normal_kl
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:
- 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 · 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 10 implementations 20 papers bcf4c54db9a3 recorded values identical |
diffusion/diffusion_utils.py 8afbfc42 recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
ddpm.py 4707efa9 recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
diffusion/gaussian_diffusion.py cf2798b6 recorded mean1:2/float/float32, logvar1:2/float/float32, mean2:2/float/float32, logvar2:2/float/float32
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
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 |
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