Swish
Swish: 22 implementations from 19 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.
- 22 compared members are class-bearing (tagged class): the class was constructed with seeded weights in evaluation mode and then called, so its recorded output depends on that initialisation as well as on the forward computation.
Bucket 1 of 1: arg 1: rank 2, kind float, dtype float32
22 implementations from 19 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 |
|---|---|---|
| 21 implementations 18 papers 457319fe226e recorded values identical |
class models/MAT.py 0fb7ab18 recorded x:2/float/float32 class EfficientNet.py 1339ce8e recorded x:2/float/float32 class mmdyn/pytorch/models/vae.py 14e06e2d recorded x:2/float/float32 class models/effnet.py 1b5e656b recorded x:2/float/float32
epiaware/models/backbone.py 21cbbccf recorded x:2/float/float32 class efficientnet_pytorch_3d/model.py 252e1eae recorded x:2/float/float32 class lib/models/pose_efficient_hrnet.py 30a91d38 recorded x:2/float/float32 class projected_gan.py 396c57f5 recorded feat:2/float/float32 class pytorchcv/models/raft.py 6152b289 recorded x:2/float/float32 class tvmodels/models/blocks/effnet_blocks.py 6a1c7184 recorded x:2/float/float32 class main_DataDAM.py 7266bcef recorded input:2/float/float32 class module/odefunc.py 786a3a61 recorded x:2/float/float32
Ref_copula.py 84af1b05 recorded x:2/float/float32 class model.py 92359874 recorded x:2/float/float32 class g_selfatt/nn/group_self_attention.py a3342b2b recorded x:2/float/float32 class src/models.py cd7a90fb recorded x:2/float/float32 class models/unet.py d0fc586d recorded x:2/float/float32 class labml_nn/diffusion/ddpm/unet.py d17cab20 recorded x:2/float/float32 class train_celeba_128.py da8f7cc9 recorded x:2/float/float32 class model/AEMST_GCN.py f96addd2 recorded x:2/float/float32
sleep_staging/cnn/net1d.py f9f00b4a 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 |
| 1 implementation 1 paper a4b5eb729b1b |
class nff/nn/models/painn.py 7f836403 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 |
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-2.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