# From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles

arXiv: https://arxiv.org/abs/2609.07673 · HTML: https://mlsanity.com/paper/2609.07673/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [SimPO: Simple Preference Optimization with a Reference-Free Reward](https://mlsanity.com/paper/2405.14734/) (2024)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Exploring the Limits of Language Modeling](https://mlsanity.com/paper/1602.02410/) (2016)
- [Long Short-Term Memory-Networks for Machine Reading](https://mlsanity.com/paper/1601.06733/) (2016)
- [Structural Scaffolds for Citation Intent Classification in Scientific Publications](https://mlsanity.com/paper/1904.01608/) (2019)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process](https://mlsanity.com/paper/2503.08569/) (2025)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Transitive Reduction of Citation Networks](https://mlsanity.com/paper/1310.8224/) (2013)

## Abstract (arXiv)

Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a paper's contribution. We introduce contribution-based credit scoring for research articles: a structured citation analysis that decomposes a paper's credit between its own original contribution and the prior work it builds on. Motivated by a cooperative-game view of scientific credit, we propose the contribution tree, a hierarchical framework that conserves importance across the document structure and separates original from citation-derived contribution. To make this framework scalable, we use LLMs as noisy comparative estimators of local importance. We further extend the model to article collections by propagating contributions through weighted citation graphs, yielding corpus-level contributions and normalized influence scores. Our experiments suggest that our framework captures contribution signals beyond surface-level heuristics. Our code is available at https://github.com/sanaebrahimi/Importance_Scoring/