entropy
entropy: 22 implementations from 25 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 16 distinct outputs across 4 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:
- 3 more implementations of this name were examined but did not run on the shared input (RuntimeError 2, ValueError 1).
- 1 more implementation from 1 paper took no array argument and ran only on its own fixture arguments; no shared input existed for it, so it is not compared (on 1 the recorded shared-output digest is the own-fixture digest).
- Every compared output was digested.
- The harness also ran torch's own computation of this name under 6 named conventions; those rows are not implementations, are not counted, and only label a cluster whose digest they share.
Bucket 1 of 4: arg 1: rank 2, kind float, dtype float32
17 implementations from 20 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 11 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 |
|---|---|---|
| 3 implementations 3 papers 7e5824d63f9f recorded values differ by up to 1.19e-07 |
support_alignment/core/algorithms.py 5b9be386 recorded logits:2/float/float32 examples/domain_adaptation/classification/cdan-TransPar.py 74b84c5d recorded output_target:2/float/float32 model/RDA.py 8ae1cfe3 recorded output_target:2/float/float32 |
[1.62273] shape [] · float32 · Tensor |
| 3 implementations 3 papers e0770880d670 recorded values differ by up to 1.19e-07 same digest as torch: softmax_then_entropy |
utils/measures.py 1c1ca7ba recorded y:2/float/float32 train_socc.py 6f956c80 recorded out:2/float/float32 bert_squeeze/models/custom_transformers/deebert.py 76ecddd6 recorded p:2/float/float32 |
[1.47929, 1.45738, 1.82225, 1.73198] shape [4] · float32 · Tensor |
| 2 implementations 3 papers 66ab6f09029c recorded values identical same digest as torch: probs_direct |
timm/models/_uncertainizer.py 888c1a93 recorded probs:2/float/float32 src/methods/stamp.py a643637f recorded p:2/float/float32 |
[nan, nan, nan, nan] shape [4] · float32 · Tensor · non-finite |
| 2 implementations 2 papers eb095794c08d recorded values identical |
snd.py 1b0bf9bd recorded p:2/float/float32; prob=True, mean=True core/apis/inference.py b96aef51 recorded p:2/float/float32; prob=True, mean=True |
[1.62265] shape [] · float32 · Tensor |
| 1 implementation 2 papers 74999fd28ab1 |
one code sha held from 2 papers' repositories models/model.py 6a961f22 recorded input:2/float/float32 |
[nan] shape [] · float32 · Tensor · non-finite |
| 1 implementation 2 papers 947540360b0c |
one code sha held from 2 papers' repositories LGA.py be3aa807 recorded input_:2/float/float32 |
[nan, nan, nan, nan] shape [4] · float32 · Tensor · non-finite |
| 1 implementation 1 paper 0686cec61109 |
torchscale/component/xmoe/routing.py 4b3cc005 recorded probs:2/float/float32 |
[-76.1817, -43.4333, -59.5329, -62.3609] shape [4] · float32 · Tensor |
| 1 implementation 1 paper 804628272603 |
src/prompting/strategies/greedy_strategies.py 1425a704 recorded probs:2/float/float32 |
[-1.42647] shape [] · float32 · Tensor |
| 1 implementation 1 paper b667706f70cb |
vqshape/model.py 2a8f2551 recorded prob:2/float/float32 |
[-55.8906, -33.125, -42.8369, -45.2454] shape [4] · float32 · Tensor |
| 1 implementation 1 paper b7550aa1ec85 |
transformers/modeling_highway_bert.py 87cde55e recorded x:2/float/float32 |
[1.47929, 1.45738, 1.82225, 1.73198] shape [4] · float32 · Tensor |
| 1 implementation 1 paper ceece58b8a49 |
entropy_reconstruction.py 5d7c8a75 recorded embeddings:2/float/float32; kappa=10.0, support='sphere', reduction='expectation' |
[-89.5905] shape [] · float32 · Tensor |
Bucket 2 of 4: arg 1: rank 1, kind float, dtype float32
3 implementations from 3 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 |
|---|---|---|
| 1 implementation 1 paper 2399fcd7f479 same digest as torch: probs_direct |
src/models/_A2C_discrete.py 57a38c7a recorded probs:1/float/float32 |
[nan] shape [] · float32 · Tensor · non-finite |
| 1 implementation 1 paper 62f9956b98df same digest as torch: softmax_then_entropy |
optimize.py 8493af3c recorded w:1/float/float32 |
[1.85562] shape [] · float32 · Tensor |
| 1 implementation 1 paper 74999fd28ab1 |
execute.py f5bc6deb recorded x:1/float/float32 |
[nan] shape [] · float32 · Tensor · non-finite |
Bucket 3 of 4: arg 1: rank 1, kind float, dtype float64
1 implementation from 1 paper 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 |
|---|---|---|
| 1 implementation 1 paper 2399fcd7f479 |
strategies/cbed.py f3d9d8d7 recorded p:1/float/float64 |
[nan] shape [] · float64 · non-finite |
Bucket 4 of 4: arg 1: rank 2, kind float, dtype float64
1 implementation from 1 paper 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 |
|---|---|---|
| 1 implementation 1 paper 06b17e4ae685 |
mnist_mi.py 5fcc1acb recorded vector_prob:2/float/float64 |
[-0.562243, -1.79945, 0.806232, 0.128989] shape [4] · float64 · ndarray |
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/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