5 of 6 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 1 has 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/2410.03145.json · badge: /api/ran/2410.03145.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 |
|---|---|---|
| kykim0/margin-matching-pref-opt | canonical (classifier label) classifier basis: census |
5 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| apply_chat_template | Ran ran; our contract draft was wrong, not the code |
kykim0/margin-matching-pref-opt/src/alignment/data.py code served (permissive licence) · get_code("9be06c85912c5236") 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 dict. 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.
|
| compute_accuracy | Ran ran; our contract draft was wrong, not the code |
kykim0/margin-matching-pref-opt/src/alignment/trainer/utils.py code served (permissive licence) · get_code("170d1cc526ffc36c") 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 dict. 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.
|
| extract_docstring | Ran ran; our contract draft was wrong, not the code |
kykim0/margin-matching-pref-opt/src/alignment/decontaminate.py code served (permissive licence) · get_code("0edeacd7a9034f53") 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 str. 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.
|
| load_dataset_column | Ran ran on a synthesized input |
kykim0/margin-matching-pref-opt/src/alignment/decontaminate.py code served (permissive licence) · get_code("a3791c5c2185e013") 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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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.
|
| normalize_whitespace | Ran ran; our contract draft was wrong, not the code |
kykim0/margin-matching-pref-opt/src/alignment/decontaminate.py code served (permissive licence) · get_code("f43e59d239019e86") 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 str. 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.
|
| mix_datasets | Not yet run unverified (harvested, no recorded run) |
kykim0/margin-matching-pref-opt/src/alignment/data.py code served (permissive licence) · get_code("7f7ffeb2c6fe3a5d") How it ranno invocation recorded. |
Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 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 |
|---|---|---|---|
| extract_docstring | 10 other papers 5 dated earlier, 2 the same month, 3 later |
2405.14734 (2024-05) SimPO: Simple Preference Optimization with a Reference-Free Reward |
2406.08414 (2024-06) Discovering Preference Optimization Algorithms with and for Large Language Models 2406.19371 (2024-06) Suri: Multi-constraint Instruction Following for Long-form Text Generation and 7 more not named here |
| normalize_whitespace | 9 other papers 5 dated earlier, 1 the same month, 3 later |
2405.14734 (2024-05) SimPO: Simple Preference Optimization with a Reference-Free Reward |
2406.08414 (2024-06) Discovering Preference Optimization Algorithms with and for Large Language Models 2406.19371 (2024-06) Suri: Multi-constraint Instruction Following for Long-form Text Generation and 6 more not named here |
| load_dataset_column | 8 other papers 5 dated earlier, 1 the same month, 2 later |
2405.14734 (2024-05) SimPO: Simple Preference Optimization with a Reference-Free Reward |
2406.08414 (2024-06) Discovering Preference Optimization Algorithms with and for Large Language Models 2406.19371 (2024-06) Suri: Multi-constraint Instruction Following for Long-form Text Generation and 5 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 2026-11-22.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. Despite their success, existing methods typically rely on simple binary labels, such as those indicating preferred outputs in pairwise preferences, which fail to capture the subtle differences in relative quality between pairs. To address this limitation, we introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models. Specifically, given quality margins in pairwise preferences, we design soft target probabilities based on the Bradley-Terry model, which are then used to train models with the standard cross-entropy objective. Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench. Notably, the 7B model trained with MMPO achieves state-of-the-art performance on RewardBench as of June 2024, outperforming other models of the same scale. Our analysis also shows that MMPO is more robust to overfitting, leading to better-calibrated models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2410.03145")
get_code_for_paper("2410.03145")
have("2410.03145")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2410.03145.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2410.03145)
Connect an agent — have() is free.