Home › Census › PatchEmbed

PatchEmbed

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

PatchEmbed: 9 implementations from 9 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 6 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. 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 1: arg 1: rank 4, kind float, dtype float32

9 implementations from 9 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 6 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
4 implementations
4 papers
4b26d71478ef
recorded values identical
class
src/models/controlnet.py 9f2cdbcb2103e1b1
recorded x:4/float/float32
class
models/early_exit.py ec9ee9d94615bfe4
recorded x:4/float/float32
class
code/sam_lora_image_encoder.py f2e2fb9b20af67da
recorded x:4/float/float32
class
MAS-SAM/sam_lora_image_encoder.py f6ebdaee467a4c18
recorded x:4/float/float32
[0.348175, 1.01024, 0.73749, -0.796148, -0.622522, 0.808107, 0.00856404, 0.685411, …]
shape [2, 1, 64] · float32 · Tensor
1 implementation
1 paper
1c7b7fb077fb
class
github_adventures/vision_transformer/custom.py 029dccee9f606fea
recorded x:4/float/float32
[0.105576, 0.163156, 0.504275, 0.225562, 0.102961, -1.30615, 0.696312, 0.225237, …]
shape [2, 4, 4] · float32 · Tensor
1 implementation
1 paper
25b9213ce983
class
holitracer/vector/models/base.py 327417879fa4f7c7
recorded x:4/float/float32
[1.37571, 0.312234, 1.25438, 1.72211, 0.886932, -2.2416, -0.067527, 0.376441, …]
shape [2, 8, 2, 2] · float32 · Tensor
1 implementation
1 paper
e028154e7ffb
class
models/two_dim_sequencer.py d21dc0c3ff2326b2
recorded x:4/float/float32
[-0.941327, -0.565096, 1.66376, -0.15734, 0.232068, -1.65413, 1.02631, 0.395745, …]
shape [2, 4, 4] · float32 · Tensor
1 implementation
1 paper
e21f16b77362
  • arXiv:2507.00698
class
classfication_release/model.py 2fa20567486ec78e
recorded x:4/float/float32
[0.999973, -0.998731, 0.999358, -0.999778, 0.997153, 0.999654, -0.998169, -0.999834, …]
shape [2, 96, 1, 1] · float32 · Tensor
1 implementation
1 paper
e697da6b24b6
class
radio/eradio_model.py 8aeb7bbb05b7dbbe
recorded x:4/float/float32
[0, 0.999904, 0, 0.985024, 0, 0.999955, 0.999469, 0.999103, …]
shape [2, 16, 1, 1] · 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/patchembed.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