Vasant Honavar, Debarshi Kundu, Swaroop Ghosh
7 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.
"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2607.21752.json · badge: /api/ran/2607.21752.svg
Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.
| Repository | Role | Ran |
|---|---|---|
| sc782/SBM-Transformer | canonical (classifier label) classifier basis: census |
7 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| append_cls | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/model_wrapper.py pointer only (licence: NONE) · get_code("defcc1e5e9bf48b2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| attach_dim | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/attention_sbm.py pointer only (licence: NONE) · get_code("9852cec20a1d486e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| batched_bincount | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/fastRG.py pointer only (licence: NONE) · get_code("5f1d8d3803a6d549") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| batched_multinomial | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/fastRG.py pointer only (licence: NONE) · get_code("04d8eb683eb1ce24") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| block_diag | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/attention_sbm.py pointer only (licence: NONE) · get_code("2db10d7fc567bec3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| fastRG | Ran ran; our contract draft was wrong, not the code |
sc782/SBM-Transformer/code/fastRG.py pointer only (licence: NONE) · get_code("b1d7a0eee487a64b") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
| pooling | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
sc782/SBM-Transformer/code/model_wrapper.py pointer only (licence: NONE) · get_code("9dbe45c9859b04e5") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, sc782/SBM-Transformer when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).
Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| append_cls | 1 other paper 1 dated earlier |
2312.02829 (2023-12) MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition |
|
| pooling | 1 other paper 1 dated earlier |
2312.02829 (2023-12) MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition |
Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Data-adaptive sparse attention masks substantially outperform fixed patterns (e.g., BigBird and Longformer) and can even exceed dense attention on long sequences. Existing adaptive approaches-including SBM-Transformer, Dynamic Mask Attention, and NSA-typically require additional learnable parameters, custom gradient estimators, or specialized CUDA kernels. We show that classical data compression provides an effective masking signal with no additional parameters. By computing per-block gzip compression ratios, we identify non-redundant content blocks and route long-range attention selectively through them. Intuitively, blocks that gzip cannot compress contain information not predictable from local repetition, making them natural long-range attention targets. Because the compression profile is input-dependent, the resulting sparse mask adapts dynamically to content without learned parameters, auxiliary losses, or custom kernels. On PG-19 byte-level language modeling at 92M parameters with 8K context, our method achieves 1.71 bits-per-byte (BPB), outperforming dense attention (2.89), BigBird (2.34), Longformer (3.21), and a reimplemented SBM-Transformer (3.38)-the only learned-mask baseline-by up to 1.67 BPB while adding no parameters. The advantage grows with sequence length, with the gap over BigBird widening from 0.05 BPB at 4K context to 0.63 BPB at 8K, while convergence is 3.3× faster.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2607.21752")
get_code_for_paper("2607.21752")
have("2607.21752")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2607.21752.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2607.21752)
Connect an agent — have() is free.