Skip to content

Identifier-Derived Signal and Sanitization Degeneracy in Graph Learning: A Sufficiency-Aware Audit

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

# Suggested Zenodo metadata Use these fields when creating the Zenodo record. Replace placeholders as needed. **Title** Reproducibility package for *Identifier-Derived Signal and Sanitization Degeneracy in Graph Learning: A Sufficiency-Aware Audit* **Creator** Mücahit Soylu — Inonu University, Faculty of Engineering, Department of Software Engineering **Resource type** Dataset / software-supporting research artifact (choose the closest option offered by the Zenodo form). **Description** Reproducibility archive accompanying the manuscript *Identifier-Derived Signal and Sanitization Degeneracy in Graph Learning: A Sufficiency-Aware Audit*. The archive contains archived MANTRA-2D and ModelNet10 run-level results, grouped MANTRA-3D summaries, statistical reanalysis scripts and outputs, synthetic regular-graph controls, generated figures, provenance notes, and complete LaTeX manuscript source. The archive documents explicit reproducibility boundaries: sample-level MANTRA triangulations and the historical MANTRA graph-construction/training source were not present in the original artifact, and exact end-to-end historical ModelNet10 retraining is not claimed where helper modules are unavailable. **Keywords** graph neural networks; MANTRA; graph learning; representation degeneracy; identifier-derived features; shortcut learning; reproducibility; benchmark audit **Version** 1.0.0 **Related work** Add the final journal article DOI after acceptance/publication. If Zenodo allows a relation type, use “is supplement to” or the closest available relation. **License** Choose the license you want to grant before publishing the Zenodo record. No license has been imposed inside this package. **After deposit** 1. Copy the assigned Zenodo DOI.2. Replace `https://doi.org/10.5281/zenodo.XXXXXXX` in the manuscript and `CITATION.cff`.3. Recompile the PDF.4. If you create a new Zenodo version later, cite the version-specific DOI when exact artifact identity matters; use the concept DOI when you want a DOI that resolves to the latest version.

View source

Similar papers

#computer vision Conference Aug 2008

Scrum in a Multiproject Environment: An Ethnographically-Inspired Case Study on the Adoption Challenges

Agile methods continue to gain popularity. In particular, the Scrum method appears to be on the verge of becoming a de-facto standard in the industry, leading the so called Agile movement. While there are success stories and recommendations, there is little scientifically valid evidence of the challenges in the adoptio...

A. Marchenko, P. Abrahamsson · 59 citations · ⚡11
#computer vision Open access Sep 2012

Making the leap to a software platform strategy: Issues and challenges

A comprehensive taxonomy of the challenges faced when a medium-scale organization decided to adopt software platforms is provided, namely: business challenges, organizational challenges, technical challenges, and people challenges.

Yaser Ghanam, F. Maurer, P. Abrahamsson · 41 citations · ⚡3
#machine learning Open access Mar 2024

Integration of molecular coarse-grained model into geometric representation learning framework for protein-protein complex property prediction

MCGLPPI, a novel geometric representation learning framework that combines graph neural networks (GNNs) with the MARTINI molecular coarse-grained (CG) model to predict overall PPI properties accurately and efficiently, offers an effective and efficient solution for PPI overall property predictions.

Yang Yue, Shu Li, Yihua Cheng et al. · 15 citations

PepPCBench is a Comprehensive Benchmarking Framework for Protein-Peptide Complex Structure Prediction

PepPCBench enables a robust evaluation of PFNN-based methods and supports their continued development for peptide-protein structure prediction, and highlights the influence of peptide length, conformational flexibility, and training set similarity on prediction accuracy.

Si-Long Zhai, Huifeng Zhao, Ji-Ke Wang et al. · 13 citations · ⚡1
#machine learning Open access Sep 2025

Unified and explainable molecular representation learning for imperfectly annotated data from the hypergraph view

OmniMol is presented, a framework using hypergraphs to improve predictions of molecular properties, addressing challenges of imperfect data annotation and enhancing model explainability, and achieves state-of-the-art performance in properties prediction.

Bowen Wang, Junyou Li, Donghao Zhou et al. · 11 citations

Related blog posts

Microsoft Research Blog Jul 13, 2026

Verifying Rust cryptography in SymCrypt, from standards to code

Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.