compute_loss
compute_loss: 11 implementations from 11 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 9 distinct outputs across 7 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:
- 8 more implementations of this name were examined but did not run on the shared input (IndexError 3, RuntimeError 3, ValueError 2).
- 6 more implementations from 7 papers took no array argument and ran only on their own fixture arguments; no shared input existed for them, so they are not compared (on 6 the recorded shared-output digest is the own-fixture digest).
- Every compared output was digested.
Bucket 1 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 0, kind float, dtype float32 · arg 5: 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); 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 |
|---|---|---|
| 3 implementations 3 papers af5570f5a181 recorded values identical |
src/robust_vlm/train/adversarial_training_clip.py 3bdfc4201b35c55b recorded embedding:2/float/float32, targets:1/int/int64, embedding_orig:2/float/float32, logit_scale:0/float/float32, embedding_text_labels_norm:2/float/float32; loss_str='l2', reduction='mean'
train/align_training_clip.py 735c7110db767760 recorded embedding:2/float/float32, targets:1/int/int64, embedding_orig:2/float/float32, logit_scale:0/float/float32, embedding_text_labels_norm:2/float/float32; loss_str='l2', reduction='mean' train/adversarial_training_clip.py b03f0274dabbb8c0 recorded embedding:2/float/float32, targets:1/int/int64, embedding_orig:2/float/float32, logit_scale:0/float/float32, embedding_text_labels_norm:2/float/float32; loss_str='l2', reduction='mean' |
[0] shape [] · float32 · Tensor |
Bucket 2 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
2 implementations from 2 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 |
|---|---|---|
| 1 implementation 1 paper af5570f5a181 |
models/graphedx.py 310b4b2e126ed8b6 recorded lower_bound:2/float/float32, upper_bound:2/float/float32, out:2/float/float32 |
[0] shape [] · float32 · Tensor |
| 1 implementation 1 paper af7e12f89d3e |
model.py ddaa3dd8a024013d recorded output:2/float/float32, labels:2/float/float32, mask:2/float/float32; reduction=True |
[-3.62225] shape [] · float32 · Tensor |
Bucket 3 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
2 implementations from 2 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 |
|---|---|---|
| 1 implementation 1 paper 81e565f324d2 |
src/srtta.py 06a1ef9308233244 recorded pred:2/float/float32, target:2/float/float32; eps=0.001 |
[0.0316228] shape [] · float32 · Tensor |
| 1 implementation 1 paper af5570f5a181 |
bayesian_laws_icl/analyse.py 303d355d2a45ca05 recorded true_nll:2/float/float32, est_nll:2/float/float32; mode='mse_prob' |
[0] shape [] · float32 · Tensor |
Bucket 4 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64 · arg 3: rank 1, kind float, dtype float32
1 implementation from 1 paper 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 |
|---|---|---|
| 1 implementation 1 paper 74999fd28ab1 |
src/NERDA_Con/training.py 193acceb49ed1761 recorded preds:2/float/float32, target_tags:1/int/int64, masks:1/float/float32; device='cpu', n_tags=4 |
[nan] shape [] · float32 · Tensor · non-finite |
Bucket 5 of 7: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 0, kind float, dtype float32
1 implementation from 2 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 |
|---|---|---|
| 1 implementation 2 papers af5570f5a181 |
train/adversarial_training_clip.py 75f68885e2ff2684 recorded embedding:2/float/float32, targets:1/int/int64, embedding_orig:2/float/float32, logit_scale:0/float/float32; loss_str='l2', embedding_text_labels_norm=None, reduction='mean' |
[0] shape [] · float32 · Tensor |
Bucket 6 of 7: arg 1: rank 3, kind float, dtype float32 · arg 2: rank 2, kind bool, dtype bool · arg 3: rank 3, kind bool, dtype bool
1 implementation from 1 paper 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 |
|---|---|---|
| 1 implementation 1 paper ad9b9550123e |
materials/train_edm.py 59178d244fffc6d5 recorded xh:3/float/float32, node_mask:2/bool/bool, edge_mask:3/bool/bool; model=DummyModel( (linear): Linear(in_features=4, out_features=1, num_node_features=2 |
[0.228237, -0.846012, -0.887721, 0.703229] shape [4] · float32 · Tensor |
Bucket 7 of 7: arg 1: rank 4, kind float, dtype float32
1 implementation from 1 paper 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 |
|---|---|---|
| 1 implementation 1 paper 7300b9435f48 |
Codes/PhyCRNet_burgers.py 39ed029c556af56b recorded output:4/float/float32; loss_func=PhysicsLossModule() |
[0.0210912] 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/compute-loss.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