{"id":42757896,"url":"https://github.com/jd-coderepos/scisynthesis","last_synced_at":"2026-01-29T20:17:05.079Z","repository":{"id":234241472,"uuid":"788501342","full_name":"jd-coderepos/scisynthesis","owner":"jd-coderepos","description":"for prompts, dataset, and code addressing the task of scientific synthesis","archived":false,"fork":false,"pushed_at":"2025-04-11T09:27:26.000Z","size":9429,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-04T19:49:16.494Z","etag":null,"topics":["corpus","dataset","evaluation-datasets","large-language-models","natural-language-generation","natural-language-understanding","scientific-summarization","scientific-synthesis"],"latest_commit_sha":null,"homepage":"https://github.com/HamedBabaei/LLMs4Synthesis","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jd-coderepos.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-04-18T14:38:17.000Z","updated_at":"2025-04-23T12:30:25.000Z","dependencies_parsed_at":"2025-04-11T10:53:36.376Z","dependency_job_id":"a27887f6-1477-4ada-953d-5571319f1998","html_url":"https://github.com/jd-coderepos/scisynthesis","commit_stats":null,"previous_names":["jd-coderepos/scisynthesis"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jd-coderepos/scisynthesis","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-coderepos%2Fscisynthesis","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-coderepos%2Fscisynthesis/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-coderepos%2Fscisynthesis/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-coderepos%2Fscisynthesis/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jd-coderepos","download_url":"https://codeload.github.com/jd-coderepos/scisynthesis/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jd-coderepos%2Fscisynthesis/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28884285,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-29T19:55:09.949Z","status":"ssl_error","status_checked_at":"2026-01-29T19:55:08.490Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["corpus","dataset","evaluation-datasets","large-language-models","natural-language-generation","natural-language-understanding","scientific-summarization","scientific-synthesis"],"created_at":"2026-01-29T20:17:04.360Z","updated_at":"2026-01-29T20:17:05.072Z","avatar_url":"https://github.com/jd-coderepos.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n \u003ch1\u003eORKG Synthesis Dataset\u003c/h1\u003e\n\u003c/div\u003e\n\n[//]: # (\u003ch3\u003eScience Synthesis\u003c/h3\u003e)\n\n\u003cdiv align=\"center\"\u003e\n \u003cimg src=\"images/llms4synthesis-logo.png\" width=\"800\" height=\"170\"/\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat\u0026labelColor=ef8336)](https://pycqa.github.io/isort/)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)\n\n\u003c/div\u003e\n\n\u003cdiv style=\"color:red;\"\u003eThis work is accepted for publication at JCDL-2024 conference.\u003c/div\u003e\n\n### What is the ORKG Synthesis Dataset?\n\nWe develop a methodology to collect and process scientific papers into a format  ready for synthesis using the Open Research Knowledge Graph, a multidisciplinary platform that facilitates the comparison of scientific contributions. Where later, we introduce new synthesis types —-  paper-wise, methodological, and thematic —- that focus on different\naspects of the extracted insights. Utilizing Mistral-7B and GPT4 , we generate a large-scale dataset of these syntheses.  The established nine quality criteria for evaluating these syntheses, assessed by both an automated LLM evaluator (GPT-4) and a human-crowdsourced survey.\n\n### Directories\n\n* `corpus`: Contains ORKG Synthesis dataset for bot GPT-4 and Mistral-7B for three synthesis objectives (paper-wise, methodological, and thematic). Also Prolific Human Survey Results.\n* `gpt-4 synthesis-evaluator`: Contains `Evaluation System Prompt` and evaluator script.\n* `orkg-comparison-data-gen-scripts`: Synthesis generation scripts.\n* `synthesis-generation-prompts`: Synthesis generation prompts for paper-wise, methodological, and thematic objectives.\n\n### Prolific Survey\nThe [Prolific Survey Participant Demographics](corpus/prolific/README.md) available at Table 1 in the `corpus/prolific` directory.\n\nAlso the [average human and automatic (LLM) evaluation](corpus/prolific/README.md) available at Table 2 in the `corpus/prolific` directory, representing average human and LLM evaluation scores by characteristic comparisons. For each domain/characteristic, the human scores are an average of 18 judgements (6 syntheses (2 samples x 3 synthesis types) x 3 participants) while the auto scores are an average of 6 judgements (6 syntheses (2 samples x 3 synthesis types) x 1 LLM evaluation).\n\n### LLMs4Synthesis\nThe **LLMs4Synthesis** framework on top of this dataset is available at  https://github.com/HamedBabaei/LLMs4Synthesis.\n\n\n### Citation\n\nIf you find this work useful, please consider citing our research papers listed below.\n\n```\n@inproceedings{evans-etal-2024-large,\n    title = \"Large Language Models as Evaluators for Scientific Synthesis\",\n    author = {Evans, Julia  and\n      D{'}Souza, Jennifer  and\n      Auer, S{\\\"o}ren},\n    editor = \"Luz de Araujo, Pedro Henrique  and\n      Baumann, Andreas  and\n      Gromann, Dagmar  and\n      Krenn, Brigitte  and\n      Roth, Benjamin  and\n      Wiegand, Michael\",\n    booktitle = \"Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024)\",\n    month = sep,\n    year = \"2024\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.konvens-main.1/\",\n    pages = \"1--22\"\n}\n\n\n@inbook{babaei-giglou-etal-2025-synthesis,\nauthor = {Babaei Giglou, Hamed and D'Souza, Jennifer and Auer, S\\\"{o}ren},\ntitle = {LLMs4Synthesis: Leveraging Large Language Models for Scientific Synthesis},\nyear = {2025},\nisbn = {9798400710933},\npublisher = {Association for Computing Machinery},\naddress = {New York, NY, USA},\nurl = {https://doi.org/10.1145/3677389.3702565},\narticleno = {31},\nnumpages = {12}\n}\n\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjd-coderepos%2Fscisynthesis","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjd-coderepos%2Fscisynthesis","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjd-coderepos%2Fscisynthesis/lists"}