Home › Census › _no_grad_trunc_normal_

_no_grad_trunc_normal_

Syntologyfunction-name censuscensus 2026-09-22battery b986f7e04d79all samples with this name

_no_grad_trunc_normal_: 16 implementations from 16 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. Each member's behaviour fingerprint (its outputs on the shared battery) is not in this export and is not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect); click a member's code_sha256 to copy that call.

Not compared, and not in the tables or the counts above:

Bucket 1 of 1: arg 1: rank 2, kind float, dtype float32

16 implementations from 16 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)MembersShared output on this bucket's input
16 implementations
16 papers
42f0dd179468
recorded values identical

models/FM/EEGPT/Model_EEGPT.py 307242ac3279e182
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
  • arXiv:2506.03110

methods/visiontransformer.py 32d549c7c63738c0
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

models.py 3f7062bb9233a958
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

easycv/models/backbones/vision_transformer.py 5bcbd988b672cf32
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

towhee/models/uniformer/uniformer.py 607038475fdc388b
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

towhee/models/swin_transformer/model.py 730a23e2dd3abea0
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

corun_colabator/archs/corun_arch.py 7eb8f921afc80af3
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

fastreid/modeling/backbones/vision_transformer.py 813ed3a96c17cf42
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

model/backbones/vit_pytorch.py 9143fd74c66cf68d
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

models/early_exit.py a682db89c810ed54
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

basicsr/archs/swinir_arch.py c30c007e9c6365e0
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

src/model/model_action.py cffc671a6c09decc
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

models/dichavit.py d05e018c317ed42b
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

src/models/predictor.py e7c3b600144accb0
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

joint_evol_opt.py ed7e8d54fc7c6786
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0

model/SSRT.py fa2dd3be10cf9804
recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
[-0.00895651, 0.69355, -1.24155, -1.04171, -0.478393, 0.326503, -0.0237045, 1.16706, …]
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/no-grad-trunc-normal.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