top_k
top_k: 7 implementations from 9 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 5 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.
Not compared, and not in the tables or the counts above:
- Every examined implementation of this name that took an array argument ran on the shared input.
- 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 1: arg 1: rank 2, kind float, dtype float32
7 implementations from 9 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 5 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 |
|---|---|---|
| 2 implementations 3 papers 0ce351e01265 recorded values identical |
one code sha held from 2 papers' repositories block_recurrent_transformer_pytorch/block_recurrent_transformer_pytorch.py 39f3cec3 recorded logits:2/float/float32; thres=0.9 speculative_decoding/speculative_decoding.py 3c61d89a recorded logits:2/float/float32; thres=0.9 |
[1.80263, -inf, -inf, -inf, -inf, -inf, -inf, -inf, …] shape [4, 8] · float32 · Tensor · non-finite |
| 2 implementations 3 papers 2a1eb671fb1d recorded values identical |
one code sha held from 2 papers' repositories marge_pytorch/marge_pytorch.py 3b65d5d7 recorded logits:2/float/float32; thres=0.9 autoregressive_wrapper.py 5d77a7df recorded logits:2/float/float32; thres=0.9 |
[-inf, -inf, -inf, -inf, -inf, -inf, -inf, -inf, …] shape [4, 8] · float32 · Tensor · non-finite |
| 1 implementation 1 paper 8c8e8216c02a |
vqvae.py fc2efb61 recorded logits:2/float/float32; thres=0.5 |
[1.80263, -inf, 0.476053, -inf, -inf, -inf, -0.662761, 0.572889, …] shape [4, 8] · float32 · Tensor · non-finite |
| 1 implementation 1 paper b6b3eb1fb739 |
evaluate_model.py 4c461540 recorded logits:2/float/float32; k=3 |
[2, 7, 0, 7, 1, 5, 0, 2, …] shape [4, 3] · int64 · ndarray |
| 1 implementation 1 paper e84b62b578f6 |
utils/generate.py 72827010 recorded logits:2/float/float32; k=2 |
[1.80263, -inf, -inf, -inf, -inf, -inf, -inf, 0.572889, …] shape [4, 8] · 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/top-k.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