Home › Census › to_var

to_var

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

to_var: 12 implementations from 21 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 1 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 2, kind float, dtype float32

12 implementations from 21 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
12 implementations
21 papers
d7bd5ceec8a6
recorded values identical
one code sha held from 5 papers' repositories
models.py 502c50812b7f31ab
recorded x:2/float/float32; volatile=False
one code sha held from 3 papers' repositories
section4/Class_Imbalance/LT1.py a2f6a25906e664c5
recorded x:2/float/float32; requires_grad=True
one code sha held from 3 papers' repositories
run_pplm.py bbebd95a156061b0
recorded x:2/float/float32; requires_grad=True, volatile=False, device='cpu'
one code sha held from 2 papers' repositories
trainer.py 21adbeb5db124ddb
recorded x:2/float/float32; requires_grad=True
one code sha held from 2 papers' repositories
model.py 2cddc9768ef9402a
recorded x:2/float/float32; requires_grad=True

model.py 36326e7b5eb789e9
recorded x:2/float/float32

paper_code/pplm.py 8857afb4339bfbee
recorded x:2/float/float32; requires_grad=False, volatile=False

multiple_attribute/model.py 8c20544f7278d430
recorded x:2/float/float32; cuda2=device(type='cpu'), volatile=False

poison_rli_agr_twp.py a56c253f53bf5251
recorded x:2/float/float32; requires_grad=False

train/discoeval_example.py ad808d0123ba9821
recorded inputs:2/float/float32; model=MinimalModel( (linear): Linear(in_features=4, out_features

desire/nn/cvae.py c87e08e7b5f708e9
recorded x:2/float/float32

my_sinkhorn_ops.py d35744eb1d104e9b
recorded x:2/float/float32
[1.80263, -1.53378, 0.476053, -0.690887, -0.902849, -1.03047, -0.662761, 0.572889, …]
shape [4, 8] · 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/to-var.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