Home › Census › normal_kl

normal_kl

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

normal_kl: 14 implementations from 24 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:

Bucket 1 of 1: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32

14 implementations from 24 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)MembersShared output on this bucket's input
10 implementations
20 papers
bcf4c54db9a3
recorded values identical
one code sha held from 4 papers' repositories
diffusion/diffusion_utils.py 8afbfc42
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
one code sha held from 3 papers' repositories
ddpm.py 4707efa9
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
one code sha held from 3 papers' repositories
diffusion/gaussian_diffusion.py cf2798b6
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
one code sha held from 2 papers' repositories
turbdiff/models/ddpm.py 52471728
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
one code sha held from 2 papers' repositories
DSTPP/DiffusionModel.py c3bf3f13
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
one code sha held from 2 papers' repositories
train_generation.py ec4a40e4
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32

MoH-DiT/diffusion/diffusion_utils.py 3f37a54a
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32

models/losses.py 75cca248
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32

DSTPP/DiffusionModel.py 97ca6069
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32

improved_diffusion/respace.py a9f45d5b
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
[0, 0, 0, 2.98023e-08, 2.98023e-08, -5.96046e-08, 0, 0, …]
shape [4, 8] · float32 · Tensor
4 implementations
5 papers
5341e6b26469
recorded values identical
one code sha held from 2 papers' repositories
src/vae_models.py 01efe1f4
recorded mu1:2/float/float32, lv1:2/float/float32, mu2:2/float/float32, lv2:2/float/float32

VKS_node.py 5a9b90e8
recorded mu1:2/float/float32, lv1:2/float/float32, mu2:2/float/float32, lv2:2/float/float32

ddpm_torch/diffusion.py 9537f40a
recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32

examples/latent_ode.py ef202a31
recorded mu1:2/float/float32, lv1:2/float/float32, mu2:2/float/float32, lv2:2/float/float32
[0, 0, 0, 0, 0, 0, 0, 0, …]
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/normal-kl.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