AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
個人 GitHub 帳號下公開儲存庫的擁有者可以登入並驗證所有權,自行管理介紹,無需管理員核准。
登入並產生驗證檔案,在 30 分鐘內將其提交至此儲存庫的預設分支。其他分支或分叉儲存庫中的檔案無效。然後在下方檢查檔案,即可無需管理員核准直接管理專案。請保留檔案以維持管理權限。
如需登入,將前往登入頁面。登入後請回到此處,再次點擊所選的驗證按鈕。
在專案資料夾中執行 /nomorevibe verify,即可驗證所有權並自行管理介紹。
一分鐘完成驗證Next-generation computational stylometry — a Python replacement for R's Stylo
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
bitig is a Python package and command-line tool for authorship attribution,
author-group style comparison and forensic authorship analysis. It covers the core
methods of R's Stylo (Delta, Zeta, PCA/MDS, clustering, bootstrap consensus trees,
classification) and adds a spaCy pipeline, transformer embeddings, a Bayesian layer (PyMC),
authorship verification with likelihood-ratio calibration, and a case workflow with
chain-of-custody hashing and sealed reports.
The name is the Old Turkic word for writing or inscription, the kind cut into the
8th-century Orkhon stelae.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
bitig is a Python package and command-line tool for authorship attribution,
author-group style comparison and forensic authorship analysis. It covers the core
methods of R's Stylo (Delta, Zeta, PCA/MDS, clustering, bootstrap consensus trees,
classification) and adds a spaCy pipeline, transformer embeddings, a Bayesian layer (PyMC),
authorship verification with likelihood-ratio calibration, and a case workflow with
chain-of-custody hashing and sealed reports.
The name is the Old Turkic word for writing or inscription, the kind cut into the
8th-century Orkhon stelae.檢視完整 README ↗