l2_norm
l2_norm: 17 implementations from 25 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 8 distinct outputs across 3 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.
- The harness also ran torch's own computation of this name under 6 named conventions; those rows are not implementations, are not counted, and only label a cluster whose digest they share.
Bucket 1 of 3: arg 1: rank 2, kind float, dtype float32
11 implementations from 17 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 4 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 2803cfee2d9a recorded values identical same digest as torch: last_dim |
models/arcface_model.py c54fea42 recorded input:2/float/float32; axis=1
losses.py 45837478 recorded input:2/float/float32 recognition/torchkit/head/localfc/cifp.py 265995c2 recorded input:2/float/float32; axis=1 src/model/margin/adaface.py 27524a6b recorded input_x:2/float/float32; axis=1 easyface/recognition/heads/adaface.py 32e70106 recorded x:2/float/float32; dim=1 main_moco.py 7b15c365 recorded input:2/float/float32 model.py b3008cda recorded x:2/float/float32 models/bottom_up_top_down_ranking.py cb8446a7 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 2 papers 52b2d2679944 same digest as torch: norm_value |
Normal-Estimation/ZTEE/evaluate.py 7f8230b3 recorded v:2/float/float32 |
[2.99171, 3.1385, 2.37496, 2.82426] shape [4] · float32 · ndarray |
| 1 implementation 2 papers bd1303ad1c87 |
trades.py bbffec6a recorded x:2/float/float32 |
[5.69363] shape [1] · float32 · Tensor |
| 1 implementation 1 paper 4171f3b5f627 |
source/models.py a84f15a8 recorded v:2/float/float32; eps=1e-10 |
[0.316604, -0.269384, 0.0836115, -0.121344, -0.158572, -0.180987, -0.116404, 0.100619, …] shape [4, 8] · float32 · Tensor |
Bucket 2 of 3: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
3 implementations from 5 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 |
|---|---|---|
| 2 implementations 3 papers 66687aadf862 recorded values identical |
model/FME_music_positional_encoding.py 0fc5d9cd recorded a:2/float/float32, b:2/float/float32 temos/model/temos.py 840f4276 recorded x1:2/float/float32, x2:2/float/float32; dim=1 |
[0, 0, 0, 0] shape [4] · float32 · Tensor |
| 1 implementation 2 papers fd3f10730196 |
dc_crn.py e150bca4 recorded s1:2/float/float32, s2:2/float/float32 |
[8.95035, 9.8502, 5.64044, 7.97647] shape [4, 1] · float32 · Tensor |
Bucket 3 of 3: arg 1: rank 3, kind float, dtype float32
3 implementations from 3 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 |
|---|---|---|
| 2 implementations 2 papers da14221e68d4 recorded values differ by up to 1.19e-07 |
nlpaug/model/word_embs/word_embeddings.py 2cc7ef3f recorded data:3/float/float32 Linear-Attention-Mechanism.py 3aa98d06 recorded x:3/float/float32 |
[-0.285035, 0.817177, -0.741447, -0.22169, 0.103779, -0.648726, -0.319664, -0.177706, …] shape [2, 4, 8] · float32 · ndarray |
| 1 implementation 1 paper 3acc6bb89f33 |
5_1_5/test_cifar.py 6295da24 recorded x:3/float/float32 |
[5.57122, 5.78202] shape [2] · 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/l2-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