From cfb61232fc341bfe849907bae556c8bc37e77f80 Mon Sep 17 00:00:00 2001 From: Tal Ifargan <65530510+TalIfargan@users.noreply.github.com> Date: Mon, 13 May 2024 22:18:37 +0300 Subject: [PATCH] Update README.md add data-to-paper project --- README.md | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/README.md b/README.md index 5cba36d..01e10aa 100644 --- a/README.md +++ b/README.md @@ -1067,6 +1067,41 @@ Build-your-own, SDK for agents, Multi-agent +## [data-to-paper](https://github.com/Technion-Kishony-lab/data-to-paper) +AI-driven research from data to human-verifiable research papers +
+ +
+ +
+ +### Category +Science, Research, Multi-agent + +### Description +[*data-to-paper*](https://arxiv.org/abs/2404.17605) is a framework for systematically navigating the power of AI to perform complete end-to-end +scientific research, starting from raw data and concluding with comprehensive, transparent, and human-verifiable +scientific papers. + +Towards this goal, *data-to-paper* systematically guides interacting +LLM and rule-based agents through the conventional scientific path, from annotated data, through creating +research hypotheses, conducting literature search, writing and debugging data analysis code, +interpreting the results, and ultimately the step-by-step writing of a complete research paper. + +The *data-to-paper* framework is created as a research project to understand the +capacities and limitations of LLM-driven scientific research, and to develop ways of harnessing LLM to accelerate +research while maintaining, and even enhancing, key scientific values, such as transparency, traceability and verifiability, +and while allowing scientist to oversee and direct the process +[see also: [living guidelines](https://www.nature.com/articles/d41586-023-03266-1)]. + + +### Links +- [GitHub](https://github.com/Technion-Kishony-lab/data-to-paper) +- [arXiv preprint](https://arxiv.org/abs/2404.17605) +- [Demo video](https://www.youtube.com/watch?v=Nt_460MmM8k) + +
+ ## [Databerry](https://www.databerry.ai/) (Pivoted to Chaindesk) No-code cahtbot building