kl_divergence
kl_divergence: 18 implementations from 18 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 15 distinct outputs across 7 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:
- 2 more implementations of this name were examined but did not run on the shared input (RuntimeError 2).
- 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.
Bucket 1 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
7 implementations from 7 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 6 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 |
|---|---|---|
| 2 implementations 2 papers 74999fd28ab1 recorded values identical |
discor/algorithm/rlkit/torch/iwq/iwq.py 310c6961 recorded mu:2/float/float32, std:2/float/float32 models/cool.py 79ad7949 recorded input:2/float/float32, target:2/float/float32; dim=2, version='nesy' |
[nan] shape [] · float32 · Tensor · non-finite |
| 1 implementation 1 paper 31ac516f930a |
models.py b7ecf10c recorded means:2/float/float32, log_sigma:2/float/float32; dim=4, target_sigma=0.1 |
[365.289] shape [] · float32 · Tensor |
| 1 implementation 1 paper 66687aadf862 |
src/scripts/train_SIDDA.py fc8000b2 recorded p:2/float/float32, q:2/float/float32 |
[0, 0, 0, 0] shape [4] · float32 · Tensor |
| 1 implementation 1 paper 947540360b0c |
src/mira_sim/metrics/kldiv/kld_metric.py ee53047b recorded pred_probs:2/float/float32, target_probs:2/float/float32; epsilon=1e-06 |
[nan, nan, nan, nan] shape [4] · float32 · Tensor · non-finite |
| 1 implementation 1 paper af5570f5a181 |
lib/SHIPS/get_ships.py 2c199cf0 recorded base_pd:2/float/float32, mask_pd:2/float/float32 |
[0] shape [] · float32 · Tensor |
| 1 implementation 1 paper cf3999a9f556 |
XOR_MNIST/models/mnistpcbmdpl.py 7f0ddf1b recorded mu:2/float/float32, logsigma:2/float/float32; reduction='mean' |
[6.66104] shape [] · float32 · Tensor |
Bucket 2 of 7: arg 1: rank 1, kind float, dtype float64 · arg 2: rank 1, kind float, dtype float64
5 implementations from 5 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 |
|---|---|---|
| 3 implementations 3 papers 9402bb655bc3 recorded values identical |
mmd_dilated/mmd_dilated.py 5b9b7639 recorded probs1:1/float/float64, probs2:1/float/float64
stratifiers/StratifierKullbackLeibler.py 8c91bd64 recorded a:1/float/float64, b:1/float/float64
tool/managed_system_cv/mape_logic/monitor.py fcef7b2c recorded p:1/float/float64, q:1/float/float64 |
[inf] shape [] · float64 · non-finite |
| 1 implementation 1 paper af5570f5a181 |
03_1_DR_Diff_matrix_generator.py 08d9e207 recorded p:1/float/float64, q:1/float/float64 |
[0] shape [] · float64 |
| 1 implementation 1 paper f5a5fd42d16a |
model/method.py d326593f recorded a:1/float/float64, b:1/float/float64 |
[1e-10, 1e-10, 1e-10, 1e-10, 1e-10, 1e-10, 1e-10, 1e-10] shape [8] · float64 · ndarray |
Bucket 3 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
2 implementations 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); 2 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 5341e6b26469 |
VDPO.py 9af8fadc recorded mu1:2/float/float32, sigma1:2/float/float32, mu2:2/float/float32, sigma2:2/float/float32 |
[0, 0, 0, 0, 0, 0, 0, 0, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 1 paper 66687aadf862 |
ebmdg_main.py cb955692 recorded mu_q:2/float/float32, sigma_q:2/float/float32, mu_p:2/float/float32, sigma_p:2/float/float32 |
[0, 0, 0, 0] shape [4] · float32 · Tensor |
Bucket 4 of 7: arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind float, dtype float32
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 ed5f4528b943 |
openrlhf/models/model_inform.py 04d7f678 recorded mu:1/float/float32, logvar:1/float/float32 |
[0.431754] shape [] · float32 · Tensor |
Bucket 5 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 1, kind float, dtype float32 · arg 3: rank 1, kind float, dtype float32
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 74999fd28ab1 |
generation/group_sampling.py 652cccb3 recorded selected_points:2/float/float32, mean:1/float/float32, std:1/float/float32; device=device(type='cpu') |
[nan] shape [] · float64 · float · non-finite |
Bucket 6 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
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 af5570f5a181 |
src/models/custom_loss.py 6a0687b0 recorded reference:2/float/float32, pred:2/float/float32, mask:2/float/float32; is_gt=False |
[0] shape [] · float32 · Tensor |
Bucket 7 of 7: arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
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 af5570f5a181 |
src/sami/trainers/sami_trainer.py 84501014 recorded policy_logits:3/float/float32, ref_logits:3/float/float32 |
[0] 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/kl-divergence.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