Home › Census › denormalize

denormalize

Syntologyfunction-name censuscensus 2026-09-22battery b986f7e04d79all samples with this name

denormalize: 9 implementations from 11 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 8 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. 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:

Bucket 1 of 4: arg 1: rank 4, kind float, dtype float32

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); 3 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.

Cluster (same digest to six decimals)MembersShared output on this bucket's input
2 implementations
2 papers
e662d3c07bf6
recorded values identical

models/ZoeDepth/zoedepth/models/zoedepth/zoedepth_v1.py 0a23d935ca395f43
recorded x:4/float/float32

waffle_tools.py 7496518009557dce
recorded images:4/float/float32; means=(0.485, 0.456, 0.406), stds=(0.229, 0.224, 0.225)
[0.650591, 0.634555, 0.816154, 0.736566, 0.745441, 0.439217, 0.422829, 0.675523, …]
shape [2, 3, 4, 4] · float32 · Tensor
1 implementation
2 papers
53994da6dabc
one code sha held from 2 papers' repositories
inference.py 2d094cdb029a3669
recorded images:4/float/float32
[0.861552, 0.82654, 1, 1, 1, 0.400036, 0.364257, 0.91599, …]
shape [2, 3, 4, 4] · float32 · Tensor
1 implementation
1 paper
91893c6722f7

certify_promptsmooth_plip.py 59c2ebaf239e6558
recorded normalized_batch:4/float/float32; mean=(0.48145466, 0.4578275, 0.40821073), std=(0.26862954, 0.26130258, 0.27577711)
[0.675702, 0.656891, 0.869916, 0.776555, 0.786966, 0.427748, 0.408525, 0.704949, …]
shape [2, 3, 4, 4] · float32 · Tensor

Bucket 2 of 4: arg 1: rank 2, 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); 3 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.

Cluster (same digest to six decimals)MembersShared output on this bucket's input
1 implementation
1 paper
1d3f8ee57486

magnitude.py b778ce8816352373
recorded tensor:2/float/float32; min_val=10.0, max_val=20.0
[28.0263, -5.33776, 14.7605, 3.09113, 0.971505, -0.304712, 3.37239, 15.7289, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
2dd79256ed45

Branch_full_ImageNet_1k/recover/data_synthesis_without_optim.py b6cec6dc0ac87904
recorded image_tensor:2/float/float32; use_fp16=False
[0.897802, 0.112434, 0.513112, -0.690887, -0.902849, -1.03047, -0.662761, 0.572889, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
94cdf28f6dc2

src/train_energy_staged.py 600affad5e62864a
recorded y:2/float/float32; max_val=100.0, min_val=0.0
[180.263, -153.378, 47.6053, -69.0887, -90.285, -103.047, -66.2761, 57.2889, …]
shape [4, 8] · float32 · Tensor

Bucket 3 of 4: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 1, kind float, dtype float32 · arg 3: rank 1, 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)MembersShared output on this bucket's input
1 implementation
2 papers
2ed5430599a9
one code sha held from 2 papers' repositories
cadm/dynamics/mlp_cadm_ensemble_cem_dynamics.py 60a2ef2b4904edd8
recorded data_array:2/float/float32, mean:1/float/float32, std:1/float/float32
[-2.53327, -0.083873, 1.32492, -0.235605, -0.0171233, -0.00161594, -0.549174, -0.27924, …]
shape [4, 8] · float32 · Tensor

Bucket 4 of 4: arg 1: rank 3, 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)MembersShared output on this bucket's input
1 implementation
1 paper
fd6bbb4d65d3

test_new.py 8a74ff00c12f2f24
recorded input_data:3/float/float32
[13, 86, 224, 94, 146, 201, 84, 78, …]
shape [2, 4, 8] · uint8 · 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/denormalize.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