SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.04339 · 2023

Merging by Matching Models in Task Parameter Subspaces

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 6 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/2312.04339.json · badge: /api/ran/2312.04339.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
r-three/mats canonical (classifier label)
classifier basis: census
2 ran · 6 no recorded run
FunctionStatusWhere it lives
concatenate_scores Ran
ran; our contract draft was wrong, not the code
r-three/mats/src/eval/utils.py
pointer only (licence: NONE) · get_code("65659f0a52551e43")
How it ran

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

prepare_batchOfEvalInfo Ran
ran; our contract draft was wrong, not the code
r-three/mats/src/eval/utils.py
pointer only (licence: NONE) · get_code("001b8f851cad7c3e")
How it ran

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

average Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/average.py
pointer only (licence: NONE) · get_code("1f58f45fd3f59164")
How it ran

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

cg_forward Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/conjugateGradient_average.py
pointer only (licence: NONE) · get_code("8f9e07b0e7fec4c9")
How it ran

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

cg_forwardBackward Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/conjugateGradient_fisherMerging.py
pointer only (licence: NONE) · get_code("4ee4acc1889850cd")
How it ran

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

conjugateGradient_average Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/conjugateGradient_average.py
pointer only (licence: NONE) · get_code("b4a85591e4919f77")
How it ran

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

conjugateGradient_diagonalFisher Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/conjugateGradient_diagonalFisher.py
pointer only (licence: NONE) · get_code("9562fd0d3e9b02ab")
How it ran

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

conjugateGradient_fisherMerging Not yet run
unverified (harvested, no recorded run)
r-three/mats/src/merging/conjugateGradient_fisherMerging.py
pointer only (licence: NONE) · get_code("18db893c37a2f806")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, r-three/mats 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, 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 8 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

Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are matched before being merged. We connect the task parameter subspace of a given model to its loss landscape and formalize how this approach to model merging can be seen as solving a linear system of equations. While past work has generally been limited to linear systems that have a closed-form solution, we consider using the conjugate gradient method to find a solution. We show that using the conjugate gradient method can outperform closed-form solutions, enables merging via linear systems that are otherwise intractable to solve, and flexibly allows choosing from a wide variety of initializations and estimates for the ''task parameter subspace''. We ultimately demonstrate that our merging framework called ''Matching Models in their Task Parameter Subspace'' (MaTS) achieves state-of-the-art results in multitask and intermediate-task model merging. We release all of the code and checkpoints used in our work at https://github.com/r-three/mats.

For agents

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

get_harvested_code_for_paper("2312.04339")
get_code_for_paper("2312.04339")
have("2312.04339")

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

curl https://syntology.ai/api/ran/2312.04339.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.04339.svg)](https://syntology.ai/paper/2312.04339)

Connect an agent — have() is free.