swish
swish: 14 implementations from 37 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 2 distinct outputs.
Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence. Implementations are compared only within one bucket, the positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name; each bucket's shared input is fixed by that key, so members of one bucket saw bitwise-identical inputs under their own scalar arguments. A cluster is the set of members whose recorded output digest is identical. Nothing here says which computation a paper's method intended, and nothing reproduces a paper's results.
Not compared, and not in the tables or the counts above:
- Every examined implementation of this name that took an array argument ran on the shared input.
- No implementation of this name ran on its own fixture arguments only: every one that ran took an array argument.
- Every compared output was digested.
Bucket 1 of 1: arg 1: rank 2, kind float, dtype float32
14 implementations from 37 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 2 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.
| Cluster (same digest to six decimals) | Members | Shared output on this bucket's input |
|---|---|---|
| 12 implementations 35 papers 457319fe226e recorded values identical |
models/modeling.py 0f786c40 recorded x:2/float/float32
uno/flux/pipeline.py 5fb03646 recorded x:2/float/float32
models.py 107bf3b7 recorded x:2/float/float32 one code sha held from 2 papers' repositories models.py 31117990 recorded x:2/float/float32 models/graddae/mlp.py 0444419a recorded x:2/float/float32 classy_vision/models/efficientnet.py 0aeebcaf recorded x:2/float/float32 efficientnet/model.py 20fb7a08 recorded x:2/float/float32 models/model.py 3a4a478b recorded x:2/float/float32 flows.py 84b2a92d recorded x:2/float/float32 labml_nn/diffusion/stable_diffusion/model/autoencoder.py 8efb92cd recorded x:2/float/float32 model.py bb3da066 recorded x:2/float/float32 transformer/modeling_bert_quant.py d09ef21d recorded x:2/float/float32 |
[1.5475, -0.272156, 0.293637, -0.230643, -0.260441, -0.271006, -0.225418, 0.366322, …] shape [4, 8] · float32 · Tensor |
| 2 implementations 3 papers 72ecfcef5a0f recorded values identical |
one code sha held from 2 papers' repositories svp/model/models_mamba.py 5f094438 recorded x:2/float/float32; beta=0.5 src/neuron/activation_functions.py 919aae7a recorded t:2/float/float32; beta=0.5 |
[1.28206, -0.486441, 0.266222, -0.286364, -0.351228, -0.385362, -0.276971, 0.327192, …] shape [4, 8] · float32 · Tensor |
Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence; where a cluster's members carry recorded values, the largest difference among them is shown under the cluster. Paper titles are the archive's archive 2025-07-28 where the paper is in the archive and the graph's where it was added by Syntology; papers with no page here are shown by their recorded paper id only. A paper count above the implementation count means one implementation (one code sha) is held from several papers' repositories and counts once. Per-sample status, licence and fingerprint records for each paper are on its paper page. JSON twin: /census/swish.json.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections