fuse_scores
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-08.)
fuse_scores is fuse scores from sparse and dense searches.
Mostly:has parameter(9), called with(6), rdf:type(4)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (15)
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.
isParameterOfIs Parameter of(4)
- Dense Scores
ex:dense-scores - Dense Weight
ex:dense-weight - Sparse Scores
ex:sparse-scores - Sparse Weight
ex:sparse-weight
assignedFromAssigned From(1)
- Fused Scores
ex:fused-scores
callsFunctionCalls Function(1)
- Example Usage
ex:example-usage
computedByComputed by(1)
- Fused Scores
ex:fused-scores
containsContains(1)
- Two Functions
ex:two-functions
definesFunctionDefines Function(1)
- Fusion Code Block
ex:fusion-code-block
demonstratesDemonstrates(1)
- Example Usage
ex:example-usage
describesDescribes(1)
- Step 2 Subpoint
ex:step-2-subpoint
isCalledByIs Called by(1)
- Fusion Code Block
ex:fusion-code-block
isUsedByIs Used by(1)
- Py Torch
ex:PyTorch
isUsedInIs Used in(1)
- Linear Combination of Weights
ex:linear-combination-of-weights
providesInputToProvides Input to(1)
- Tune Weights
ex:tune-weights
Other facts (83)
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.
| Predicate | Value | Ref |
|---|---|---|
| Has Parameter | Sparse Scores | [2] |
| Has Parameter | Dense Scores | [2] |
| Has Parameter | Sparse Weight | [2] |
| Has Parameter | Dense Weight | [2] |
| Has Parameter | scores1 | [3] |
| Has Parameter | scores2 | [3] |
| Has Parameter | Scores1 | [4] |
| Has Parameter | Scores2 | [4] |
| Has Parameter | Weights | [4] |
| Called With | Sparse Scores | [2] |
| Called With | Dense Scores | [2] |
| Called With | 0.6 | [2] |
| Called With | 0.4 | [2] |
| Called With | scores1 | [3] |
| Called With | scores2 | [3] |
| Rdf:type | Implementation Task | [1] |
| Rdf:type | Function | [2] |
| Rdf:type | Function | [3] |
| Rdf:type | Function | [4] |
| Execution Order | Convert to Tensor | [2] |
| Execution Order | Normalize | [2] |
| Execution Order | Weighted Sum | [2] |
| Execution Order | Convert Back to Numpy | [2] |
| Returns | Numpy Array | [2] |
| Returns | Fused Scores | [3] |
| Returns | Fused Scores | [4] |
| Performs Operation | Convert to Tensor | [2] |
| Performs Operation | Normalize | [2] |
| Performs Operation | Weighted Sum | [2] |
| Has Comment | Convert scores to PyTorch tensors | [2] |
| Has Comment | Normalize scores | [2] |
| Has Comment | Fuse scores | [2] |
| Combines | scores1 | [3] |
| Combines | scores2 | [3] |
| Inverse Has Parameter | scores1 | [3] |
| Inverse Has Parameter | scores2 | [3] |
| Performs | Normalization | [4] |
| Performs | Weighted Sum Fusion | [4] |
| Normalizes | Scores1 | [4] |
| Normalizes | Scores2 | [4] |
| Uses Library | Py Torch | [2] |
| Description | fuse scores from sparse and dense searches | [2] |
| Source Code | def fuse_scores(sparse_scores, dense_scores, sparse_weight=0.5, dense_weight=0.5): | [2] |
| Specifies Dtype | torch.float32 | [2] |
| Converts From | Numpy Array | [2] |
| Converts to | Py Torch Tensor | [2] |
| Purpose | score fusion for retrieval systems | [2] |
| Return Type | numpy.ndarray | [2] |
| Parameter Order | ["sparse_scores","dense_scores","sparse_weight","dense_weight"] | [2] |
