SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.13434 · 2026

Modality-free Graph In-context Alignment

Siqiang Luo, Wei Zhuo, Meta Episode, Learning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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 4 have no contract verdict; 1 failure of our instrument; 4 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/2603.13434.json · badge: /api/ran/2603.13434.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
JhuoW/MF-GIA community
Papers with Code archive
6 ran · 4 no recorded run
FunctionStatusWhere it lives
ConvProjection Ran
ran on a synthesized input
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("8bb3ce4a5edcb089")
How it ran

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

DomainFiLM Ran
ran on a synthesized input
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("b829d4803e8ebf14")
How it ran

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

GraphProbContrastLoss Ran
ran on a synthesized input
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("44fe9315b5e5c3ec")
How it ran

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

MLPLayer Ran
ran on a synthesized input
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("8475cb62293539a2")
How it ran

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

_iter_params Ran
ran; our contract draft was wrong, not the code
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("53fa46754d41ff61")
How it ran

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

flatten_grads Ran
ran, honoured the contract we drafted
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("5bed140f7ab8dabf")
How it ran

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

DomainEmbedder Not yet run
unverified (harvested, no recorded run)
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("d9f59267ab679f28")
How it ran

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

DomainEmbeddingExtractor Not yet run
unverified (harvested, no recorded run)
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("9d5689c27cbbb095")
How it ran

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

GFM Not yet run
unverified (harvested, no recorded run)
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("be3e96583742459d")
How it ran

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

PAMA Not yet run
unverified (harvested, no recorded run)
JhuoW/MF-GIA/model/pt_model.py
pointer only (licence: NONE) · get_code("b05122b5574df53b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JhuoW/MF-GIA 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 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 10 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

In-context learning (ICL) converts static encoders into task-conditioned reasoners, enabling adaptation to new data from just a few examples without updating pretrained parameters. This capability is essential for graph foundation models (GFMs) to approach LLM-level generality. Yet current GFMs struggle with crossdomain alignment, typically relying on modality-specific encoders that fail when graphs are pre-vectorized or raw data is inaccessible. In this paper, we introduce Modality-Free Graph In-context Alignment (MF-GIA), a framework that makes a pretrained graph encoder promptable for few-shot prediction across heterogeneous domains without modality assumptions. MF-GIA captures domain characteristics through gradient fingerprints, which parameterize lightweight transformations that align pre-encoded features and indexed labels into unified semantic spaces. During pretraining, a dual prompt-aware attention mechanism with episodic objective learns to match queries against aligned support examples to establish prompt-based reasoning capabilities. At inference, MF-GIA performs parameter-update-free adaptation using only a few-shot support set to trigger cross-domain alignment and enable immediate prediction on unseen domains. Experiments demonstrate that MF-GIA achieves superior few-shot performance across diverse graph domains and strong generalization to unseen domains. The code is available at https://github.com/JhuoW/MF-GIA.

For agents

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

get_harvested_code_for_paper("2603.13434")
get_code_for_paper("2603.13434")
have("2603.13434")

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

curl https://syntology.ai/api/ran/2603.13434.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.13434.svg)](https://syntology.ai/paper/2603.13434)

Connect an agent — have() is free.