Hui Huang, Lu Yin, Yile Wang, Ziyang Chen, Weiqin Wang, Zhenxuan Huang
3 of 3 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; 3 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/2601.05075.json · badge: /api/ran/2601.05075.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 |
|---|---|---|
| szu-tera/SemPA | canonical (classifier label) classifier basis: census |
3 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_answers | Ran ran; our contract draft was wrong, not the code |
szu-tera/SemPA/drop/utils.py pointer only (licence: NONE) · get_code("1b91c1817a9609fa") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, szu-tera/SemPA 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. |
| parse_answer | Ran ran; our contract draft was wrong, not the code |
szu-tera/SemPA/drop/utils.py pointer only (licence: NONE) · get_code("082dc362726bba49") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, szu-tera/SemPA 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. |
| process_docs | Ran ran; our contract draft was wrong, not the code |
szu-tera/SemPA/drop/utils.py pointer only (licence: NONE) · get_code("3ff35dfc829b5be3") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, szu-tera/SemPA 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 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.
Traditional sentence embedding methods employ token-level contrastive learning on nongenerative pre-trained models. Recently, there have emerged embedding methods based on generative large language models (LLMs). These methods either rely on fixed prompt templates (Jiang et al., 2024) or involve modifications to the model architecture (BehnamGhader et al., 2024). The former lacks further optimization of the model and results in limited performance, while the latter alters the internal computational mechanisms of the model, thereby compromising its generative capabilities. We propose SEMPA, a novel approach that boosts the sentence representations while preserving the generative ability of LLMs via semantic preference alignment. We leverage sentence-level Direct Preference Optimization (DPO) to efficiently optimize LLMs on a paraphrase generation task, where the model learns to discriminate semantically equivalent sentences while preserving inherent generative capacity. Theoretically, we establish a formal connection between DPO and contrastive learning under the Plackett-Luce model framework. Empirically, experimental results on both semantic textual similarity tasks and various benchmarks for LLMs show that SEMPA achieves better semantic representations without sacrificing the inherent generation capability of LLMs. We release the code at https: //github.com/szu-tera/SemPA.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2601.05075")
get_code_for_paper("2601.05075")
have("2601.05075")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2601.05075.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2601.05075)
Connect an agent — have() is free.