Home › Census › contrastive_loss

contrastive_loss

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

contrastive_loss: 11 implementations from 18 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 7 distinct outputs across 3 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 3: arg 1: rank 2, kind float, dtype float32

6 implementations from 12 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
5 implementations
11 papers
c4f8f09479c1
recorded values identical
one code sha held from 4 papers' repositories
CLIP-ViP/src/modeling/CLIP_ViP.py 4675779a
recorded logits:2/float/float32
one code sha held from 2 papers' repositories
M2PT/model/llava_archPT.py 35caa662
recorded logits:2/float/float32
one code sha held from 2 papers' repositories
LLaVA/llava/model/language_model/llava_llama.py 83ada93f
recorded logits:2/float/float32
one code sha held from 2 papers' repositories
MarT/models/modeling_clip.py f2e5f286
recorded logits:2/float/float32

fgclip2/model/strcs/fgclip2.py 54554dd5
recorded logits:2/float/float32
[1.42727]
shape [] · float32 · Tensor
1 implementation
1 paper
7891d656fa5f

src/transformers/models/align/modeling_align.py d1d7fb60
recorded logits:2/float/float32
[1.54175]
shape [] · float32 · Tensor

Bucket 2 of 3: arg 1: rank 2, kind float, dtype float32 · arg 2: 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)MembersShared output on this bucket's input
1 implementation
1 paper
2399fcd7f479

model/model.py e5fdec8e
recorded z_t:2/float/float32, z_f:2/float/float32; tau=0.1
[nan]
shape [] · float32 · Tensor · non-finite
1 implementation
1 paper
272f78036db6

utils/pair_selection_util.py a0ad7c05
recorded f_emb:2/float/float32, v_emb:2/float/float32; margin=1.0, tau=0.5
[0.25]
shape [] · float32 · Tensor
1 implementation
1 paper
570d68f10e57

methods/contrastive.py ba00312b
recorded x0:2/float/float32, x1:2/float/float32; tau=0.07, norm=True
[0.0234837]
shape [] · float32 · Tensor
1 implementation
1 paper
7207fa2607ab

dual_ae_trainer.py 7567a11b
recorded z_audio:2/float/float32, z_tag:2/float/float32; t=0.5
[0.730524]
shape [] · float32 · Tensor

Bucket 3 of 3: arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32 · arg 3: rank 3, kind float, dtype float32 · arg 4: rank 3, 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)MembersShared output on this bucket's input
1 implementation
2 papers
74999fd28ab1
one code sha held from 2 papers' repositories
hete/model.py bd248e25
recorded projected_emd:3/float/float32, v_emd:3/float/float32, sampled_embeddings_u:3/float/float32, sampled_embeddings_neg_v:3/float/float32; tau=0.1, lambda_loss=1.0
[nan]
shape [] · float32 · Tensor · non-finite

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/contrastive-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