attest-detector 0.1.0__tar.gz

attest_detector-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 nehabetai1809
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

attest_detector-0.1.0/PKG-INFO

@@ -0,0 +1,270 @@
+Metadata-Version: 2.1
+Name: attest-detector
+Version: 0.1.0
+Summary: Detect what percentage of a text was written by AI, with per-sentence and per-paragraph breakdowns.
+Author: nehabetai1809
+License: MIT
+Project-URL: Homepage, https://github.com/nehabetai1809/attest-detector
+Project-URL: Repository, https://github.com/nehabetai1809/attest-detector
+Project-URL: Issues, https://github.com/nehabetai1809/attest-detector/issues
+Keywords: ai detection,text analysis,nlp,chatgpt,ai generated text
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing :: Linguistic
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: transformers>=4.35.0
+Requires-Dist: torch>=2.0.0
+Requires-Dist: nltk>=3.8.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: langdetect>=1.0.9
+Provides-Extra: pdf
+Requires-Dist: pypdf>=4.0.0; extra == "pdf"
+Provides-Extra: docx
+Requires-Dist: python-docx>=1.1.0; extra == "docx"
+Provides-Extra: all-formats
+Requires-Dist: pypdf>=4.0.0; extra == "all-formats"
+Requires-Dist: python-docx>=1.1.0; extra == "all-formats"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
+
+# attest-detector
+
+[![Tests](https://github.com/nehabetai1809/attest-detector/actions/workflows/ci.yml/badge.svg)](https://github.com/nehabetai1809/attest-detector/actions/workflows/ci.yml)
+[![PyPI version](https://badge.fury.io/py/attest-detector.svg)](https://pypi.org/project/attest-detector/)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+**Detect what percentage of a piece of text was written by AI.**
+
+`attest-detector` is an offline-friendly Python package that analyzes text using **three different AI detection models** and reports each model's score separately — so you can make your own informed judgement rather than trusting a single black-box score.
+
+## Why three models?
+
+No single AI detection model is reliable on its own for modern AI text. After testing, here's what we found:
+
+| Model | Catches AI text | False positives on human text | Best used for |
+|---|---|---|---|
+| `fakespot` | ~100% | ~66% | Flagging potential AI writing |
+| `roberta` | ~40% | ~6% | Confirming text is human-written |
+| `chatgpt` | ~3% | ~0% | "Definitely human" confirmation |
+
+Running all three together and reading them side by side gives a much more honest picture than any single score.
+
+> ⚠️ **First run:** Each model (~500MB) is downloaded automatically and cached locally. Subsequent runs are fully offline.
+
+---
+
+## Installation
+
+```bash
+pip install attest-detector
+```
+
+With PDF support:
+```bash
+pip install attest-detector[pdf]
+```
+
+With Word (.docx) support:
+```bash
+pip install attest-detector[docx]
+```
+
+---
+
+## Quick Start
+
+```python
+from ai_detector import Detector
+
+d = Detector()  # runs all three models by default
+result = d.analyze("Your text goes here...")
+
+print(result.summary())
+```
+
+### Example Output
+
+```
+============================================================
+  Overall: 48.8% likely AI-written  [Human]
+  Primary model: fakespot
+============================================================
+
+  Per-model scores (full document):
+    fakespot      100.0%  [✓ AI]
+    roberta        40.3%  [✗ Human]
+    chatgpt         2.9%  [✗ Human]
+
+  Models flagging as AI: 1 / 3
+
+  Analyzed 2 sentence(s) across 1 paragraph(s).
+
+  Per-paragraph breakdown:
+    Para 1:  48.8%  [█████████░░░░░░░░░░░]  [Human]  [1/3 models]
+```
+
+### How to read the results
+
+- **All three models flag AI** → Strong signal the text is AI-written
+- **Only fakespot flags AI** → Uncertain — fakespot has many false positives
+- **All three say Human** → Very likely human-written
+- **roberta and chatgpt both say Human** → Strong signal text is human-written
+
+---
+
+## Per-Sentence and Per-Paragraph Breakdown
