Hongxin Wei, Huipeng Huang
5 of 5 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; 2 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/2608.14728.json · badge: /api/ran/2608.14728.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 |
|---|---|---|
| HuipengHuang/TA-OPD | canonical (classifier label) classifier basis: census |
5 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| extract_answer_region | Ran ran; our contract draft was wrong, not the code |
HuipengHuang/TA-OPD/evaluation/verifier.py pointer only (licence: NONE) · get_code("d35f6829bfcd24db") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HuipengHuang/TA-OPD 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. |
| extract_first_boxed_content | Ran ran; our contract draft was wrong, not the code |
HuipengHuang/TA-OPD/evaluation/verifier.py pointer only (licence: NONE) · get_code("688d4bbc66fab59f") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HuipengHuang/TA-OPD 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. |
| find_first_boxed_end | Ran ran, honoured the contract we drafted |
HuipengHuang/TA-OPD/evaluation/verifier.py pointer only (licence: NONE) · get_code("bf227217ffd04227") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HuipengHuang/TA-OPD 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. |
| generate_config_from_args | Ran ran; our contract draft was wrong, not the code |
HuipengHuang/TA-OPD/verl/verl/model_merger/base_model_merger.py pointer only (licence: NONE) · get_code("45205d24c28c95d4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HuipengHuang/TA-OPD 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. |
| get_dynamic_pipeline_shards | Ran ran, honoured the contract we drafted |
HuipengHuang/TA-OPD/verl/verl/model_merger/megatron_model_merger.py pointer only (licence: NONE); the stored copy get_code serves, from LeapLabTHU/OPDVR, is pointer only (licence: NONE) · get_code("94209884dcb2308e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, HuipengHuang/TA-OPD 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 1 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_dynamic_pipeline_shards | 52 other papers 43 dated earlier, 5 the same month, 2 later, 2 undated |
2410.02992 (2024-10) Learning to Better Search with Language Models via Guided Reinforced Self-Training |
2509.25787 (2025-09) Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking 2510.08630 (2025-10) ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection and 49 more not named here |
| generate_config_from_args | 2 other papers 2 the same month |
2608.23566 (2026-08) Best Practice Critic Optimization BEST PRACTICE CRITIC OPTIMIZATION |
2608.24350 (2026-08) FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision |
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.
On-policy distillation (OPD) has emerged as an effective paradigm for transferring knowledge between language models, where a student is trained to align its nexttoken distribution with the teacher's along its own trajectories. To provide dense supervision at tractable cost, many works minimize the reverse Kullback-Leibler (KL) divergence between the student and teacher's normalized distributions over the teacher's top-k tokens. However, this normalized objective discards the information about tail probability: the total probability outside the teacher's top-k tokens. As a result, the optimization can steadily increase the student's tail probability and entropy, empirically degrading downstream accuracy. To address this issue, we propose Tail-Aware Top-k OPD (TA-OPD), a novel distillation method that restores the missing tail probability signal. In particular, TA-OPD minimizes the reverse KL divergence over the top-k tokens plus a tail token that carries the tail probability. In effect, TA-OPD better aligns the student's next-token distribution with the teacher's, preventing the increase in tail probability and entropy caused by top-k normalization. Extensive experiments demonstrate the superiority of TA-OPD, improving Avg@8 by up to 8.05 points on common benchmarks. Our code is available at https://github.com/HuipengHuang/TA-OPD.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2608.14728")
get_code_for_paper("2608.14728")
have("2608.14728")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2608.14728.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2608.14728)
Connect an agent — have() is free.