l2norm
l2norm: 12 implementations from 20 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 3 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
12 implementations from 20 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 3 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 18 papers 2803cfee2d9a recorded values differ by up to 5.96e-08 |
CLIP_eval/CLIPure_Cos.py 3eb58dae recorded t:2/float/float32
face-cluster-by-infomap.py 9e5b9ebb recorded vec:2/float/float32
DM-GAN+CL/code/pretrain_DAMSM.py be7c4a67 recorded X:2/float/float32; dim=1, eps=1e-08
LaVIT/models/modeling_visual_tokenzier.py eca6cdf0 recorded t:2/float/float32
model.py 03e1f23d recorded X:2/float/float32; dim=-1, eps=1e-08 byol_pytorch/byol_pytorch.py 09b2eed1 recorded t:2/float/float32 model.py 741174c8 recorded X:2/float/float32 model/cross_modal_attention.py e4fe846f recorded x:2/float/float32 flash_cosine_sim_attention/flash_cosine_sim_attention.py ebc72970 recorded t:2/float/float32 model.py f92e514b 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 |
| 1 implementation 1 paper 52b2d2679944 |
interactive.py f97c5f06 recorded t:2/float/float32 |
[2.99171, 3.1385, 2.37496, 2.82426] shape [4, 1] · float32 · Tensor |
| 1 implementation 1 paper 73f4a3f4fb69 |
models/ours/model.py 8deabf79 recorded inp:2/float/float32; dim=0 |
[0.884224, -0.621319, 0.393432, -0.33966, -0.58261, -0.334824, -0.400333, 0.410058, …] 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/l2norm.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