loss_function
loss_function: 7 implementations from 6 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 7 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:
- 14 more implementations of this name were examined but did not run on the shared input (RuntimeError 12, ValueError 2).
- 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 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
4 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); 4 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 |
|---|---|---|
| 1 implementation 1 paper 670edbd56259 |
trainvae.py 46304a89 recorded recon_x:2/float/float32, x:2/float/float32, mu:2/float/float32, logsigma:2/float/float32 |
[105.182] shape [] · float32 · Tensor |
| 1 implementation 1 paper 7184e596aee4 |
models.py 615c1c08 recorded recon_x:2/float/float32, x:2/float/float32, mu:2/float/float32, logvar:2/float/float32; anneal=0.5 |
[-6.17762] shape [] · float32 · Tensor |
| 1 implementation 1 paper e77817b64982 |
objective.py 5c93a9f6 recorded online_prediction1:2/float/float32, online_prediction2:2/float/float32, target_projection1:2/float/float32, target_projection2:2/float/float32 |
[-1] shape [] · float32 · Tensor |
| 1 implementation 1 paper e87df3173497 |
modules_tied.py 5c76b12c recorded recon_x:2/float/float32, x:2/float/float32, mu:2/float/float32, logvar:2/float/float32; bsz=2 |
[0.0169925] shape [] · float32 · Tensor |
Bucket 2 of 2: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
3 implementations from 3 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 |
|---|---|---|
| 1 implementation 1 paper 715623d0a821 |
utiles/loss_function.py d1695fe8 recorded predict:2/float/float32, target:2/float/float32 |
[2.38419e-07, -2.38419e-07, 0, 0] shape [4] · float32 · Tensor |
| 1 implementation 1 paper af5570f5a181 |
code/Model_AE2.py d9f4e300 recorded recon_x:2/float/float32, x:2/float/float32 |
[0] shape [] · float32 · Tensor |
| 1 implementation 1 paper d4b132a4a797 |
imagenet/main_simsiam.py bdc4977b recorded p:2/float/float32, z:2/float/float32; criterion=MSELoss(), args=<fx_bdc4977b50394a14__loss_function.Args object at 0xffff6e2 |
[0.931388] 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/loss-function.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