BERT-based AI-generated academic text detection model
Russian text quality for AI agents — neuroslop cleanup, typography, information style, editorial standards, UX writing, business correspondence. Scores text 0–10. 2,000+ linguistic atoms.
Skill для AI-агентов (Claude Code, Codex, OpenClaw, Hermes): убирает 37 признаков AI-генерации из русского текста и проверяет, писала ли его нейросеть - канцелярит, штампы ChatGPT, артефакты копипаста | Russian AI-text humanizer & detector skill for coding agents
In today's rapidly evolving landscape, vale-ai-tells is a comprehensive, cutting-edge Vale style package that empowers writers to seamlessly delve into the rich tapestry of AI tells. It's not just a rule set; it's a game-changer that supercharges your prose, unlocks new possibilities, and really lands. Ship cleaner prose. Full stop. 🚀
[NeurIPS 2024] DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline.
Release package for SlopShape: Identifying AI-Generated Commercial Web Content (verification artifacts, instrument, prompts, code)
Uncertainty-gated two-stage AI-text detection with fast DTD routing and cross-family MS-LRC evidence. Sole-author submission to UncertaiNLP 2026 @ EMNLP.
[NeurIPS 2025] DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
Open-source AI text detector — VirusTotal for AI slop. 23 engines, self-hosted, runs on CPU. Scan text or URLs locally.
Strip AI writing patterns from any text. Claude Code skill with 507-entry banned word list, structural pattern detection, and 12-check validation.
A simple web app that can be used to detect AI-generated text in the Indonesian language, using various AI models such as LSTM, GRU, Bi-LSTM, Bi-GRU, and IndoBERT
Clean the AI out of text and detect AI slop - bilingual (EN+RU) Claude skill. Rewrites AI cliches into natural prose, rates AI-likeness, and tells decorative AI emoji from genuine human emoji.
免费的本地 AI 率 / AIGC 检测工具箱：拖入论文（PDF/DOCX/TXT）即出整篇 AI 生成占比与段落级高亮，并给出 AI 降重闭环。全程离线推理、论文不上传。9 项方法：SimpleAI 中文 / GLTR 困惑度 / Fast-DetectGPT / DetectGPT / Binoculars。Free, private, offline AI-text detector for theses.
Claude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.
A measuring instrument for text, not an AI detector. Estimates statistical signals of machine-generated language and reports them with measured false-positive rates, broken down by text category. Abstains when the evidence doesn't hold. Never asserts authorship. Runs entirely locally; Spanish calibrated first.
Reproducibility bundle for the paper 'One Prediction Set, Two Reported Results: Provenance Linkage and a Reproducible Benchmark-Audit Sequence for AI-Text Detection'. Seven-step audit sequence, executable checks, sanitized per-item predictions with SHA-256 manifest.
Local-first toolkit for detecting AI-generated text and disrupting classical detectors plus statistical LLM watermarks (SynthID-Text / tournament-sampling style).
Transparent, explainable, local AI-generated-text detector: multi-signal (NLTK, GPT-2 perplexity, Binoculars cross-perplexity, calibrated ensemble) with a real evaluation harness — verdict, confidence, per-signal metrics, and reasoning, not one opaque score.
Sparse probing and activation patching of AI-text detection neurons in frozen BERT (EMNLP 2026)
To associate your repository with the ai-text-detection topic, visit your repo's landing page and select "manage topics."