DropPath
DropPath: 17 implementations from 17 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 8 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:
- 1 more implementation of this name was examined but did not run on the shared input (RuntimeError 1).
- 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.
- 17 compared members are class-bearing (tagged class): the class was constructed with seeded weights in evaluation mode and then called, so its recorded output depends on that initialisation as well as on the forward computation.
Bucket 1 of 3: arg 1: rank 3, kind float, dtype float32
15 implementations from 15 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 |
|---|---|---|
| 6 implementations 6 papers 6f3faa1240b8 recorded values identical |
models/ocebo.py 15090130 recorded x:3/float/float32 class mae/modeling_pretrain.py 762514af recorded x:3/float/float32 class easycv/models/backbones/vision_transformer.py c713760d recorded x:3/float/float32
modeling/fusion_part/CRM.py cb0614ea recorded x:3/float/float32 class Codes/multimae/multimae.py e6e9f6bf recorded x:3/float/float32 class vissl/models/trunks/beit_transformer.py f4d723c4 recorded x:3/float/float32 |
[-1.11641, 2.10357, -1.57351, -0.322757, 0.188745, -1.79345, -0.425182, -0.476407, …] shape [2, 4, 8] · float32 · Tensor |
| 5 implementations 5 papers 00c5d9cceda3 recorded values identical |
class models_counting_network.py 59c07cf4 recorded x:3/float/float32 class codes/models/decoder_affordance.py 7bf42bf0 recorded x:3/float/float32 class models/maniqa.py 93f0fde3 recorded x:3/float/float32 class aff_block_LL.py 99f368d7 recorded x:3/float/float32 class core/gmflownet_model.py b20207e9 recorded x:3/float/float32 |
[-0, 0, -0, -0, 0, -0, -0, -0, …] shape [2, 4, 8] · float32 · Tensor |
| 1 implementation 1 paper 844ec428d46d |
model/s2wat.py 7d33ccdf recorded x:3/float/float32 |
[-0, 0, -0, -0, 0, -0, -0, -0, …] shape [2, 4, 8] · float32 · Tensor |
| 1 implementation 1 paper a162a74a61f1 |
class VLog/model/models.py eb3438f3 recorded x:3/float/float32 |
[-0.992364, 1.86984, -1.39867, -0.286895, 0.167773, -1.59418, -0.37794, -0.423473, …] shape [2, 4, 8] · float32 · Tensor |
| 1 implementation 1 paper b0bc893fafe2 |
class code/model/decoder.py 511f72cb recorded x:3/float/float32 |
[-0, 0, -0, -0, 0, -0, -0, -0, …] shape [2, 4, 8] · float32 · Tensor |
| 1 implementation 1 paper d9503ca0a311 |
class networks/RetrievalNet.py 938eafe3 recorded x:3/float/float32 |
[-0.992364, 1.86984, -1.39867, -0.286895, 0.167773, -1.59418, -0.37794, -0.423473, …] shape [2, 4, 8] · float32 · Tensor |
Bucket 2 of 3: arg 1: 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 fc21e89419f0 |
class projects/evad/models/vit_model.py f1ba368c recorded x:2/float/float32 |
[0, -0, 0, -0, -0, -0, -0, 0, …] shape [4, 8] · float32 · Tensor |
Bucket 3 of 3: arg 1: rank 4, 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 780f05c32657 |
models/T1.py 96592475 recorded x:4/float/float32 |
[0.903881, 0.816349, 1.80761, 1.37318, 1.42162, -0.249909, -0.339359, 1.03997, …] shape [2, 3, 4, 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/droppath.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