+
+```python
+# Per-sentence scores
+for sentence in result.sentences:
+    print(f"{sentence.ai_score:.1%}  [{sentence.label}]  {sentence.text}")
+    print(f"  Model scores: {sentence.model_scores}")
+
+# Per-paragraph scores
+for para in result.paragraphs:
+    print(f"{para.ai_score:.1%}  [{para.label}]")
+    print(f"  {para.models_flagging_ai()}/{len(para.model_scores)} models flagged as AI")
+```
+
+---
+
+## Single Model Mode
+
+```python
+# Use a specific model instead of all three
+d = Detector(model='fakespot')   # best at catching AI
+d = Detector(model='roberta')    # best at confirming human
+d = Detector(model='chatgpt')    # near-zero false positives
+```
+
+---
+
+## Adjusting Sensitivity
+
+```python
+# More sensitive — flags more text as AI
+d = Detector(threshold=0.3)
+
+# Less sensitive — only flags strongly AI text
+d = Detector(threshold=0.7)
+```
+
+---
+
+## CLI Usage
+
+After installation, use `attest-detect` directly in your terminal — no Python needed:
+
+```bash
+# Analyze a text file (runs all three models)
+attest-detect essay.txt
+
+# Analyze a PDF
+attest-detect paper.pdf
+
+# Analyze a Word document
+attest-detect report.docx
+
+# Analyze text directly
+attest-detect --text "Paste your text here"
+
+# Use a specific model
+attest-detect essay.txt --model fakespot
+
+# Show per-sentence breakdown
+attest-detect essay.txt --sentences
+
+# Adjust sensitivity
+attest-detect essay.txt --threshold 0.3
+
+# List available models
+attest-detect --list-models
+```
+
+---
+
+## API Reference
+
+### `Detector(model=None, threshold=0.5, device=None)`
+
+| Parameter | Type | Default | Description |
+|---|---|---|---|
+| `model` | str | `None` | Run a single model: `'roberta'`, `'chatgpt'`, `'fakespot'`. If not set, runs all three. |
+| `threshold` | float | `0.5` | AI cutoff. Lower = more sensitive |
+| `device` | str | `None` | `'cpu'`, `'cuda'`, `'mps'`. Auto-detected |
+
+### `DetectionResult`
+
+| Attribute/Method | Type | Description |
+|---|---|---|
+| `ai_score` | float | Primary model's overall AI probability (0–1) |
+| `label` | str | `'AI'` or `'Human'` |
+| `model_scores` | dict | Every model's score e.g. `{'fakespot': 1.0, 'roberta': 0.4, 'chatgpt': 0.03}` |
+| `sentences` | list | Per-sentence `Segment` list |
+| `paragraphs` | list | Per-paragraph `Segment` list |
+| `models_flagging_ai()` | int | Count of models that scored above threshold |
+| `summary()` | str | Formatted text summary |
+
+### `Segment`
+
+| Attribute/Method | Type | Description |
+|---|---|---|
+| `text` | str | Original text |
+| `ai_score` | float | Primary model's AI probability |
+| `model_scores` | dict | Every model's score for this segment |
+| `label` | str | `'AI'` or `'Human'` |
+| `segment_type` | str | `'sentence'` or `'paragraph'` |
+| `models_flagging_ai(threshold)` | int | Count of models above threshold |
+
+---
+
+## Available Models
+
+| Key | Model | Trained On | Size |
+|---|---|---|---|
+| `fakespot` | `fakespot-ai/roberta-base-ai-text-detection-v1` | Modern AI text | ~500MB |
+| `roberta` | `openai-community/roberta-base-openai-detector` | GPT-2 output (2019) | ~500MB |
+| `chatgpt` | `Hello-SimpleAI/chatgpt-detector-roberta` | ChatGPT output (2023) | ~500MB |
+
+---
+
+## Limitations
+
+- No single model reliably detects all modern AI text — use all three together
+- All models are English-only
+- Very short texts (< 2 sentences) may produce unreliable scores
+- AI detection is probabilistic — treat results as signals, not verdicts
+- Paraphrased or lightly edited AI text may score lower than expected
+
+---
+
+## Running Tests
+
+```bash
+pip install -e ".[dev]"
+pytest tests/ -v
+```
+
+---
+
+## Contributing
+
+Contributions are welcome! Please open an issue first to discuss changes.
+
+1. Fork the repo
+2. Create a feature branch (`git checkout -b feature/my-feature`)
+3. Commit your changes
+4. Push and open a Pull Request
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE) for details.

