trunc_normal_
trunc_normal_: 37 implementations from 54 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 4 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:
- 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
37 implementations from 54 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 4 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 |
|---|---|---|
| 34 implementations 50 papers 42f0dd179468 recorded values identical |
real/test_code/architecture/MST.py c76d18678f19d332 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
architectures/backbone/DINO_ViT.py 915b71e73a54fc97 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
model/SSRT.py 02566da69866c48c recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
corun_colabator/archs/corun_arch.py 056f371660385ea5 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
models/FM/EEGPT/Model_EEGPT.py 359975e35f7d1d79 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
fastreid/modeling/backbones/vision_transformer.py 605878f6dcef72e9 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
easy_ViTPose/vit_models/model.py c3487124f762d881 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
src/model/model_action.py d8578a1e5c318cf9 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 one code sha held from 2 papers' repositories model/impl/actionformer.py e6ea9664b9a77523 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
models/cha_mae_vit.py fabe0899316ffaa5 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models/early_exit.py 04c04dfd96b26f9a recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 basicsr/archs/swinir_arch.py 0af416f19e3851c1 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models/jepa.py 28455f5511c6676f recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 easycv/models/backbones/vision_transformer.py 462cf9fa4898bc51 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
src/models/predictor.py 4e02bf1d1efcb33d recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 real/test_code/architecture/DAUHST.py 505222cf2cc4240f recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 split_model.py 6586759c888019fc recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models/network_vrt.py 8347c57b16dab539 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
modeling/fusion_part/CRM.py 8c3374496d26feda recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 foundation/model.py 95f8054d3a8863e8 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 vissl/models/trunks/beit_transformer.py ab8464b48ee9d702 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 towhee/models/swin_transformer/model.py ada91a01b9efbb1d recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 src/models/reefl_vit.py af8aefa30bd76920 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0
models/sam_withToken.py b425e24882305880 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 model/backbones/vit_pytorch.py ba6277edefa610aa recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models/dichavit.py be2feea89481c009 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 timm/models/bixt.py c92dcfe50ad922d8 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models/vision_transformer_moe.py ca3425736d00ed34 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 dic_models.py cd079d4c82711147 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 pypots/nn/modules/tslanet/backbone.py d347dc5f198621fd recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 joint_evol_opt.py ef92035251726e40 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 towhee/models/uniformer/uniformer.py f3e47c6e3250d13b recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 codes/models/decoder_affordance.py f836ffb10ee7ef21 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 models.py fd05acd780fc4073 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 |
| 1 implementation 2 papers 8983255eae79 |
modules/fusion_module.py 5cb5985f521b3573 recorded x:2/float/float32; mean=0.0, std=1.0 |
[-1.12584, -1.15236, -0.250579, -0.433879, 0.84871, 0.692009, -0.316013, -0.11522, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 10d0186bfd20 |
pbb/models.py 92221940e53dde88 recorded tensor:2/float/float32; mean=0.0, std=1.0, a=-2.0, b=2.0 |
[-0.00895653, 0.69355, -1.24155, -1.04171, -0.478393, 0.326503, -0.0237045, 1.16706, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 8be0b5c837c2 |
models/modeling/PSVMAModel/PSVMANet.py 49e6743e36a2c42f recorded tensor:2/float/float32; mean=0, std=0.01 |
[-0.0112584, 0.0084871, 0.00322275, 0.00119842, -0.0135265, 0.00598839, 0.00750189, 0.0138937, …] 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/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