GEGLU
GEGLU: 12 implementations from 12 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 1 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:
- 1 more implementation of this name was examined but did not run on the shared input (RuntimeError 1).
- 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.
- 12 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
12 implementations from 12 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 1 distinct output, 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 12 papers 2fde4292a2c2 recorded values identical |
class make_a_video_pytorch/make_a_video.py 06c17462 recorded x:2/float/float32 class model/cross_modal_attention.py 22d4e664 recorded x:2/float/float32 class phenaki_pytorch/phenaki_pytorch.py 579b2c6b recorded x:2/float/float32 class models/model.py 594fabef recorded x:2/float/float32 class marge_pytorch/marge_pytorch.py 5f34e2fd recorded x:2/float/float32 class utils/perceiver.py 7852fe36 recorded x:2/float/float32 class src/model/transformer_xl.py 845f84e3 recorded x:2/float/float32 class cod/models/vae/vae.py 96a67196 recorded x:2/float/float32
models/m3.py 98fc29d2 recorded x:2/float/float32
model/FedMVP.py a23cbed0 recorded x:2/float/float32 class block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py c5c74119 recorded x:2/float/float32
model/CoIFNet.py c83d2ae5 recorded x:2/float/float32 |
[-0.298326, 0.239281, -0.080058, -0.283647, -0.0578597, 2.20472, 0.062027, -0.612184, …] shape [4, 4] · 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/geglu.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