Home › Census › Conv

Conv

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

Conv: 8 implementations from 8 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 8 distinct outputs across 2 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:

Bucket 1 of 2: arg 1: rank 4, kind float, dtype float32

6 implementations from 6 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
1 implementation
1 paper
16db17812ebd
class
training_testing_code/LISPLUT/LISPLUT_M.py 334cc5c9
recorded x:4/float/float32
[-0.661603, 0.404552, 0.754689, -0.970863, -1.16408, 1.01219, 0.881081, -1.96136, …]
shape [2, 4, 4, 4] · float32 · Tensor
1 implementation
1 paper
35590a9242c1
class
MAS-SAM/sam_lora_image_encoder.py aa1d3f6e
recorded x:4/float/float32
[1.9104, -0.0570247, -0.106393, 0.0120317, 0.607098, -0.0598723, -0.150487, 0.696993, …]
shape [2, 4, 4, 4] · float32 · Tensor
1 implementation
1 paper
607026b564fc
class
radio/eradio_model.py 23523ebc
recorded x:4/float/float32
[1.7174, -0.0594097, -0.117045, 0.0119486, 0.532215, -0.251671, -0.181629, 0.608185, …]
shape [2, 4, 4, 4] · float32 · Tensor
1 implementation
1 paper
669bfe71a452
class
model/hourglass.py 2573d074
recorded x:4/float/float32
[1.95945, 0, 0, 0.0236183, 0.776935, 0, 0, 0.864413, …]
shape [2, 4, 4, 4] · float32 · Tensor
1 implementation
1 paper
ba487e4ef64b
class
models/DSCNet.py f279a135
recorded x:4/float/float32
[1.35942, 0, 0, 0, 0.332252, 0, 0, 0.408238, …]
shape [2, 8, 4, 4] · float32 · Tensor
1 implementation
1 paper
ca9c0e6998de
class
unlearn.py d574992e
recorded input:4/float/float32
[1.95945, 0, 0, 0.0236183, 0.776935, 0, 0, 0.864413, …]
shape [2, 4, 4, 4] · float32 · Tensor

Bucket 2 of 2: arg 1: rank 3, kind float, dtype float32

2 implementations 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); 2 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
4d8c4909babf
class
bddm/models/diffwave.py 267f77d5
recorded x:3/float/float32
[0.158444, 0.949217, 0.157169, 0.622094, 0.399472, -0.00928695, 0.182535, -0.000131861, …]
shape [2, 8, 8] · float32 · Tensor
1 implementation
1 paper
6ee758442e43
class
WaveNet.py 2a41b9a5
recorded signal:3/float/float32
[-1.17791, 1.1353, -0.619868, 0.203455, 0.344583, -0.488272, -0.625739, 1.33683, …]
shape [2, 3, 6] · 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/conv.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