4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 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/2410.13828.json · badge: /api/ran/2410.13828.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 |
|---|---|---|
| humainlab/understand_marginpo | canonical (classifier label) classifier basis: census |
4 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| common_start | Ran ran; our contract draft was wrong, not the code |
humainlab/understand_marginpo/utils/hh_dataset.py pointer only (licence: NONE) · get_code("1b1396884ed8f16b") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, humainlab/understand_marginpo 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. |
| compute_per_token_gradients | Ran ran; our contract draft was wrong, not the code |
humainlab/understand_marginpo/analysis/grad_heatmap_1.py pointer only (licence: NONE) · get_code("116c91a093f0c807") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, humainlab/understand_marginpo 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_dialogue | Ran ran; our contract draft was wrong, not the code |
humainlab/understand_marginpo/utils/hh_dataset.py pointer only (licence: NONE) · get_code("339f51a1827342d6") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, humainlab/understand_marginpo 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. |
| formatting_prompts_func | Ran ran; our contract draft was wrong, not the code |
humainlab/understand_marginpo/sft.py pointer only (licence: NONE) · get_code("4fc874bb9bf50168") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, humainlab/understand_marginpo 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. |
| load_model_and_tokenizer | Not yet run unverified (harvested, no recorded run) |
humainlab/understand_marginpo/analysis/grad_heatmap_1.py pointer only (licence: NONE) · get_code("2b221536391e6a55") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, humainlab/understand_marginpo 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. No invocation 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, 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 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.
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.
Reinforcement Learning from Human Feedback (RLHF) has become the predominant approach for language model (LM) alignment. At its core, RLHF uses a margin-based loss for preference optimization, specifying ideal LM behavior only by the difference between preferred and dispreferred responses. In this paper, we identify a common pitfall of margin-based methods -- the under-specification of ideal LM behavior on preferred and dispreferred responses individually, which leads to two unintended consequences as the margin increases: (1) The probability of dispreferred (e.g., unsafe) responses may increase, resulting in potential safety alignment failures. (2) The probability of preferred responses may decrease, even when those responses are ideal. We demystify the reasons behind these problematic behaviors: margin-based losses couple the change in the preferred probability to the gradient of the dispreferred one, and vice versa, often preventing the preferred probability from increasing while the dispreferred one decreases, and thus causing a synchronized increase or decrease in both probabilities. We term this effect, inherent in margin-based objectives, gradient entanglement. Formally, we derive conditions for general margin-based alignment objectives under which gradient entanglement becomes concerning: the inner product of the gradients of preferred and dispreferred log-probabilities is large relative to the individual gradient norms. We theoretically investigate why such inner products can be large when aligning language models and empirically validate our findings. Empirical implications of our framework extend to explaining important differences in the training dynamics of various preference optimization algorithms, and suggesting potential algorithm designs to mitigate the under-specification issue of margin-based methods and thereby improving language model alignment.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.13828")
get_code_for_paper("2410.13828")
have("2410.13828")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.13828.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.13828)
Connect an agent — have() is free.