grad_reverse
grad_reverse: 12 implementations from 17 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 1 distinct outputs.
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.
- 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 1: arg 1: rank 2, kind float, dtype float32
12 implementations from 17 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 |
|---|---|---|
| 12 implementations 17 papers d7bd5ceec8a6 recorded values identical |
models/component.py 29525c5a recorded x:2/float/float32; lambd=0.5
model.py 2a7e1891 recorded x:2/float/float32
adapteacher/modeling/meta_arch/rcnn.py 7d2aba87 recorded x:2/float/float32
trainer.py 8a26ee1d recorded x:2/float/float32
exp1.py b5becb52 recorded x:2/float/float32; scale=1.0
tabula/model/transfomer/transformer.py 12adce58 recorded x:2/float/float32; lambd=0.5 maskrcnn_benchmark/modeling/domain_adaption/DA.py 3953ff0e recorded x:2/float/float32; grl_alpha=0.5 algorithms/algorithms.py 568eece0 recorded x:2/float/float32; lambd=1.0 APY/code/model.py 5a2b24f3 recorded x:2/float/float32; LAMBDA=0.5
module/model.py 5c9517d1 recorded x:2/float/float32; lambda_=1.0 Pytorch/lib/model/faster_rcnn_MV_3/DA.py abb34bc8 recorded x:2/float/float32 models/basenet.py ed0154a7 recorded x:2/float/float32; lambd=1.0 |
[1.80263, -1.53378, 0.476053, -0.690887, -0.902849, -1.03047, -0.662761, 0.572889, …] 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/grad-reverse.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