Home › Census › repeat_kv

repeat_kv

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

repeat_kv: 15 implementations from 60 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 2 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. 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:

Bucket 1 of 1: arg 1: rank 4, kind float, dtype float32

15 implementations from 60 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
12 implementations
56 papers
78125b9a9282
recorded values identical
one code sha held from 34 papers' repositories
modeling_xalma.py 30d7eec482ebf6b1
recorded hidden_states:4/float/float32; n_rep=2
one code sha held from 10 papers' repositories
time_moe/models/modeling_time_moe.py 3c76e52815c5401d
recorded hidden_states:4/float/float32; n_rep=2
one code sha held from 2 papers' repositories
src/gemma.py 4e762613ee907cdb
recorded hidden_states:4/float/float32; n_rep=2
one code sha held from 2 papers' repositories
modeling_mole.py ab40781baaa35b67
recorded hidden_states:4/float/float32; n_rep=2

src/flas/model.py 0f07b44f9c18969e
recorded hidden_states:4/float/float32; n_rep=2

SVDLLM.py 25ef0712acc702e7
recorded hidden_states:4/float/float32; n_rep=2

model.py 31333a36df31a820
recorded hidden_states:4/float/float32; n_rep=2

model_lib/attention_tools.py 3281dccd4fa39596
recorded hidden_states:4/float/float32; n_rep=2

eval/attention_helpers.py 404c0af567476d50
recorded hidden_states:4/float/float32; n_rep=2

trol/arch_internlm2/modeling_trol.py 6045450d1a869974
recorded hidden_states:4/float/float32; n_rep=2

Diff-Transformer/multihead_attention.py 8b9e23cfcb2e7648
recorded x:4/float/float32; n_rep=2

src/model/linear_attention/linear_window_attention_sw_linear.py ab05d5e4c4236572
recorded hidden_states:4/float/float32; n_rep=2
[0.723105, 0.653079, 1.44609, 1.09854, 1.1373, -0.199927, -0.271487, 0.831979, …]
shape [2, 6, 4, 4] · float32 · Tensor
3 implementations
4 papers
2f77db535cd3
recorded values identical
one code sha held from 2 papers' repositories
models/bam.py 6d2a08dcf3466514
recorded x:4/float/float32; n_rep=2

model/model_miniwin.py 07d6ef500d143328
recorded x:4/float/float32; n_rep=2

model/model_minimind.py 226c2c7378c2826e
recorded x:4/float/float32; n_rep=2
[0.723105, 0.653079, 1.44609, 1.09854, 0.723105, 0.653079, 1.44609, 1.09854, …]
shape [2, 3, 8, 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/repeat-kv.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