Home › Census › gumbel_softmax_sample

gumbel_softmax_sample

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

gumbel_softmax_sample: 14 implementations from 16 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.

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

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

14 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); 4 distinct outputs, 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
11 implementations
12 papers
4b71b65a282d
recorded values differ by up to 1.86e-08
one code sha held from 2 papers' repositories
vqapc_model.py 4650349b
recorded logits:2/float/float32; temperature=0.5

model_vmtl.py 09ef8173
recorded logits:2/float/float32; temperature=0.5

vision/quantizer.py 545203c7
recorded logits:2/float/float32; temperature=0.5

ibr_game/finetune.py 626e470a
recorded logits:2/float/float32; temp=0.5

maddpg-pytorch/algorithms/maddpg.py 6697676f
recorded logits:2/float/float32; temperature=0.5

cgae.py 6bd331cf
recorded logits:2/float/float32; temperature=0.5, device='cpu'

ec-game/models.py 7a26c95f
recorded logits:2/float/float32; temp=0.5, tt=<module 'torch' from '/usr/local/lib/python3.11/site-package, idx_=10

models_dy.py 8c49f9e9
recorded logits:2/float/float32; temperature=0.5

distributions/gumbel.py d069f664
recorded logits:2/float/float32; temperature=0.5, device=device(type='cpu')

model/pytorch/model.py d925dcd1
recorded logits:2/float/float32; temperature=0.5

models/LSINet.py fce7e942
recorded logits:2/float/float32; temperature=0.5, eps=1e-10, device=None
[0.220078, 0.00196556, 0.00129395, 0.000179896, 0.000346918, 0.00180161, 0.00153395, 0.7728, …]
shape [4, 8] · float32 · Tensor
1 implementation
2 papers
2ddd2140e02e
one code sha held from 2 papers' repositories
model_search.py 0d41bbe5
recorded logits:2/float/float32; temperature=1.0
[0.304198, 0.0287482, 0.0233253, 0.00869719, 0.0120776, 0.0275231, 0.0253964, 0.570035, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
54a41cc63543

imgnet_models/hypernet.py 82162a60
recorded logits:2/float/float32; T=0.5, offset=0
[0.986832, 0.400954, 0.305856, 0.0577232, 0.105653, 0.380227, 0.34312, 0.996214, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
8de8fd95c344

model/GroupNet_nba.py 2cecb123
recorded logits:2/float/float32; tau=1.0, eps=1e-10
[0.60614, 0.0818282, 0.0120068, 0.134808, 0.105253, 0.0575458, 0.349442, 0.348225, …]
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/gumbel-softmax-sample.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