chunk
      text/plain963 Bdoc:beam/b0390377-17cd-4838-999f-26ca02c6c6a4
      Show excerpt
      - We use a pre-trained BERT model to generate embeddings for documents and the query. - `cosine_similarity` computes the similarity between the query embedding and document embeddings. 3. **Combining Scores**: - We combine the BM2
  3. ctx:claims/beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
    • full textbeam-chunk
      text/plain1 KBdoc:beam/07b00e3a-dd0e-40bb-a9be-bbdf1ac254da
      Show excerpt
      with torch.no_grad(): doc_outputs = model(**doc_inputs) query_outputs = model(**query_inputs) doc_embeddings = doc_outputs.last_hidden_state.mean(dim=1) query_embedding = query_outputs.last_hidden_state.mean(dim
  4. ctx:claims/beam/961aaaa1-3f78-41a4-b639-fb057c9f07c8
    • full textbeam-chunk
      text/plain1 KBdoc:beam/961aaaa1-3f78-41a4-b639-fb057c9f07c8
      Show excerpt
      4. **Final Ranking**: Rank the combined results and return the top-k documents. ### Step 2: Architectural Components To achieve 2,000 queries/sec with 99.9% uptime, you need to design a scalable and fault-tolerant architecture. Here are t
  5. ctx:claims/beam/9669963d-f7d7-452d-a9ec-0cf09ed6be1d
    • full textbeam-chunk
      text/plain1 KBdoc:beam/9669963d-f7d7-452d-a9ec-0cf09ed6be1d
      Show excerpt
      predictions.append(predicted_label) return predictions # Make predictions predictions = predict_labels(test_df, bm25, train_df) # Calculate the recall score recall = recall_score(test_df['label'], predictions, average='binary'

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.