masked_mean
masked_mean: 8 implementations from 11 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.
Not compared, and not in the tables or the counts above:
- 4 more implementations of this name were examined but did not run on the shared input (RuntimeError 4).
- 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 2, kind float, dtype float32 · arg 2: 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); 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 4 papers c42d56d87512 recorded values identical |
src/verl/trainer/ppo/core_algos.py 514a8131 recorded values:2/float/float32, mask:2/float/float32; axis=None
verl/verl/trainer/ppo/core_algos.py 1ab358e6 recorded values:2/float/float32, mask:2/float/float32; axis=None
verl/trainer/ppo/sdar_utils.py d0bcd263 recorded values:2/float/float32, mask:2/float/float32; axis=None |
[-11.0179] shape [] · float32 · Tensor |
| 1 implementation 2 papers 07e1559e97da |
unimol_plus/inference.py 698e12d1 recorded mask:2/float/float32, value:2/float/float32; dim=1, eps=1e-10, keepdim=False |
[-4.54523, 6.22724, -2.46617, -29.7917] shape [4] · float32 · Tensor |
| 1 implementation 1 paper 570aa2376848 |
denserlhf/trainer/ppo_utils/experience_maker.py bff9c1af recorded tensor:2/float/float32, mask:2/float/float32; dim=0 |
[2.61015, -3.45413, 1.0056, -2.51069, -0.984296, 6.83858, -0.902562, 1.29008] shape [8] · float32 · Tensor |
Bucket 2 of 2: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind bool, dtype bool
3 implementations from 4 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 |
|---|---|---|
| 2 implementations 2 papers e52e77fcb901 recorded values identical |
src/clrcmd/models.py 64dbc58a recorded x:2/float/float32, mask:2/bool/bool; dim=1 pretrain/models.py 6f0e0c50 recorded x:2/float/float32, mask:2/bool/bool; dim=-1, keepdim=False |
[-0.0713914, 0.100194, 0.204759, 0.0182505] shape [4] · float32 · Tensor |
| 1 implementation 2 papers ba6280b80432 |
algs/rep.py e078eeed recorded values:2/float/float32, mask:2/bool/bool |
[0.0432014] 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/masked-mean.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