Home › Census › log

log

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

log: 10 implementations from 16 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 7 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

10 implementations from 16 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 7 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
3 implementations
3 papers
2194d6f35f20
recorded values identical
one code sha held from 2 papers' repositories
marge_pytorch/autoregressive_wrapper.py 6269424d608eba34
recorded t:2/float/float32; eps=1e-09

coco_lm_pytorch/coco_lm_pytorch.py 5926a238cd968779
recorded t:2/float/float32; eps=1e-09

electra_pytorch/electra_pytorch.py c01e5c8df433613c
recorded t:2/float/float32; eps=1e-09
[0.589246, nan, -0.742226, nan, nan, nan, nan, -0.557063, …]
shape [4, 8] · float32 · Tensor · non-finite
2 implementations
6 papers
95f9ebd4dcc0
recorded values identical
one code sha held from 5 papers' repositories
speculative_decoding/speculative_decoding.py b5472673332de78e
recorded t:2/float/float32; eps=1e-20

vectree/vectree.py 0a7e4f0159ab841a
recorded t:2/float/float32; eps=1e-20
[0.589246, -46.0517, -0.742226, -46.0517, -46.0517, -46.0517, -46.0517, -0.557063, …]
shape [4, 8] · float32 · Tensor
1 implementation
3 papers
7948875a4f52
one code sha held from 3 papers' repositories
diffusion/text_denoising_diffusion.py d93be7ef30d67f1e
recorded t:2/float/float32; eps=1e-12
[0.589246, -27.631, -0.742226, -27.631, -27.631, -27.631, -27.631, -0.557063, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
3fd84e3d9f2b

vit_pytorch/ats_vit.py 8f3eea58724263db
recorded t:2/float/float32; eps=1e-06
[0.589247, nan, -0.742223, nan, nan, nan, nan, -0.557061, …]
shape [4, 8] · float32 · Tensor · non-finite
1 implementation
1 paper
a54a279e425b

src/losses.py b1951f4f25d8e36c
recorded x:2/float/float32
[0, -18.4207, -0.742226, -18.4207, -18.4207, -18.4207, -18.4207, -0.557063, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
ac559b556f48

vqshape/model.py 7d6c3243647c53d9
recorded t:2/float/float32; eps=1e-05
[0.589246, -11.5129, -0.742226, -11.5129, -11.5129, -11.5129, -11.5129, -0.557063, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
f3ecf67148c4

editor/horse.py 0974a4d82bf5f79d
recorded x:2/float/float32
[0.589246, nan, -0.742225, nan, nan, nan, nan, -0.557063, …]
shape [4, 8] · float32 · Tensor · non-finite

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/log.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