D
danielsaatchi/G-indexes
G-indexes powered by Ollama AI-Agent & Google Scholar for Researchers Forensics and Research Integrity
更新 2026-11-19
在 GitHub 查看 ↗直链 · 无中转页
- ★ 数取值
- 0 ★ · danielsaatchi/G-indexes · 取自 GitHub 搜索 API · (2026-11-19 20:00:48 核对)
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型:开源项目
- 收录与活跃
- 收录于 2026-11-20 · 最近见到 2026-11-20 · 共见到 1 次 · 被 2 个来源列出
- 评分构成
- 综合分 203 · 2 个来源 · repo
常见问题(答案都来自我们的记录)
它适合谁 / 用来做什么?
我们把它归在这些标签下: 开源项目。标签来自条目自身,不是我们强加的分类。
谁维护它、还在更新吗?
仓库
danielsaatchi/G-indexes;我们收录于 2026-11-20;最近见到 2026-11-20。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。README 原文(英文,未翻译) · 在 GitHub 读完整 README →
# G-Indexes
以下摘录自该仓库的 README(片段)
Forensic G-indexes for researchers powered by Ollama AI-Agent & Google Scholar
## G-Index Scholar Agent (local AI-Agent app)
A small local web app that reconstructs a Google Scholar "Citations" page and
adds three extra indicators — G1, G2, G3 — computed from the
Graded Authorship-Filtered Citation Metrics (GAFCM) framework:
G1-index = citations from publications where you are the 1st author
G2-index = citations from publications where you are 1st or 2nd author
G3-index = citations from publications where you are 1st, 2nd, or 3rd author
GRW-index = citations from reviews for authorship inflation and citation anomaly
It runs entirely on your machine:
The Flask server scrapes the public Google Scholar profile you give it
(server-side, so there's no browser CORS/blocking issue).
The server also talks to your local Ollama instance to help determine your
authorship position in each paper (optional — a surname/initial heuristic
runs even without it, and you can always correct positions by hand).
## Setup
bash
cd gindex_app
pip install -r requirements.txt
python app.py
Then open http://localhost:5000 or http://127.0.0.1:5000 in your browser.
## Using it
1. The Scholar URL field is pre-filled with default profile of DANIEL SAATCHI
(https://scholar.google.com/citations?user=Uv7KQxEAAAAJ&hl=en) — change
it if needed.
2. Set Ollama model to whatever you have pulled locally, e.g. gemma4:latest
(Ollama's current naming — if you literally have a model tagged
gemma4:e4b, type that exact tag; just make sure it's been pulled with
ollama pull first).
3. Leave Ollama server as http://localhost:11434 or http://127.0.0.1:11434 unless yours runs
elsewhere.
4. Click Fetch profile — this pulls your full publication list, citation
counts, and Scholar's own Citations/h-index/i10-index, laid out like your
real Scholar "Citations" page.
5. Click Compute G1 / G2 / G3 / GRw — the server sends each paper's author
byline to your local Ollama model, asks it to find your position in the
author list, falls back to a heuristic match where the model can't decide,
and then computes G1/G2/G3 (and re-derives Citations/h-index/i10-index)
from the results.
6. Every row's Position box is editable — fix it directly for any paper
(equal-contribution, alphabetical ordering, consortium authorship, etc.)
and the totals recompute instantly.
## Notes
Google Scholar occasionally shows a CAPTCHA to automated requests. If
Fetch profile fails with a bot-check message, wait a few minutes and
retry — this is Scholar's rate limiting, not a bug in the app.
Author lists on the Citations page are sometimes truncated with "…". Check
resolve truncated author lists before fetching to have the app pull the
full author list from each paper's detail page (slower — capped at 15
papers per fetch to stay polite to Scholar).
If the Ollama call fails (model not pulled, server not running, wrong
port), the app still computes G1/G2/G3 from the heuristic surname match and
## G-Index Scholar Agent (local AI-Agent app)
A small local web app that reconstructs a Google Scholar "Citations" page and
adds three extra indicators — G1, G2, G3 — computed from the
Graded Authorship-Filtered Citation Metrics (GAFCM) framework:
G1-index = citations from publications where you are the 1st author
G2-index = citations from publications where you are 1st or 2nd author
G3-index = citations from publications where you are 1st, 2nd, or 3rd author
GRW-index = citations from reviews for authorship inflation and citation anomaly
It runs entirely on your machine:
The Flask server scrapes the public Google Scholar profile you give it
(server-side, so there's no browser CORS/blocking issue).
The server also talks to your local Ollama instance to help determine your
authorship position in each paper (optional — a surname/initial heuristic
runs even without it, and you can always correct positions by hand).
## Setup
bash
cd gindex_app
pip install -r requirements.txt
python app.py
Then open http://localhost:5000 or http://127.0.0.1:5000 in your browser.
## Using it
1. The Scholar URL field is pre-filled with default profile of DANIEL SAATCHI
(https://scholar.google.com/citations?user=Uv7KQxEAAAAJ&hl=en) — change
it if needed.
2. Set Ollama model to whatever you have pulled locally, e.g. gemma4:latest
(Ollama's current naming — if you literally have a model tagged
gemma4:e4b, type that exact tag; just make sure it's been pulled with
ollama pull first).
3. Leave Ollama server as http://localhost:11434 or http://127.0.0.1:11434 unless yours runs
elsewhere.
4. Click Fetch profile — this pulls your full publication list, citation
counts, and Scholar's own Citations/h-index/i10-index, laid out like your
real Scholar "Citations" page.
5. Click Compute G1 / G2 / G3 / GRw — the server sends each paper's author
byline to your local Ollama model, asks it to find your position in the
author list, falls back to a heuristic match where the model can't decide,
and then computes G1/G2/G3 (and re-derives Citations/h-index/i10-index)
from the results.
6. Every row's Position box is editable — fix it directly for any paper
(equal-contribution, alphabetical ordering, consortium authorship, etc.)
and the totals recompute instantly.
## Notes
Google Scholar occasionally shows a CAPTCHA to automated requests. If
Fetch profile fails with a bot-check message, wait a few minutes and
retry — this is Scholar's rate limiting, not a bug in the app.
Author lists on the Citations page are sometimes truncated with "…". Check
resolve truncated author lists before fetching to have the app pull the
full author list from each paper's detail page (slower — capped at 15
papers per fetch to stay polite to Scholar).
If the Ollama call fails (model not pulled, server not running, wrong
port), the app still computes G1/G2/G3 from the heuristic surname match and
收录徽章(可选)
想把收录标记放进 README 就复制这行,可选,不影响收录。
[](https://anclum.com/zh/s/danielsaatchi-g-indexes/)
- 来源
- github · https://github.com/danielsaatchi/G-indexes
- 按领域浏览
- 开源项目
- 收录来源
- 2 个独立来源
- 收录于
- 今天
更多条目
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。