attest_detector-0.1.0/README.md

@@ -0,0 +1,235 @@
+# attest-detector
+
+[![Tests](https://github.com/nehabetai1809/attest-detector/actions/workflows/ci.yml/badge.svg)](https://github.com/nehabetai1809/attest-detector/actions/workflows/ci.yml)
+[![PyPI version](https://badge.fury.io/py/attest-detector.svg)](https://pypi.org/project/attest-detector/)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+**Detect what percentage of a piece of text was written by AI.**
+
+`attest-detector` is an offline-friendly Python package that analyzes text using **three different AI detection models** and reports each model's score separately — so you can make your own informed judgement rather than trusting a single black-box score.
+
+## Why three models?
+
+No single AI detection model is reliable on its own for modern AI text. After testing, here's what we found:
+
+| Model | Catches AI text | False positives on human text | Best used for |
+|---|---|---|---|
+| `fakespot` | ~100% | ~66% | Flagging potential AI writing |
+| `roberta` | ~40% | ~6% | Confirming text is human-written |
+| `chatgpt` | ~3% | ~0% | "Definitely human" confirmation |
+
+Running all three together and reading them side by side gives a much more honest picture than any single score.
+
+> ⚠️ **First run:** Each model (~500MB) is downloaded automatically and cached locally. Subsequent runs are fully offline.
+
+---
+
+## Installation
+
+```bash
+pip install attest-detector
+```
+
+With PDF support:
+```bash
+pip install attest-detector[pdf]
+```
+
+With Word (.docx) support:
+```bash
+pip install attest-detector[docx]
+```
+
+---
+
+## Quick Start
+
+```python
+from ai_detector import Detector
+
+d = Detector()  # runs all three models by default
+result = d.analyze("Your text goes here...")
+
+print(result.summary())
+```
+
+### Example Output
+
+```
+============================================================
+  Overall: 48.8% likely AI-written  [Human]
+  Primary model: fakespot
+============================================================
+
+  Per-model scores (full document):
+    fakespot      100.0%  [✓ AI]
+    roberta        40.3%  [✗ Human]
+    chatgpt         2.9%  [✗ Human]
+
+  Models flagging as AI: 1 / 3
+
+  Analyzed 2 sentence(s) across 1 paragraph(s).
+
+  Per-paragraph breakdown:
+    Para 1:  48.8%  [█████████░░░░░░░░░░░]  [Human]  [1/3 models]
+```
+
+### How to read the results
+
+- **All three models flag AI** → Strong signal the text is AI-written
+- **Only fakespot flags AI** → Uncertain — fakespot has many false positives
+- **All three say Human** → Very likely human-written
+- **roberta and chatgpt both say Human** → Strong signal text is human-written
+
+---
+
+## Per-Sentence and Per-Paragraph Breakdown
+
+```python
+# Per-sentence scores
+for sentence in result.sentences:
+    print(f"{sentence.ai_score:.1%}  [{sentence.label}]  {sentence.text}")
+    print(f"  Model scores: {sentence.model_scores}")
+
+# Per-paragraph scores
+for para in result.paragraphs:
+    print(f"{para.ai_score:.1%}  [{para.label}]")
+    print(f"  {para.models_flagging_ai()}/{len(para.model_scores)} models flagged as AI")
+```
+
+---
+
+## Single Model Mode
+
+```python
+# Use a specific model instead of all three
+d = Detector(model='fakespot')   # best at catching AI
+d = Detector(model='roberta')    # best at confirming human
+d = Detector(model='chatgpt')    # near-zero false positives
+```
+
+---
+
+## Adjusting Sensitivity
+
+```python
+# More sensitive — flags more text as AI
+d = Detector(threshold=0.3)
+
+# Less sensitive — only flags strongly AI text
+d = Detector(threshold=0.7)
+```
+
+---
+
+## CLI Usage
+
+After installation, use `attest-detect` directly in your terminal — no Python needed:
