Home › Census › euclidean_dist
euclidean_dist
euclidean_dist: 12 implementations from 14 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 3 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 · arg 2: rank 2, kind float, dtype float32
12 implementations from 14 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 |
|---|---|---|
| 6 implementations 7 papers 7044be76a671 recorded values identical |
ICLR25_OT.py c83d9f7f recorded x:2/float/float32, y:2/float/float32
mmt/loss/triplet.py e5480498 recorded x:2/float/float32, y:2/float/float32 model/loss.py 06851d0b recorded x:2/float/float32, y:2/float/float32 loss/ordinal_ce.py 426c9712 recorded x:2/float/float32, y:2/float/float32 mmt/loss/triplet.py cea0110f recorded x:2/float/float32, y:2/float/float32 OrdinalEntropy.py e0e54582 recorded x:2/float/float32, y:2/float/float32 |
[1e-06, 4.58637, 2.02175, 4.57945, 4.58637, 0.00135723, 4.63023, 3.79885, …] shape [4, 4] · float32 · Tensor |
| 4 implementations 6 papers f8b683d411a9 recorded values identical |
few_shot.py 4dd319c4 recorded x:2/float/float32, y:2/float/float32
OOD_Distance.py 57bbb1c2 recorded x:2/float/float32, support_mean:2/float/float32 model.py 0d9f00b5 recorded t1:2/float/float32, t2:2/float/float32 processor/processor_protonet.py 7ad5cda3 recorded x:2/float/float32, y:2/float/float32 |
[0, 21.0348, 4.08747, 20.9713, 21.0348, 0, 21.439, 14.4312, …] shape [4, 4] · float32 · Tensor |
| 2 implementations 1 paper 7db073e7c508 recorded values identical |
agent.py 5b618196 recorded x:2/float/float32, y:2/float/float32 codes/agent.py b8e29986 recorded x:2/float/float32, y:2/float/float32 |
[0, 4.58637, 2.02175, 4.57945, 4.58637, 0.00135723, 4.63023, 3.79885, …] shape [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/euclidean-dist.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