Home › Census › softmax_entropy
softmax_entropy
softmax_entropy: 18 implementations from 29 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 4 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. 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:
- Every examined implementation of this name that took an array argument ran on the shared input.
- No implementation of this name ran on its own fixture arguments only: every one that ran took an array argument.
- Every compared output was digested.
- The harness also ran torch's own computation of this name under 3 named conventions; those rows are not implementations, are not counted, and only label a cluster whose digest they share.
Bucket 1 of 2: arg 1: rank 2, kind float, dtype float32
15 implementations from 25 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 3 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.
| Cluster (same digest to six decimals) | Members | Shared output on this bucket's input |
|---|---|---|
| 12 implementations 21 papers e0770880d670 recorded values identical same digest as torch: tent |
map_nav_src/models/FSTTA.py 3078648c75e3e1e3 recorded x:2/float/float32
src/main_task_wise_adamerging.py c2df94ca3de67eb0 recorded x:2/float/float32
domainbed/scripts/unsupervised_adaptation.py e6171e29ed623a12 recorded x:2/float/float32
src/learn_few_shots.py 60e9cb8fea03027c recorded x:2/float/float32
TTAs-2/E-BATS.py c549267af6d34f9a recorded x:2/float/float32; dim=-1
tta_library/zotta.py 1bdb21f20be90a8f recorded x:2/float/float32 eata.py 1ddd5315f5202ec9 recorded x:2/float/float32 src/sumi.py 311413feee2ab1dd recorded x:2/float/float32 tent.py 5f3e7b3e8f7ad589 recorded x:2/float/float32 sar.py 8f4830ebee73f4a1 recorded x:2/float/float32
tta_library/beta.py 99c9d70a0d3706d9 recorded logits:2/float/float32 tent.py be510b4c74ce8440 recorded x:2/float/float32 |
[1.47929, 1.45738, 1.82225, 1.73198] shape [4] · float32 · Tensor |
| 2 implementations 3 papers 2ce2016ced5f recorded values identical |
learner/sotta.py a9edd84f4eedeec8 recorded x:2/float/float32
ProtoPFormer/proto_tta.py 9ccab176a6977060 recorded logits:2/float/float32 |
[1.47928, 1.45737, 1.82224, 1.73197] shape [4] · float32 · Tensor |
| 1 implementation 1 paper 7e5824d63f9f |
methods/das.py db8b634a36fc3530 recorded x:2/float/float32 |
[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
3 implementations from 4 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 3 implementations 4 papers e0770880d670 recorded values identical |
src/adapter/petta.py 8cc4004512e3fa2f recorded x:2/float/float32, x_ema:2/float/float32
cotta_vit_opd.py 6aa4e7aea80769c7 recorded x:2/float/float32, x_ema:2/float/float32 imagenet/cotta.py 867d3ea552eca91a recorded x:2/float/float32, x_ema:2/float/float32 |
[1.47929, 1.45738, 1.82225, 1.73198] shape [4] · 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/softmax-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