Wei Wu, Xiang Hu, Kewei Tu, Qingyang Zhu
3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2309.16319.json · badge: /api/ran/2309.16319.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 |
|---|---|---|
| ant-research/structuredlm_rtdt | canonical (classifier label) classifier basis: classifier_2025 |
3 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| InsideEncoder | Ran ran on a synthesized input · constructed an object; no result was computed |
ant-research/structuredlm_rtdt/model/tree_encoder.py code served (permissive licence) · get_code("5d098ec6c3be99a0") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, InsideEncoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| TreeEncoderLayer | Ran ran on a synthesized input · constructed an object; no result was computed |
ant-research/structuredlm_rtdt/model/tree_encoder.py code served (permissive licence) · get_code("ef2b7ab2ebb4fc06") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, TreeEncoderLayer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
| _get_activation_fn | Ran ran; our contract draft was wrong, not the code |
ant-research/structuredlm_rtdt/model/tree_encoder.py code served (permissive licence) · get_code("a9d317f927330280") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.
|
Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.
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.
We present ReCAT, a recursive composition augmented Transformer that is able to explicitly model hierarchical syntactic structures of raw texts without relying on gold trees during both learning and inference. Existing research along this line restricts data to follow a hierarchical tree structure and thus lacks inter-span communications. To overcome the problem, we propose novel contextual inside-outside (CIO) layers, each of which consists of a top-down pass that forms representations of high-level spans by composing low-level spans, and a bottom-up pass that combines information inside and outside a span. The bottom-up and top-down passes are performed iteratively by stacking CIO layers to fully contextualize span representations. By inserting the stacked CIO layers between the embedding layer and the attention layers in Transformer, the ReCAT model can perform both deep intra-span and deep inter-span interactions, and thus generate multi-grained representations fully contextualized with other spans. Moreover, the CIO layers can be jointly pre-trained with Transformers, making ReCAT enjoy scaling ability, strong performance, and interpretability at the same time. We conduct experiments on various sentence-level and span-level tasks. Evaluation results indicate that Re-CAT can significantly outperform vanilla Transformer models on all span-level tasks and recursive models on natural language inference tasks. More interestingly, the hierarchical structures induced by ReCAT exhibit strong consistency with human-annotated syntactic trees, indicating good interpretability brought by the CIO layers. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2309.16319")
get_code_for_paper("2309.16319")
have("2309.16319")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2309.16319.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2309.16319)
Connect an agent — have() is free.