結果RST-2026-0205v0.1

登記的預測不成立：同時用三種以上 AI 工具的人並沒有洩漏更多

P1 看起來像是「偵測到三種以上 AI 工具的倉庫更常公開本機檔與高警示內容」。這在打開 P2 之前就寫下；P2 方向相反。

研究狀態: STABLE 目前的研究結論相對穩定
證據等級: E2 受控實驗
結果: NEGATIVE
資料基礎: BLIND PUBLIC DATA 真實的公開檔案，由演算法在封閉程序中量測；沒有任何人或 AI 模型讀過，只有編碼特徵離開程序。數字可能失真。
版本: 0.1
更新: 2026-10-13
建立: 2026-10-13
領域: Privacy
計畫: PRG-2026-0201 AI Agent 公開邊界與安全閉包（APBSC）
作者: Neo.K (EveMissLab)
AI 協作: Splice (Claude Code, Anthropic) — Phase II protocols, runners, audits, reports and the integrated edition

觀察到的結果

metrics

by_marker_family_count

1

2

3+

interpretation: Single-round patterns are noise until they survive a round they did not come from.

limitations: Exploratory, non-probability frame; not a prevalence estimate.
No human checked any finding; secret-like means a shape and was never tested.
Current public state only, observed once.

來源	關係	目標	狀態	ID
`EXP-2026-0203` P1–P2 輪——帶 AI 協作標記的個人倉庫（400 個，2026-10-13）	`produces`	`RST-2026-0205` 登記的預測不成立：同時用三種以上 AI 工具的人並沒有洩漏更多	`ACTIVE`	`REL-2026-0617`

Canonical URL

機器可讀

快照

AI-SNAPSHOT-v0.1-58e716495670

來源歷程

source: EveMissLab research collection: AI Agent Publication Boundary and Security Closure (真本體論14)
extracted_by: Splice (Claude Code), reading the open-source release's own manifests, locks and pooled outputs, and the hashes of the internal drafts
extracted_at: 2026-10-13
generator: tools/extract_all.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports