Open Research Knowledge Graph

@orkg
142 Followers
30 Following
98 Posts
Scholarly Knowledge. Structured. FAIR.
Homepagehttps://orkg.org/
ORKG Askhttps://ask.orkg.org/

Hey, participants of ICSA 2026! Have you seen the Open Science Challenge?

Annotate your paper with SciKGTex, make it machine-actionable and have the chance to win our ORKG Open Science Award! 🏆
It is super easy. Just use the SciKGTeX package and add a few structured descriptions to your LaTeX code. It does not only simplify the contribution to research knowledge graphs but also promotes the semantic representations in scientific communication and, thus, Open Science.
➡️ https://conf.researchr.org/track/icsa-2026/icsa-2026-open-science-challenge#Open-Science-Competition

ICSA 2026 - Open Science Challenge - ICSA 2026

Since the introduction of the Artifacts Evaluation Track in 2021, ICSA has taken important steps toward improving reproducibility and transparency in software architecture research. This track encouraged authors to share their tools, datasets, and replication packages, setting a strong foundation for artifact quality and reusability. Building on this success, we launch the ICSA 2026 Open Science Challenge. This challenge is inspired by ongoing discussions, challenges, and meta-research efforts in the software architecture community and beyond. This includes, among others: Fostering availa ...

ORKG Ask – KI unterstützt Forschende bei Recherchen – Wissen hoch N

Leibniz Universität Hannover

📣 New Paper

Title - YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering

We tackle the optimism bias in LLMs and their unsuitability as robust evaluators. One of our scienceQ&A dataset is sourced from the ORKG.

➡️ Preprint: https://arxiv.org/abs/2505.14279

YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering

Large Language Models (LLMs) drive scientific question-answering on modern search engines, yet their evaluation robustness remains underexplored. We introduce YESciEval, an open-source framework that combines fine-grained rubric-based assessment with reinforcement learning to mitigate optimism bias in LLM evaluators. We release multidisciplinary scienceQ&A datasets, including adversarial variants, with evaluation scores from multiple LLMs. Independent of proprietary models and human feedback, our approach enables scalable, cost-free evaluation. By advancing reliable LLM-as-a-judge models, this work supports AI alignment and fosters robust, transparent evaluation essential for scientific inquiry.

arXiv.org

📣 New Paper: Human-In-The-Loop Workflow for Neuro-Symbolic Scholarly Knowledge Organization

We developed a Human-in-the-Loop workflow that supports researchers in creating and structuring scientific knowledge. Find relevant literature and extract relevant key information in a two-stage process

➡️ Jupyter Book: https://gitlab.com/TIBHannover/orkg/hitl-litrev-kg

➡️ Preprint: https://arxiv.org/abs/2506.03221

TIB Hannover / Open Research Knowledge Graph (ORKG) / HITL-LitRev-KG · GitLab

GitLab.com

GitLab

@tibhannover @Life_is

Thanks for letting us know! Seemed to be a server error earlier. Now the data protection sheet is loaded.

Last chance to apply for our ORKG Curation Grants! The application deadline is this Sunday.

➡️ https://orkg.org/page/call-curation-grants-2025

Open Research Knowledge Graph

📣 Don't miss this opportunity to learn about how machine-actionable knowledge can simplify your #academiclife and help with your #research tasks!

Join our webinar:
⏰ April 28, 15:00
➡️ https://orkg.org/page/5th-orkg-webinar

#ResearchTools

Open Research Knowledge Graph

📣 We are excited to announce our 5th ORKG Webinar!

Learn how to create and use machine-actionable knowledge for your own research to get ahead of the publication flood.

⏰ April 28th, 3pm (CEST)

➡️ https://orkg.org/page/5th-orkg-webinar

Open Research Knowledge Graph

⚛️ It’s #WorldQuantumDay!

❓ Did you know that there have been more than 6000 publications on quantum physics this year already?

Keeping track can get quite overwhelming. ORKG is here to help. Find out how in this article on @tibhannover 's blog:
➡️ https://blog.tib.eu/2025/04/14/frag-die-quantenphysik-ki-auf-der-suche-nach-antworten-in-physikalischer-literatur/

Frag die Quantenphysik – KI auf der Suche nach Antworten in physikalischer Literatur - TIB-Blog

Die Quantenphysik ist eines der faszinierendsten Forschungsfelder unserer Zeit. So ist es nicht verwunderlich, dass auch einhundert Jahre nach ihrer Begründung weiter viel publiziert wird. Von Grundlagenforschung bis zur Anwendung, von Quantenverschränkung bis Qbits: Allein im Quantenjahr 2025 verzeichnet arXiv bislang über 6.000 Veröffentlichungen zur Quantenphysik. Einen besonders nutzerfreundlichen Zugang ermöglicht der KI-Assistent ORKG Ask. Forschenden können ihre Fragen in natürlicher Sprache stellen und erhalten eine Antwort aus fast 80 Millionen Open-Access-Veröffentlichungen. Zusätzlich zur synthetisierten Kurzzusammenfassung zeigt ORKG Ask eine tabellarische Übersicht der relevantesten Veröffentlichungen an.

TIB-Blog

@cark @orkg

Hey, here are some answers, hope this helps!

1. Ask is currently going through some data ingests which have led to some complications. The service will be back soon and as usual available to everyone. Glad to hear that is a useful resource to you and sorry for the unexpected downtime!

2. That is our old account. We switched to this account a while ago since it seemed to reach more people. This all happened when we were new to Mastodon and were still trying around with instances.