# Hello-SimpleAI/chatgpt-comparison-detection

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

Repository: https://github.com/Hello-SimpleAI/chatgpt-comparison-detection
Canonical: https://ross.abutalabs.com/products/chatgpt-comparison-detection
Homepage: https://arxiv.org/abs/2301.07597
Language: Python
License Family: other
Topics: ai, chatbot, chatgpt, dataset, nlp, openai, text-classification, python, gpt2, gpt3, gpt-3, ml, machine-learning, deep-learning
Last push: 2023-12-01T16:03:51+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 95
- inputs: {"age_days": 1334, "days_push": 1006, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1443, forks 128 (observed 2026-08-28T04:04:44.802330+00:00)

## What it is
The Human ChatGPT Comparison Corpus (HC3) project provides datasets of paired human-expert and ChatGPT answers across domains like open QA, medicine, and finance, in English and Chinese. It also includes trained detectors for classifying text as human- or ChatGPT-generated, accompanying an arXiv research paper.

## Use cases
- detect whether text was written by ChatGPT
- train an AI-generated text classifier
- get a human vs ChatGPT comparison dataset
- research differences between ChatGPT and human expert answers
- fine-tune a model on Chinese and English ChatGPT responses
- benchmark LLM answer quality against human experts

## When to choose
- you need labeled human vs ChatGPT text for training or evaluating detectors
- you want a research-backed AI-text detection baseline in English or Chinese
- you are studying linguistic differences between LLM and human responses

## When to avoid
- you need a production-ready AI content detector with guarantees
- you require a clearly licensed dataset - some source splits have unknown licenses
- you need detection of LLMs other than ChatGPT

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, nlp, data-science
- domain: large-language-models, machine-learning, artificial-intelligence
- platform: python
- tags: chatgpt-detection, ai-generated-text-detection, hc3, text-classification, corpus, huggingface-datasets, english-chinese, natural-language-processing

## Member repositories
- Hello-SimpleAI/chatgpt-comparison-detection (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.802330+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 2026-08-30T04:36:19.361317+00:00, confidence not recorded.
  - readme: https://github.com/Hello-SimpleAI/chatgpt-comparison-detection (fetched 2026-08-28T04:04:44.802330+00:00, sha 0f90d7b996fa)
  - homepage: https://arxiv.org/abs/2301.07597 (fetched 2026-08-29T11:46:23.476160+00:00, sha e4b3ab02c982)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:46:23.482489+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:46:23.478797+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:46:23.484533+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:46:23.480480+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.