SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.14949 · 2024

On the Convergence and Straightness of Rectified Flow

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2410.14949.json · badge: /api/ran/2410.14949.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
bansal-vansh/rectified-flow canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_weights Ran
ran, violated the contract we drafted
bansal-vansh/rectified-flow/simulated-data/gaussian.py
pointer only (licence: NONE) · get_code("5c14fa88c2b691fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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.

create_save_dir Ran
ran; our contract draft was wrong, not the code
bansal-vansh/rectified-flow/real-data/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from roysaptaumich/Low-dim-RF, is pointer only (licence: NONE) · get_code("3379901e9c2a25f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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_mixture_samples Ran
ran; our contract draft was wrong, not the code
bansal-vansh/rectified-flow/simulated-data/gaussian.py
pointer only (licence: NONE) · get_code("3944b220ba759545")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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.

postprocess Ran
ran; our contract draft was wrong, not the code
bansal-vansh/rectified-flow/real-data/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from roysaptaumich/Low-dim-RF, is pointer only (licence: NONE) · get_code("643e229256ef78bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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_norm_squared_full_derivative Not yet run
unverified (harvested, no recorded run)
bansal-vansh/rectified-flow/real-data/straightness.py
pointer only (licence: NONE); the stored copy get_code serves, from roysaptaumich/Low-dim-RF, is pointer only (licence: NONE) · get_code("acee3106924910c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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.

compute_scores Not yet run
unverified (harvested, no recorded run)
bansal-vansh/rectified-flow/simulated-data/gaussian.py
pointer only (licence: NONE) · get_code("9da8172da0f91e5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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.

get_dataloader Not yet run
unverified (harvested, no recorded run)
bansal-vansh/rectified-flow/real-data/data.py
pointer only (licence: NONE); the stored copy get_code serves, from roysaptaumich/Low-dim-RF, is pointer only (licence: NONE) · get_code("c5957497bd84f1cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, bansal-vansh/rectified-flow 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, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
compute_norm_squared_full_derivative 1 other paper
1 later
2601.15500 (2026-01)
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
create_save_dir 1 other paper
1 later
2601.15500 (2026-01)
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
get_dataloader 1 other paper
1 later
2601.15500 (2026-01)
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
postprocess 1 other paper
1 later
2601.15500 (2026-01)
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

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

Flow Matching has become a cornerstone of modern generative models like Stable Diffusion 3, largely due to the efficiency of its Rectified Flow (RF) variant. The success of RF hinges on iteratively learning straight trajectories, pushing generation towards fewer sampling steps. However, the theoretical link between path geometry and sampling efficiency has been underexplored. This paper fills this gap by introducing a novel \textit{Piecewise Straightness} parameter, $γ_{2,T}$. We establish the first Wasserstein convergence bound that explicitly links the discretization error of \textit{any} general flow-model to $γ_{2,T}$, proving that minimizing curvature is the key to achieving high-fidelity, one-step sampling. Building on this theory, we establish the first theoretical framework to analyze the straightness of RF. We begin by offering intuitive geometric arguments for simple cases before identifying sufficient conditions under which a single rectification step (1-RF) yields a perfectly straight or even a Monge optimal coupling. While whether these sufficient conditions are met depends on the problem geometry, they enable the first concrete proofs in this area. Critically, fulfilling these conditions makes the subsequent flow (2-RF) perfectly straight ($γ_{2,T}=0$). This eliminates the discretization error in our bound and makes flawless, single-step sampling possible.

For agents

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

get_harvested_code_for_paper("2410.14949")
get_code_for_paper("2410.14949")
have("2410.14949")

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

curl https://syntology.ai/api/ran/2410.14949.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.14949.svg)](https://syntology.ai/paper/2410.14949)

Connect an agent — have() is free.