Home › Census › get_loss

get_loss

Syntologyfunction-name censuscensus 2026-09-22battery b986f7e04d79all samples with this name

get_loss: 5 implementations from 5 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 5 distinct outputs across 4 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:

Bucket 1 of 4: 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)MembersShared output on this bucket's input
1 implementation
1 paper
af5570f5a181

sel-update-mtl/utils/train_utils.py 32835f4d
recorded outputs:2/float/float32, targets:2/float/float32; task='class_task'
[0]
shape [] · float32 · Tensor
1 implementation
1 paper
cacc347f3ef5

example.py 04093a74
recorded x:2/float/float32, y:2/float/float32
[0.844422]
shape [] · float64 · float

Bucket 2 of 4: arg 1: 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)MembersShared output on this bucket's input
1 implementation
1 paper
69c67292ace5

src/generate.py c3455032
recorded props:1/float/float32; model=DummyModel(), target=[1.4, None, 3.2, 4.1]
[11.4166]
shape [] · float32 · Tensor

Bucket 3 of 4: arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind int, dtype int64

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)MembersShared output on this bucket's input
1 implementation
1 paper
3578b5c82c6e

autoprompt/create_trigger.py f614f524
recorded predict_logits:2/float/float32, label_ids:2/int/int64
[0.85454, 1.0092, 0.835677, -0.473235]
shape [4] · float32 · Tensor

Bucket 4 of 4: arg 1: rank 2, 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)MembersShared output on this bucket's input
1 implementation
1 paper
5f71001451ac

detector.py bafd66dc
recorded temp:2/float/float32
[-0.0919452]
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/get-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