André Martins, Marcos Treviso, Pavlo Vasylenko, Hugo Pitorro
2 of 2 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; 2 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2506.16640.json · badge: /api/ran/2506.16640.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 |
|---|---|---|
| deep-spin/asentmax | canonical (classifier label) classifier basis: census |
2 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| deep_update_dict | Ran ran; our contract draft was wrong, not the code |
deep-spin/asentmax/synthetic/src/utils/dict.py pointer only (licence: GPL-3.0) · get_code("5dc1ebd8c8c4dd11") How it ranThe body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, deep-spin/asentmax, is not in the permissive set Syntology serves inline. 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. |
| max_neg_value | Ran ran; our contract draft was wrong, not the code |
deep-spin/asentmax/synthetic/src/attention/topk.py pointer only (licence: GPL-3.0) · get_code("b209878199e80c50") How it ranThe body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, deep-spin/asentmax, is not in the permissive set Syntology serves inline. 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 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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 |
|---|---|---|---|
| max_neg_value | 4 other papers 3 dated earlier, 1 later · 3 only as an assembly brick |
2006.15020 (2020-06) Pre-training via Paraphrasing |
2105.14850 (2021-05) Cascaded Head-colliding Attention 2108.12630 (2021-08) GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer and 1 more not named here |
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for tasks that demand precise focus on fixed-size patterns: as sequence length increases, noninformative tokens accumulate attention probability mass, leading to dispersion and representational collapse. We show in this paper that dynamically sparse attention mechanisms using α-entmax can avoid these issues, due to their ability to assign exact zeros to irrelevant tokens. Furthermore, we introduce Adaptive-Scalable Entmax (ASEntmax), which endows α-entmax with a learnable temperature parameter, allowing the attention distribution to interpolate between sparse (pattern-focused) and dense (softmax-like) regimes. Our empirical evaluation on synthetic tasks and language modeling demonstrates that ASEntmax substantially outperforms softmax, scalable softmax, and fixed-temperature α-entmax baselines, achieving up to 1000× length extrapolation on synthetic benchmarks and superior long-context generalization on language modeling while preserving short-context performance, including better perplexity trends and higher retrieval accuracies at 8× training length. Source code: https://github.com/deep-spin/asentmax
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2506.16640")
get_code_for_paper("2506.16640")
have("2506.16640")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2506.16640.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2506.16640)
Connect an agent — have() is free.