sample
sample: 8 implementations from 9 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 7 distinct outputs across 5 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:
- 2 more implementations of this name were examined but did not run on the shared input (RuntimeError 2).
- 3 more implementations from 5 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 3 the recorded shared-output digest is the own-fixture digest).
- Every compared output was digested.
Bucket 1 of 5: arg 1: rank 3, kind float, dtype float32
3 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); 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 |
|---|---|---|
| 2 implementations 3 papers fa99eb14cf3d recorded values identical |
angelslim/compressor/speculative/train/models/draft/qwen_dflare.py ab21ebd9 recorded logits:3/float/float32; temperature=0.8
tree_flash.py 12b15cc8 recorded logits:3/float/float32; temperature=0.8 |
[1, 4, 0, 5, 1, 7, 4, 2] shape [2, 4] · int64 · Tensor |
| 1 implementation 1 paper 53781a550edb |
diffusion.py 06448db9 recorded scores:3/float/float32; N=5, deterministic=False |
[1, 7, 6, 4, 0, 5, 3, 2, …] shape [5, 2, 4, 8] · int64 · Tensor |
Bucket 2 of 5: arg 1: 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 01ba64c03421 |
results/distribute_sp.py a2d0fabb recorded logits:2/float/float32; temperature=1.0, top_k=0, top_p=0.0 |
[7, 5, 6, 5] shape [4, 1] · int64 · Tensor |
| 1 implementation 1 paper 5f7a4d906bc1 |
ccil/intervention_policy_execution.py dfb4cca4 recorded weights:2/float/float32; temperature=1.5 |
[1, 0, 1, 1, 1, 0, 0, 0, …] shape [4, 8] · int64 · ndarray |
Bucket 3 of 5: arg 1: rank 1, kind float, dtype float32 · arg 2: 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 de2a7bfc268a |
src/train_ace.py 0962a70b recorded target:1/float/float32, unconditional:1/float/float32; sampling_batch_size=2, tokenizer=None, text_encoder=None |
[-0.903889, 0.157131, 0.897612, -0.762196, -0.176256, 0.0530317, -1.62844, -0.177533, …] shape [32] · float32 · Tensor |
Bucket 4 of 5: arg 1: rank 1, kind float, dtype float64
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 05264cc120d9 |
tester.py dcdd0b5c recorded x:1/float/float64 |
[-0.841706] shape [] · float64 |
Bucket 5 of 5: arg 1: rank 4, kind float, dtype float32 · arg 2: 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) | Members | Shared output on this bucket's input |
|---|---|---|
| 1 implementation 1 paper a6b3aaaaad3f |
inference.py 21949a5a recorded dec_img:4/float/float32, extra_cond:2/float/float32; net=Net( (linear): Linear(in_features=6, out_features=8, bias=, encoder=Encoder( (linear): Linear(in_features=5, out_features=6, b, img_size=64 |
[0.446243, 0.322447, 0.637082, 0.564545, 0.456619, 0.336541, 0.718748, 0.61984, …] shape [4, 3, 4, 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/sample.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