+
+```bash
+# Analyze a text file (runs all three models)
+attest-detect essay.txt
+
+# Analyze a PDF
+attest-detect paper.pdf
+
+# Analyze a Word document
+attest-detect report.docx
+
+# Analyze text directly
+attest-detect --text "Paste your text here"
+
+# Use a specific model
+attest-detect essay.txt --model fakespot
+
+# Show per-sentence breakdown
+attest-detect essay.txt --sentences
+
+# Adjust sensitivity
+attest-detect essay.txt --threshold 0.3
+
+# List available models
+attest-detect --list-models
+```
+
+---
+
+## API Reference
+
+### `Detector(model=None, threshold=0.5, device=None)`
+
+| Parameter | Type | Default | Description |
+|---|---|---|---|
+| `model` | str | `None` | Run a single model: `'roberta'`, `'chatgpt'`, `'fakespot'`. If not set, runs all three. |
+| `threshold` | float | `0.5` | AI cutoff. Lower = more sensitive |
+| `device` | str | `None` | `'cpu'`, `'cuda'`, `'mps'`. Auto-detected |
+
+### `DetectionResult`
+
+| Attribute/Method | Type | Description |
+|---|---|---|
+| `ai_score` | float | Primary model's overall AI probability (0–1) |
+| `label` | str | `'AI'` or `'Human'` |
+| `model_scores` | dict | Every model's score e.g. `{'fakespot': 1.0, 'roberta': 0.4, 'chatgpt': 0.03}` |
+| `sentences` | list | Per-sentence `Segment` list |
+| `paragraphs` | list | Per-paragraph `Segment` list |
+| `models_flagging_ai()` | int | Count of models that scored above threshold |
+| `summary()` | str | Formatted text summary |
+
+### `Segment`
+
+| Attribute/Method | Type | Description |
+|---|---|---|
+| `text` | str | Original text |
+| `ai_score` | float | Primary model's AI probability |
+| `model_scores` | dict | Every model's score for this segment |
+| `label` | str | `'AI'` or `'Human'` |
+| `segment_type` | str | `'sentence'` or `'paragraph'` |
+| `models_flagging_ai(threshold)` | int | Count of models above threshold |
+
+---
+
+## Available Models
+
+| Key | Model | Trained On | Size |
+|---|---|---|---|
+| `fakespot` | `fakespot-ai/roberta-base-ai-text-detection-v1` | Modern AI text | ~500MB |
+| `roberta` | `openai-community/roberta-base-openai-detector` | GPT-2 output (2019) | ~500MB |
+| `chatgpt` | `Hello-SimpleAI/chatgpt-detector-roberta` | ChatGPT output (2023) | ~500MB |
+
+---
+
+## Limitations
+
+- No single model reliably detects all modern AI text — use all three together
+- All models are English-only
+- Very short texts (< 2 sentences) may produce unreliable scores
+- AI detection is probabilistic — treat results as signals, not verdicts
+- Paraphrased or lightly edited AI text may score lower than expected
+
+---
+
+## Running Tests
+
+```bash
+pip install -e ".[dev]"
+pytest tests/ -v
+```
+
+---
+
+## Contributing
+
+Contributions are welcome! Please open an issue first to discuss changes.
+
+1. Fork the repo
+2. Create a feature branch (`git checkout -b feature/my-feature`)
+3. Commit your changes
+4. Push and open a Pull Request
+
+---
+
+## License
+
+MIT — see [LICENSE](LICENSE) for details.

attest_detector-0.1.0/ai_detector/__init__.py

@@ -0,0 +1,23 @@
+"""
+attest-detector
+---------------
+Detect what percentage of a text was written by AI.
+Provides overall score, per-sentence, and per-paragraph breakdowns.
+
+Basic usage:
+    from ai_detector import Detector
+
+    d = Detector()
+    result = d.analyze("Your text goes here...")
+
+    print(result.ai_score)          # e.g. 0.82  → 82% likely AI
+    print(result.summary())         # human-readable summary
+    for s in result.sentences:
+        print(s.text, s.ai_score)   # per-sentence scores
+"""
+
+from .detector import Detector
+from .result import DetectionResult, Segment
+
+__version__ = "0.1.0"
+__all__ = ["Detector", "DetectionResult", "Segment"]