Home › Census › soft_cross_entropy

soft_cross_entropy

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

soft_cross_entropy: 6 implementations from 8 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 3 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 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32

5 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); 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
3 implementations
4 papers
ba10c57de7de
recorded values identical
one code sha held from 2 papers' repositories
lightning_subset/module.py 49e2f0c5
recorded pred:2/float/float32, soft_targets:2/float/float32

label_distillation_or2.py 7b40608d
recorded pred:2/float/float32, soft_targets:2/float/float32

validate/train_fkd.py cef161c1
recorded logits:2/float/float32, soft_targets:2/float/float32
[-9.50814]
shape [] · float32 · Tensor
2 implementations
2 papers
7e5824d63f9f
recorded values identical

DynaBERT/run_glue.py 32fee351
recorded predicts:2/float/float32, targets:2/float/float32

minima/run_distillation_llama_ds.py 5ea641b9
recorded input:2/float/float32, target:2/float/float32; reduction='mean'
[1.62273]
shape [] · float32 · Tensor

Bucket 2 of 2: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, 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
17b520c2acab
one code sha held from 2 papers' repositories
scood/trainers/udg_trainer.py 61492b34
recorded logit:2/float/float32, label:2/float/float32, weight:1/float/float32; reduce=None, reduction='mean'
[6.13653]
shape [] · 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/soft-cross-entropy.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