# AakashKumarNain/annotated_research_papers

This repo contains annotated research papers that I found really good and useful

Repository: https://github.com/AakashKumarNain/annotated_research_papers
Canonical: https://ross.abutalabs.com/products/annotated_research_papers
License: MIT
License Family: permissive
Topics: research, research-paper, annotations, machine-learning, deep-learning
Last push: 2026-04-19T11:05:59+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 100
- inputs: {"age_days": 2236, "days_push": 136, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2793, forks 267 (observed 2026-08-28T04:07:22.255405+00:00)

## What it is
A curated collection of machine learning and deep learning research papers with the author's handwritten-style annotations explaining key ideas. Papers span computer vision, meta-learning, and other ML topics, with links to code and abstracts.

## Use cases
- find annotated machine learning research papers
- learn to read deep learning papers more easily
- get explanations of arxiv papers like ConvNeXt and EfficientNetV2
- build a habit of reading ML research
- study computer vision research with guided notes
- find papers with linked implementations

## When to choose
- you find research papers intimidating and want guided annotations
- you want a curated, opinionated ML paper reading list
- you prefer visual, pen-and-paper style explanations

## When to avoid
- you need comprehensive coverage of all ML papers
- you want searchable, structured paper databases
- you need production code rather than study material

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation
- domain: machine-learning, deep-learning, computer-vision, tutorials
- platform: cross-platform
- tags: annotated-papers, research-papers, arxiv, reading-list, education

## Member repositories
- AakashKumarNain/annotated_research_papers (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.255405+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:49:13.711321+00:00, confidence not recorded.
  - readme: https://github.com/AakashKumarNain/annotated_research_papers (fetched 2026-08-28T04:07:22.255405+00:00, sha f87501e47dae)
- Data as of 2026-08-30T08:39:29.467469+00:00.