SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.08538 · ICML · 2026

Trajectory Stitching for Solving Inverse Problems with Flow-Based Models

Alexander Denker, Carola-Bibiane Schönlieb, Moshe Eliasof, Zeljko Kereta

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2602.08538.json · badge: /api/ran/2602.08538.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
annegnx/PnP-Flow canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_activation_statistics Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/fid_score.py
pointer only (licence: NONE) · get_code("014ed7df4050e8a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

custom_collate Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/dataloaders.py
pointer only (licence: NONE) · get_code("3b05acd66d4cf394")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

downsample Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/models.py
pointer only (licence: NONE) · get_code("64fff7f072e05415")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

get_activations Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/fid_score.py
pointer only (licence: NONE) · get_code("f10c698bdf0953d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

group_norm Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/models.py
pointer only (licence: NONE) · get_code("0ee1a2c94acafeca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

to_nn_parameter Ran
ran, honoured the contract we drafted
annegnx/PnP-Flow/pnpflow/methods/pnp_diff.py
pointer only (licence: NONE) · get_code("42e5d1476a6ac5cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

upsample Ran
ran; our contract draft was wrong, not the code
annegnx/PnP-Flow/pnpflow/models.py
pointer only (licence: NONE) · get_code("77e6e60b8a8a69da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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.

calculate_frechet_distance Not yet run
unverified (harvested, no recorded run)
annegnx/PnP-Flow/pnpflow/fid_score.py
pointer only (licence: NONE) · get_code("0def50a351111624")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, annegnx/PnP-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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
calculate_frechet_distance 74 other papers
73 dated earlier, 1 later
1610.09585 (2016-10)
Conditional Image Synthesis With Auxiliary Classifier GANs
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
1807.11458 (2018-07)
To learn image super-resolution, use a GAN to learn how to do image degradation first
and 71 more not named here
downsample 4 other papers
4 dated earlier
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2101.09258 (2021-01)
Maximum Likelihood Training of Score-Based Diffusion Models
2305.11463 (2023-05)
Generative Sliced MMD Flows with Riesz Kernels
and 1 more not named here
group_norm 4 other papers
4 dated earlier
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2101.09258 (2021-01)
Maximum Likelihood Training of Score-Based Diffusion Models
2305.11463 (2023-05)
Generative Sliced MMD Flows with Riesz Kernels
and 1 more not named here
upsample 4 other papers
4 dated earlier
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2101.09258 (2021-01)
Maximum Likelihood Training of Score-Based Diffusion Models
2305.11463 (2023-05)
Generative Sliced MMD Flows with Riesz Kernels
and 1 more not named here
calculate_activation_statistics 1 other paper
1 dated earlier
2403.18705 (2024-03)
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching
get_activations 1 other paper
1 dated earlier
2403.18705 (2024-03)
Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching

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-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow output solves the inverse problem. However, this requires backpropagating through the entire generative trajectory, incurring high memory costs and numerical instability. We propose MS-Flow, which represents the trajectory as a sequence of intermediate latent states rather than a single initial code. By enforcing the flow dynamics locally and coupling segments through trajectory-matching penalties, MS-Flow alternates between updating intermediate latent states and enforcing consistency with observed data. This reduces memory consumption while improving reconstruction quality. We demonstrate the effectiveness of MS-Flow over existing methods on image recovery and inverse problems, including inpainting, super-resolution, and computed tomography.

For agents

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

get_harvested_code_for_paper("2602.08538")
get_code_for_paper("2602.08538")
have("2602.08538")

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

curl https://syntology.ai/api/ran/2602.08538.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.08538.svg)](https://syntology.ai/paper/2602.08538)

Connect an agent — have() is free.