preprocess
preprocess: 11 implementations from 13 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 10 distinct outputs across 5 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:
- 4 more implementations of this name were examined but did not run on the shared input (RuntimeError 2, IndexError 1, ValueError 1).
- 3 more implementations from 5 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 3 the recorded shared-output digest is the own-fixture digest).
- Every compared output was digested.
Bucket 1 of 5: arg 1: rank 2, kind float, dtype float32
4 implementations from 4 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 |
|---|---|---|
| 2 implementations 2 papers 48e680d0884b recorded values identical |
scripts/train_2d_image.py 1194fc2f recorded img_tensor:2/float/float32 adversarial_reprogram.py b49e330f recorded img:2/float/float32 |
[2.60526, -4.06755, -0.0478935, -2.38177, -2.8057, -3.06094, -2.32552, 0.145778, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 0a0fa7893b5b |
FedEP/FLAlgorithms/users/spca.py e8a2974b recorded x:2/float/float32 |
[0.704148, -0.442548, 0.248215, -0.152854, -0.225704, -0.269566, -0.143187, 0.281496, …] shape [4, 8] · float32 · ndarray |
| 1 implementation 1 paper d9c1aed2ac1b |
Copycat_CNN-Expansion/01-classification_space-TSNE/experiment-01-DIG10/tsne.py e3f8928f recorded X:2/float/float32 |
[1.49678, -0.947885, 0.2319, -0.299953, -0.61298, -0.918218, 0.29216, 0.331433, …] shape [4, 8] · float32 · ndarray |
Bucket 2 of 5: arg 1: rank 4, kind int, dtype uint8
4 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); 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 |
|---|---|---|
| 1 implementation 2 papers 95b953d72b25 |
defenses/ABS/abs_pytorch_round1.py 06fcb055 recorded img:4/int/uint8 |
[0.0117647, 0.00784314, 0, 0.0117647, 0.00784314, 0, 0.0117647, 0, …] shape [2, 4, 3, 4] · float32 · ndarray |
| 1 implementation 1 paper 3e8637d8686a |
render.py 967a6852 recorded images:4/int/uint8 |
[-0.976471, -0.984314, -1, -0.976471, -0.984314, -1, -0.976471, -1, …] shape [2, 4, 3, 4] · float32 · Tensor |
| 1 implementation 1 paper 61b71998a4cd |
detoxification.py 9205308a recorded x_in:4/int/uint8 |
[-1.94159, -1.96413, -1.66202, 0, -1.95747, -1.94802, -1.69201, 2, …] shape [2, 3, 4, 4] · float32 · ndarray |
| 1 implementation 1 paper d93468965ca7 |
train_images.py d0e563c3 recorded x:4/int/uint8 |
[0.988235, 0.992157, 1, 0.988235, 0.992157, 1, 0.988235, 1, …] shape [2, 4, 3, 4] · float64 · ndarray |
Bucket 3 of 5: arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32 · arg 3: rank 3, 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 8b4895091311 |
evaluate_model.py 77ff24f1 recorded x:3/float/float32, pixel_mean:3/float/float32, pixel_std:3/float/float32; img_size=1024 |
[-0, 0, -0, -0, 0, -0, -0, -0, …] shape [2, 1024, 1024] · float32 · Tensor |
Bucket 4 of 5: arg 1: rank 3, kind float, dtype float64
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 17e9e5918229 |
utils/attention_flow.py 7c84ea3a recorded layer_attn:3/float/float64; n_words=3 |
[0.118748, 2.81709, -1.93584, -0.531067, 0.575045, -0.402134, -0.148058, 0.680208, …] shape [4, 8] · float64 · ndarray |
Bucket 5 of 5: arg 1: rank 6, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64
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 0df3cf00dea9 |
train_vcp.py 56662da1 recorded inputs:6/float/float32, targets:1/int/int64 |
[0.668295, -1.57255, 0.0160641, 1.36997, -0.28447, -0.211828, 0.8614, 0.743046, …] shape [2, 2, 2, 2, 2, 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/preprocess.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