norm
norm: 23 implementations from 26 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 15 distinct outputs across 6 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. 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.
- 2 more implementations from 4 papers took no array argument and ran only on their own fixture arguments; no shared input existed for them, so they are not compared (on 2 the recorded shared-output digest is the own-fixture digest).
- Every compared output was digested.
Bucket 1 of 6: arg 1: rank 2, kind float, dtype float32
15 implementations from 18 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 8 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 |
|---|---|---|
| 4 implementations 5 papers 52b2d2679944 recorded values identical |
ebm_models.py e68ef3509ca0d2e9 recorded t:2/float/float32; dim=1 nff/nn/models/painn.py 3df02af32c33da5a recorded vec:2/float/float32 apollo_circle.py dac7f0e24f48b251 recorded x:2/float/float32 heterogeneous/torchmoo/mtl.py f5594684df370bd8 recorded tensor:2/float/float32 |
[2.99171, 3.1385, 2.37496, 2.82426] shape [4] · float32 · Tensor |
| 4 implementations 4 papers 2803cfee2d9a recorded values identical |
model.py 21d247685c39adc6 recorded data:2/float/float32 coco_lm_pytorch/coco_lm_pytorch.py 81e946165f36f51e recorded t:2/float/float32 coco_lm_pytorch/coco_lm_pytorch.py 8774449259dd9b86 recorded t:2/float/float32 cifar_mnist/sep_clr_k-jem.py abb3b39c6e174088 recorded x:2/float/float32 |
[0.60254, -0.512675, 0.159124, -0.230934, -0.301783, -0.344442, -0.221532, 0.191492, …] shape [4, 8] · float32 · Tensor |
| 2 implementations 2 papers fd3f10730196 recorded values identical |
forwardforward.py a76b972fcaf75086 recorded x:2/float/float32; p=2, dim=-1, keepdims=True py_version/transc.py cd402801e7b0ddb3 recorded x:2/float/float32; pnorm=0 |
[8.95035, 9.8502, 5.64044, 7.97647] shape [4, 1] · float32 · Tensor |
| 1 implementation 3 papers 035f1e86888b |
posterior_sample.py 32aa054396114d07 recorded x:2/float/float32 |
[1, 0, 0.738027, 0.154556, 0.0485753, 0, 0.16862, 0.786445, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 8c69b6423dae |
SinGAN/functions.py 0489bfec4716b314 recorded x:2/float/float32 |
[1, -1, -0.0478935, -1, -1, -1, -1, 0.145778, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper bc9e7bc34a68 |
model.py b7b09d9d9a19672a recorded x:2/float/float32 |
[0.60252, -0.512658, 0.159119, -0.230926, -0.301773, -0.34443, -0.221525, 0.191486, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper bd1303ad1c87 |
DeepKnockoffs/DeepKnockoffs/machine.py e1d9c760ce9d1c42 recorded X:2/float/float32; p=2 |
[5.69363] shape [] · float32 · Tensor |
| 1 implementation 1 paper e5506853bb51 |
optimizers/dense/MFAC.py 79cfb98e536acac6 recorded v:2/float/float32 |
[1.03903, 1.52347, 0.366024, 1.03434, 0.600363, 2.36798, 0.685188, 0.487966] shape [8] · float32 · Tensor |
Bucket 2 of 6: arg 1: rank 1, kind float, dtype float64
2 implementations 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 |
|---|---|---|
| 2 implementations 2 papers 337416622ab6 recorded values identical |
Code/NMF/ml_base.py 0c31533258db390a recorded x:1/float/float64 deep_stable.py 8f0218f1e23e4c15 recorded x:1/float/float64 |
[2.22386] shape [] · float64 |
Bucket 3 of 6: arg 1: rank 2, kind float, dtype float64
2 implementations 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); 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 |
|---|---|---|
| 1 implementation 1 paper 771dbde58a2f |
network.py 24c29a6cb4733ecd recorded X:2/float/float64 |
[0.868319, 0.0225855, 0.53205, 0.236246, 0.182517, 0.150166, 0.243376, 0.556597, …] shape [4, 8] · float64 · ndarray |
| 1 implementation 1 paper bd1303ad1c87 |
recapp.py d35071d927f4e662 recorded M:2/float/float64 |
[5.69363] shape [] · float64 |
Bucket 4 of 6: arg 1: rank 4, kind float, dtype float32
2 implementations 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); 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 |
|---|---|---|
| 1 implementation 1 paper 48bf8b9eb7d0 |
dre/mixuploss.py 2d1316f9f86a0471 recorded x:4/float/float32 |
[0.728997, 0.713934, 0.884524, 0.80976, 0.818097, 0.530436, 0.515043, 0.752418, …] shape [2, 3, 4, 4] · float32 · Tensor |
| 1 implementation 1 paper e915b985d5de |
attack.py c0bd0f11c7d847e7 recorded t:4/float/float32; p=2 |
[6.60307, 8.35964] shape [2, 1, 1, 1] · float32 · Tensor |
Bucket 5 of 6: arg 1: rank 1, 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 ebfdf9421e6b |
class_estimate.py d4d831024e44fed8 recorded s:1/float/float32 |
[0.286831, 0.706863, 1, 0.342924, 0.574883, 0.665652, 0, 0.574377] shape [8] · float32 · Tensor |
Bucket 6 of 6: arg 1: rank 2, kind int, dtype uint8
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 e681dbad78b8 |
ComputeDice.py 8cedd657c11f6f8c recorded im:2/int/uint8 |
[0.666667, 1, 0.666667, 0.333333, 0.333333, 1, 0, 0.333333, …] shape [4, 8] · float32 · ndarray |
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/norm.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