From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-09.)
Dense Retrieval has 23 facts recorded in Dontopedia across 8 references, with 4 live disagreements.
Mostly:rdf:type(7), rdfs:label(6), has parameter(2)
hasParameterusescombinedWithreturnsNumpyArraycalledByconsistsOfhasRecallRateOther 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)ex:hybrid_retrieval_systemex:hybrid_searchcallsCalls(1)ex:hybrid_sparse_dense_retrievalcombinedWithCombined With(1)ex:sparse_retrievalcombinesTechniquesCombines Techniques(1)ex:hybrid_rankingconsistsOfConsists of(1)ex:hybrid_systemcontainsContains(1)ex:code_structurerequestsForRequests for(1)ex:UsersupportsSupports(1)ex:Haystack_1.16.0Timeline 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.
doc:beam/8419193f-8cac-4d94-919a-b1c2084db6fdalphas = np.linspace(0, 1, 11) # Range of alpha values to test best_alpha, best_map = {}, {} for query in queries: best_alpha[query], best_map[query] = tune_alpha(query, documents, relevant_docs[query], alphas) print(f"Best alpha f…
doc:beam/d06f3ba0-b9c5-4f2b-b1ca-35d6a83f323a- A nested dictionary (`metadata_index`) maps metadata fields to dictionaries of values, which in turn map to lists of documents. - This structure allows for efficient lookups based on metadata fields and values. ### Efficiency - **…
doc:beam/587972a9-5e6f-49d1-8222-dffeeff81ee5class QueryRequest(BaseModel): query: str limit: int class QueryResponse(BaseModel): results: List[HybridResult] total_results: int @app.route('/query', methods=['POST']) def query(): query = QueryRequest(**request.jso…
doc:beam/e3d6146f-0be0-4107-8509-b0471fc829a9precision = precision_at_k(true_labels, predicted_labels, k=k) if precision > best_precision: best_precision = precision best_alpha = alpha print(f"Best Alpha: {best_alpha}, Best Precision@{k…
doc:beam/8036737b-9c5e-4cf6-8fd5-40137132613bFinally, 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…
Dontopedia is in a read-only public launch. Follow the references and disputed branches now; contributions will open after durable identity and moderation are in place.