drop_path
drop_path: 27 implementations from 61 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 5 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.
Bucket 1 of 2: arg 1: rank 4, kind float, dtype float32
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); 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 |
|---|---|---|
| 7 implementations 16 papers a8c38328240c recorded values identical |
src/models/dwiseneuro.py 971ae8d2d8313e30 recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
mono/model/backbones/ViT_DINO.py c157f5b112b3a392 recorded x:4/float/float32; drop_prob=0.5, training=True
pypots/nn/modules/tslanet/backbone.py 87577b3ff9d32712 recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
networks.py e3aa4e8e74369506 recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
models/croco.py f9a1900525331e0f recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
src/dust3r/model.py aea279a2d78d1352 recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True nas_ood_single/search/models/model_search.py b1286732acea8936 recorded x:4/float/float32; drop_prob=0.5 |
[0, 0, 0, 0, 0, -0, -0, 0, …] shape [2, 3, 4, 4] · float32 · Tensor |
| 7 implementations 10 papers fae90c40e485 recorded values identical |
towhee/models/uniformer/uniformer.py 39eace7e2822504f recorded x:4/float/float32; drop_prob=0.5, training=True
model/OpenCity/OpenCity.py 9bdf2492c6e0a8de recorded x:4/float/float32; drop_prob=0.5, training=True
model/impl/actionformer.py a34c005ba2203f35 recorded x:4/float/float32; drop_prob=0.5, training=True src/model/backbones/swin.py 2ec78252af199d14 recorded x:4/float/float32; drop_prob=0.5, training=True network/RerankTransformer.py 3c83cad222232ac6 recorded x:4/float/float32; drop_prob=0.5, training=True
networks/embedding_translation.py 68b7ffb36f0515ff recorded x:4/float/float32; p=0.5, training=True networks/RetrievalNet.py e37b79debce8d027 recorded x:4/float/float32; drop_prob=0.5, training=True |
[0, 0, 0, 0, 0, -0, -0, 0, …] shape [2, 3, 4, 4] · float32 · Tensor |
| 4 implementations 10 papers 780f05c32657 recorded values identical |
basicsr/archs/swinir_arch.py 52d96aa31ed74a56 recorded x:4/float/float32; drop_prob=0.2, training=True
net.py fe7d4321dbeef661 recorded x:4/float/float32; drop_prob=0.2, training=True models/network_vrt.py 9ea4d5b8b4d5ef2f recorded x:4/float/float32; drop_prob=0.2, training=True dyn_slim/models/dyn_slim_net.py a86440e38234fea6 recorded inputs:4/float/float32; training=True, drop_path_rate=0.2 |
[0.903881, 0.816349, 1.80761, 1.37318, 1.42162, -0.249909, -0.339359, 1.03997, …] shape [2, 3, 4, 4] · float32 · Tensor |
Bucket 2 of 2: arg 1: rank 2, kind float, dtype float32
9 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); 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 |
|---|---|---|
| 8 implementations 23 papers 9913fdcbb256 recorded values identical |
basicsr/models/archs/Xformer_arch.py 55120f2026b56aa2 recorded x:2/float/float32; drop_prob=0.5, training=True
seaformer-cls/seaformer.py 3ac6b7d76e8e3584 recorded x:2/float/float32; drop_prob=0.5, training=True
src/vit.py 6bb7492655ecbda4 recorded x:2/float/float32; drop_prob=0.5, training=True
VLog/model/models.py 10e67144852e5fce recorded x:2/float/float32; drop_prob=0.5, training=True
models/base_model_ts.py 314973a77b15948e recorded x:2/float/float32; drop_prob=0.5, training=True vissl/models/trunks/beit_transformer.py 0233d6e8a07784ae recorded x:2/float/float32; drop_prob=0.5, training=True look2hear/models/TDANet.py 04e8544d3f2fd61b recorded x:2/float/float32; drop_prob=0.5, training=True fourm/models/fm.py e60d6e23233f6f4b recorded x:2/float/float32; drop_prob=0.5, training=True |
[0, -0, 0, -0, -0, -0, -0, 0, …] shape [4, 8] · float32 · Tensor |
| 1 implementation 2 papers 3159ee4a7683 |
units/models/model.py f5ab76486eeab7b9 recorded x:2/float/float32; drop_prob=0.5, training=True, scale_by_keep=True |
[0, -0, 0, -0, -0, -0, -0, 0, …] 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/drop-path.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