| Uses | Num Py Dot | [3] |
| Sets Weights | [0.6, 0.4] | [3] |
| Test Input1 | [0.8, 0.2, 0.4] | [3] |
| Test Input2 | [0.3, 0.7, 0.1] | [3] |
| Has Return Type | Fused Scores Array | [3] |
| Computes | Dot Product | [3] |
| Outputs | Fused Scores | [3] |
| Test Output | Fused Scores Value | [3] |
| Test Input1 Length | 3 | [3] |
| Test Input2 Length | 3 | [3] |
| Is Pure Function | true | [3] |
| Algorithm Type | linear-combination | [3] |
| Parameter Type | Num Py Array | [3] |
| Computational Operation | dot-product | [3] |
| Has Two Parameters | true | [3] |
| Returns Single Value | true | [3] |
| Is Defined in | Fusion Code Block | [3] |
| Follows Python Naming Convention | true | [3] |
| Has No Error Handling | true | [3] |
| Has No Input Validation | true | [3] |
| Uses Numpy Dot | true | [3] |
| Test Input1 Element Count | 3 | [3] |
| Test Input2 Element Count | 3 | [3] |
| Has Fixed Weights | true | [3] |
| Computes Weighted Sum | true | [3] |
| Return Statement | return fused_scores | [3] |
| Parameter Names | ["scores1","scores2"] | [3] |
| Uses Formula | Min Max Normalization | [4] |
| Uses Operation | Dot Product | [4] |
| Consumes Output of | Tune Weights | [4] |
| Transforms | Array Construction | [4] |
| Enables | Ensemble Prediction | [4] |
| Creates | Fused Score Array | [4] |
| Has Return Statement | Return Fused Scores | [4] |
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.
References (4)
ctx:claims/beam/b2901d01-4633-4513-84d1-1ea253e96bbfctx:claims/beam/2ba6cd1e-507f-44fe-bc7e-a6ea9503c472- full textbeam-chunktext/plain1 KB
doc:beam/2ba6cd1e-507f-44fe-bc7e-a6ea9503c472Show excerpt
Use PyTorch to fuse the scores from sparse and dense searches: ```python def fuse_scores(sparse_scores, dense_scores, sparse_weight=0.5, dense_weight=0.5): # Convert scores to PyTorch tensors sparse_scores_tensor = torch.tensor(spa…
ctx:claims/beam/83d82fac-5668-4797-9ad9-b4b6b371089e- full textbeam-chunktext/plain1 KB
doc:beam/83d82fac-5668-4797-9ad9-b4b6b371089eShow excerpt
[Turn 6684] User: I'm testing fusion on 3,000 queries and achieving 91% relevance improvement, but I need help optimizing the fusion algorithm. Can you review my code and suggest improvements? I'm using NumPy 1.25.0 for score calculations a…
ctx:claims/beam/c2cfce3c-ef3d-4bc1-8ac6-e059a3dd9fbb- full textbeam-chunktext/plain1 KB
doc:beam/c2cfce3c-ef3d-4bc1-8ac6-e059a3dd9fbbShow excerpt
#### 2. Normalization Normalize the scores to ensure they are on the same scale. #### 3. Advanced Fusion Techniques Consider using a weighted sum with normalization. ### Example Code ```python import numpy as np from sklearn.model_select…
See also
- Implementation Task
- Function
- Sparse Scores
- Dense Scores
- Sparse Weight
- Dense Weight
- Numpy Array
- Py Torch
- Convert to Tensor
- Normalize
- Weighted Sum
- Py Torch Tensor
- Convert Back to Numpy
- Num Py Dot
- Fused Scores
- Fused Scores Array
- Dot Product
- Fused Scores Value
- Num Py Array
- Fusion Code Block
- Scores1
- Scores2
- Weights
- Normalization
- Weighted Sum Fusion
- Min Max Normalization
- Tune Weights
- Array Construction
- Ensemble Prediction
- Fused Score Array
- Return Fused Scores
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.