Home › Census › reparameterize
reparameterize
reparameterize: 12 implementations from 17 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 5 distinct outputs across 4 buckets, one shared input per bucket.
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 4: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
9 implementations from 13 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 |
|---|---|---|
| 8 implementations 12 papers 6daa96efdfc7 recorded values identical |
model.py 3cd91116 recorded mu:2/float/float32, logvar:2/float/float32
models/kovae.py dadec7f7 recorded mean:2/float/float32, logvar:2/float/float32; random_sampling=True Models.py 26ebad4d recorded mu:2/float/float32, logvar:2/float/float32 model/crvae_model.py 2f6aa7a6 recorded mu:2/float/float32, log_var:2/float/float32; sampling_distribution=Normal(loc: 0.0, scale: 1.0) model.py 447585e6 recorded mu:2/float/float32, logvar:2/float/float32 model.py 588fadd7 recorded mu:2/float/float32, logsigma:2/float/float32
src/pgmc/vae_models.py 8425038d recorded mu:2/float/float32, logvar:2/float/float32 pgvae/pgvae.py c28f74f4 recorded mu:2/float/float32, logvar:2/float/float32; batch_rng=<fx_c28f74f4a6577670__reparameterize.BatchRNG object at 0xff |
[-0.970132, -2.069, 0.158133, -0.998033, -0.362458, -0.617093, -0.889637, -2.24392, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 32bde78b5057 |
models/mnist.py d7b93d9b recorded mu:2/float/float32, logvar:2/float/float32; n_samples=3 |
[-0.970132, -2.069, 0.158133, -0.998033, -0.362458, -0.617093, -0.889637, -2.24392, …] shape [3, 4, 8] · float32 · Tensor |
Bucket 2 of 4: 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 · arg 5: rank 2, kind float, dtype float32
1 implementation from 1 paper 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 1 implementation 1 paper b2d13af9d050 |
modules/layers.py d71a61ef recorded mu:2/float/float32, sigma:2/float/float32, a:2/float/float32, b:2/float/float32, y:2/float/float32; eps=1e-05 |
[6.06557, 0.21572, 1.60971, 0.501131, 0.405413, 0.356839, 0.515426, 1.77338, …] shape [4, 8] · float32 · Tensor |
Bucket 3 of 4: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
1 implementation from 2 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 1 implementation 2 papers c3a1cab1d3de |
src/dvip.py 2a884630 recorded mean:2/float/float32, var:2/float/float32, z:2/float/float32; full_cov=False |
[4.22287, nan, 0.804514, nan, nan, nan, nan, 1.00651, …] shape [4, 8] · float32 · Tensor · non-finite |
Bucket 4 of 4: arg 1: rank 2, kind float, dtype float32
1 implementation from 1 paper 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 1 implementation 1 paper a28edada04cb |
models/mmali/factor2.py efc66d60 recorded z:2/float/float32 |
[1.08578, -2.22215, 0.296155, -1.26868, 1.25357, 3.16894, -0.641498, -4.35384, …] shape [4, 4] · 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/reparameterize.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