sigmoid
sigmoid: 36 implementations from 56 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 7 distinct outputs across 3 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:
- Every examined implementation of this name that took an array argument ran on the shared input.
- 5 more implementations from 7 papers took no array argument and ran only on their own fixture arguments; no shared input existed for them, so they are not compared (on 5 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 3 named conventions; those rows are not implementations, are not counted, and only label a cluster whose digest they share.
Bucket 1 of 3: arg 1: rank 1, kind float, dtype float64
18 implementations from 36 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 4 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 |
|---|---|---|
| 15 implementations 33 papers 2091c6f76ede recorded values differ by up to 5.55e-17 |
Model/MuSeGNN_all_tissues.py b8e95809 recorded x:1/float/float64
scripts/metrics/calculate_AR_RPR.py f35babe3 recorded x:1/float/float64
algos/dps.py 152398a5 recorded x:1/float/float64 one code sha held from 2 papers' repositories svm_logreg/logreg.py a911f9ca recorded z:1/float/float64
logistic.py b30dd0f0 recorded x:1/float/float64
test_iteration_conf_gnn.py b7880bde recorded inX:1/float/float64 zero-shot/zero_shot.py 1846a09d recorded x:1/float/float64
RVFL.py 1a3c174f recorded x:1/float/float64 main_1d_20190924.py 2d3e248b recorded xx:1/float/float64 random_mutation_search.py 2f53c83e recorded x:1/float/float64 disentanglement_lib/visualize/visualize_model.py 4adb351c recorded x:1/float/float64 algorithms.py 549a2707 recorded inx:1/float/float64 glad.py 6c965eb3 recorded x:1/float/float64 hierarchical/mixed_level1.py ea4aa57f recorded z:1/float/float64 PeerLoss.py f082a972 recorded z:1/float/float64 |
[0.288252, 0.539202, 0.710459, 0.31817, 0.45605, 0.513255, 0.164044, 0.455733] shape [8] · float64 · ndarray |
| 1 implementation 1 paper a95d9807cc1e |
dataset.py 0ed3188e recorded x:1/float/float64; L=1.0, x0=2.5, k=1.0, b=0.0 |
[0.0321741, 0.0876343, 0.167648, 0.0368911, 0.0643891, 0.0796605, 0.0158526, 0.0643122] shape [8] · float64 · ndarray |
| 1 implementation 1 paper cb4c711ae1bf |
evosoro/tools/utils.py 697dfbb9 recorded x:1/float/float64 |
[-0.423496, 0.0784045, 0.420917, -0.36366, -0.0879003, 0.0265096, -0.671912, -0.0885343] shape [8] · float64 · ndarray |
| 1 implementation 1 paper cc60658c28a2 |
imagenet.py c4ae0f42 recorded x:1/float/float64; beta=0.8 |
[0.326708, 0.531385, 0.672186, 0.352115, 0.464807, 0.510605, 0.213702, 0.464553] shape [8] · float64 · ndarray |
Bucket 2 of 3: arg 1: rank 2, kind float, dtype float64
13 implementations from 13 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 |
|---|---|---|
| 12 implementations 12 papers cac27aad11ab recorded values differ by up to 8.29e-08 |
image_classification/assistant.py 19ed4e8d recorded x:2/float/float64 transformer.py 1f96ec62 recorded hs:2/float/float64 DP_FL_MNIST_logistic_FINAL.py 58eb8e19 recorded z:2/float/float64 predict.py 5f33cd04 recorded z:2/float/float64 nmodel.py 604c5823 recorded x:2/float/float64 train_lottery.py 6bb3881c recorded x:2/float/float64 maxoutCNN.py 78fdd436 recorded array:2/float/float64; deriv=False mll_sgd.py c803a6bd recorded z:2/float/float64 src/oxonfair/learners/fair_frontier.py d05c71a4 recorded x:2/float/float64
src/ppi_aipw/_api.py d3cb240d recorded z:2/float/float64 prompteval/methods.py d4621865 recorded x:2/float/float64 RBM_ICML.py e21f8508 recorded x:2/float/float64 |
[0.858469, 0.177442, 0.616815, 0.333836, 0.288465, 0.262993, 0.34012, 0.63943, …] shape [4, 8] · float64 · ndarray |
| 1 implementation 1 paper 886b5e96fd4d |
dev/model_validation_experiment.py 8716af66 recorded x:2/float/float64; k=5.0, x0=0.5 |
[0.998518, 3.83437e-05, 0.470102, 0.0025876, 0.000898175, 0.000474698, 0.00297716, 0.590116, …] shape [4, 8] · float64 · ndarray |
Bucket 3 of 3: arg 1: rank 2, kind float, dtype float32
5 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); 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 |
|---|---|---|
| 5 implementations 7 papers c774619a31ae recorded values identical same digest as torch: torch |
muxnet.py 1ab2898f recorded x:2/float/float32; inplace=False
src/Smooth_AP_loss.py 4b3a13b8 recorded tensor:2/float/float32; temp=1.0 models/sparsefunc.py 6ed27939 recorded z:2/float/float32 models/common.py a74710df recorded logits:2/float/float32; hard=False, threshold=0.5 Online Platt Scaling with Calibeating/calibration.py f8558288 recorded x:2/float/float32 |
[0.858469, 0.177442, 0.616816, 0.333836, 0.288465, 0.262993, 0.34012, 0.63943, …] shape [4, 8] · 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/sigmoid.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