paper-polisher

学术论文润色助手：AI生成率自检、学术风格与术语润色建议、翻译腔检测、隐喻审计与质量报告，助力论文精修与学术写作。 AI writing detection (AI-rate self-check for authors), academic polishing guidance (style, terminology, translation-smell), metaphor audit, quality report, AIGC compliance label check (China 2025-09 labeling rules), paragraph-level attribution, journal precheck. Bilingual CN/EN, 100% local, zero upload, zero credentials. v3: 11-layer recalibrated rule engine + token-spectrum layer + length-routed fusion + optional supervised Qwen3-0.6B ONNX layer (AUROC 1.0 on held-out test) + LLM fingerprint attribution (GLM / DeepSeek / Qwen / Kimi / MiniMax / GPT / Claude / Gemini) + freshness pipeline. Base-engine numbers reproduce from the bundled held-out evaluation; supervised-layer columns are author-side held-out measurements (the model itself is not bundled).

存档时间线

版本索引永久保留；内容副本只保留最新 1 份，更早版本仅留索引与哈希（存档时间线的证据链不会因此断裂）。

下载存档内容副本

相关资产