Independent by design · no pay-to-rank placements  · How we evaluate tools →
Anclum Submit
D

danielsaatchi/G-indexes

Independent directory — not the official site. Details below come from the project's public repository.

G-indexes powered by Ollama AI-Agent & Google Scholar for Researchers Forensics and Research Integrity

Before you install: no copy-paste command · license MIT

First step: nothing runnable here yet - start from the repository: https://github.com/danielsaatchi/G-indexes

updated 2026-11-19
View on GitHub ↗Direct link · no redirect page
Star count
0 ★ · danielsaatchi/G-indexes · read from the GitHub search API · (checked 2026-11-19 20:00:48)
Source
read directly from its GitHub page · type: open-source project
Harvest history
first seen 2026-11-20 · last seen 2026-11-20 · seen 1× · listed by 2 sources
Score
score 203 · 2 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository danielsaatchi/G-indexes;first catalogued 2026-11-20;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.
README excerpt (English, untranslated) · Read the full README on GitHub →

# G-Indexes

Excerpted from the repository README (abridged)

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
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[![Listed on Anclum](https://anclum.com/badge/listed.svg)](https://anclum.com/en/s/danielsaatchi-g-indexes/)
Source
github · https://github.com/danielsaatchi/G-indexes
Browse by field
Open source
Listed by
2 independent sources
added
today

More entries

All 1,875 →

Filed under

Every tag opens the full list for that filter. Counts are the live catalogue figures.

Browse all fields →

← Back to index