SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.07063 · 2026

Dr. Post-Training : A Data Regularization Perspective on LLM Post-Training

Jiaqi Ma, Pingbang Hu, Z Mao, Xueshen Liu

arXiv · PDF

Code that ran

6 of 7 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; 4 failures of our instrument; 1 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/2605.07063.json · badge: /api/ran/2605.07063.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.

RepositoryRoleRan
TRAIS-Lab/Dr.Post-Training canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
init_end_of_turn_from_eos Ran
ran; our contract draft was wrong, not the code
TRAIS-Lab/Dr.Post-Training/SFT/train/model_arguments.py
pointer only (licence: NONE) · get_code("c510e9e1cdf406bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

per_example_mean Ran
ran; our contract draft was wrong, not the code
TRAIS-Lab/Dr.Post-Training/drpt/losses.py
pointer only (licence: NONE) · get_code("ed42baef5aa9c11e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

reduce_masked_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TRAIS-Lab/Dr.Post-Training/drpt/losses.py
pointer only (licence: NONE) · get_code("f489d7eab0acb3c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

stochastic_diagonal_estimation Ran
ran, honoured the contract we drafted
TRAIS-Lab/Dr.Post-Training/drpt/utils.py
pointer only (licence: NONE) · get_code("e74a437491e0b1ea")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

validate_loss_reduction Ran
ran; our contract draft was wrong, not the code
TRAIS-Lab/Dr.Post-Training/drpt/losses.py
pointer only (licence: NONE) · get_code("2a7b7368965e946d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

vectorize Ran
ran, honoured the contract we drafted
TRAIS-Lab/Dr.Post-Training/drpt/utils.py
pointer only (licence: NONE) · get_code("2b12fa6b855b18ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

apply_hadamard_matvec Not yet run
unverified (harvested, no recorded run)
TRAIS-Lab/Dr.Post-Training/drpt/utils.py
pointer only (licence: NONE) · get_code("c24ab30e74cbc342")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TRAIS-Lab/Dr.Post-Training 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant but imperfectly aligned general training data. In this work, we move beyond the data-selection framing and introduce Dr. Post-Training (Data-Regularized Post-Training), a novel framework that reconceptualizes general training data as a data-induced regularizer that prevents overfitting to the scarce target objective, rather than serving as a pool for selection. Specifically, our framework proposes that at each training step, construct a feasible set of model update directions using the general training data, and project the model update direction specified by the scarce target data onto that feasible set. Standard training and existing data selection methods arise as special cases with different choices of the data-induced regularizer, and these methods correspond to different points on a bias-variance spectrum with different regularization strength. Building on this view, we propose a family of methods offering a richer design space and more flexible bias-variance tradeoffs. For practical LLM-scale use, we introduce careful system optimizations that realize these methods with minimal overhead. Extensive experiments across SFT, RLHF, and RLVR show that our methods consistently outperform state-of-the-art data selection baselines, and system benchmarks confirm their efficiency.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2605.07063")
get_code_for_paper("2605.07063")
have("2605.07063")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2605.07063.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2605.07063.svg)](https://syntology.ai/paper/2605.07063)

Connect an agent — have() is free.