eduevidence 5.2.0 → 6.0.0

package/README.md

@@ -1,18 +1,22 @@
+<p align="center">
+  <img src="assets/readme/logo.png" width="88" height="88" alt="EduEvidence logo" />
+</p>
+
 # EduEvidence
 
 > **🌐 English | [中文](README.zh-CN.md)**
 
-## EduEvidence Research Engine — Evidence-Based Education Decision Skill
+## EduEvidence Research Engine — Evidence Research & Decision Skill
 
-> **From Education Questions to Evidence-Based Decisions.**
+> **From Research Questions to Evidence-Based Decisions.**
 
 EduEvidence is delivered as an **AI Agent Skill**; inside the Skill operates
 the **EduEvidence Research Engine** — a persistent, auditable engine that
-turns education questions into evidence-grounded decisions.
+turns research questions into evidence-grounded decisions across education and organizational policy.
 
-- **Two Research Modes** — **Evidence Review** (secondary-evidence research)
-  and **Full Research Cycle** (Evidence Review → Knowledge Gap → study design
-  → your data → analysis → updated decision).
+- **Three public workflows** — **Evidence Review**, **Decision & Pilot**, and
+  **Evaluate & Update**. A full research cycle connects existing evidence,
+  grounded knowledge gaps, a study design, new data and a revised decision.
 - **Project Workspace + Evidence Graph** — long-lived Projects with versioned,
   immutable graph revisions; `result.json`/HTML/Markdown are projections, not
   fact stores.
@@ -21,14 +25,16 @@ turns education questions into evidence-grounded decisions.
 - **Frozen scientific rule** — *No new study design without evidence
   grounding*: designs must reference explicit, evidence-grounded Knowledge
   Gap IDs.
-- ⚖️ It does not generate answers for teachers — it shows what the evidence supports, what it cannot support, who it applies to, and how to pilot and verify it.
+- ⚖️ Inspect what the evidence supports, what it cannot support, who it applies to, and how to pilot and verify it.
 - 🧪 Built on real research (examples include CHI 2023 / PNAS 2025 / ACL 2025 / Springer 2024 empirical evidence); no claims without sources.
-- 🚦 The output is not a binary "allow/forbid" answer but a four-state decision — **ADOPT / PILOT / REJECT / INSUFFICIENT EVIDENCE** — plus an actionable teaching intervention and evaluation plan.
+- 🚦 The output is not a binary "allow/forbid" answer but a four-state decision — **ADOPT / PILOT / REJECT / INSUFFICIENT EVIDENCE** — plus an actionable intervention and evaluation plan.
 - 🧩 The engine is an internal capability architecture — not a standalone
   server/app; Native Core runs on Python stdlib only and never requires
   Agent MCP or a daemon.
 
-![EduEvidence overview banner](assets/top-banner.jpg)
+![Actual Research Studio overview: workplace AI evidence](assets/readme/studio-overview.png)
+
+*Actual local Studio screenshot. This case is manually curated literature, with no attached research execution history.*
 
 ---
 
@@ -54,7 +60,7 @@ bash install.sh              # one-click: venv + deps + self-check + tests
 Open the example report right away:
 
 ```bash
-open examples/ai-coding-assistant/EduEvidence_Report.html
+open examples/ai-coding-assistant-evidence/EduEvidence_Report.html
 ```
 
 > Requires Python 3.10+; the core has zero third-party dependencies. `pip install matplotlib` is optional for academic-figure PNG/PDF export.
@@ -174,7 +180,7 @@ It answers six questions:
 | 155–170s | Teaching Intervention + Evaluation |
 | 170–180s | Benchmark |
 
-Full example pack: [`examples/ai-coding-assistant/`](examples/ai-coding-assistant/).
+Full example pack: [`examples/ai-coding-assistant-evidence/`](examples/ai-coding-assistant-evidence/).
 
 ## Why Education Evidence Is Hard
 
@@ -244,7 +250,7 @@ The demo's highlight: in Kazemitabaar et al. (CHI 2023), the AI code assistant r
 - Can Claim / Cannot Claim boundaries
 - four-state decision + Confidence (rule-based, not model-generated freely)
 
-![Evidence Tribunal Workflow](assets/tribunal-workflow.jpg)
+![Evidence Tribunal Workflow](assets/readme/research-workflow.svg)
 
 ## From Evidence to Action
 
@@ -276,26 +282,18 @@ Key metrics: Citation Support Precision / Unsupported Claim Rate / Contradiction
 
 > **Should first-year C programming students be allowed to use generative AI coding assistants?**
 
-`examples/ai-coding-assistant/` shows the full path from question to decision:
+`examples/ai-coding-assistant-evidence/` shows the full path from question to decision:
 
-- **Evidence** (7 items, all bound to real sources): task-performance gains (Kazemitabaar 2023), unguarded access harming independent exam performance by −17% (Bastani 2025, PNAS), guardrails eliminating the negative effect (Bastani 2025), formative-feedback writing evidence (Marzuki 2024).
+- **Evidence** (12 findings from 8 sources): task-performance gains (Kazemitabaar 2023), unguarded access harming independent exam performance by −17% (Bastani 2025, PNAS), guardrails eliminating the negative effect (Bastani 2025), formative-feedback writing evidence (Marzuki 2024).
 - **Decision**: **PILOT** — task-performance evidence is strong, but direct learning-effect evidence for university programming courses is missing, and the unguarded-access risk is documented.
 - **Intervention**: 4-phase pilot (Independent Foundation → Explain Don't Solve → Structured Collaboration → Transfer Check).
 - **Evaluation**: no-AI baseline / post-test / final-exam retention / no-AI transfer task + AI-dependency risk metrics.
 
-Two more examples — AI writing assistant (`examples/ai-writing-assistant/`) and a calculus AI tutor (`examples/ai-tutor/`) — show the skill is not hard-coded to one question.
+A second public example, `examples/workplace-ai-assistant/`, evaluates AI assistance in enterprise customer support using the policy domain: 4 findings from 3 studies, with direct and indirect evidence distinguished. Its proposed supervised pilot has not been executed.
 
-**Example provenance (read before citing)**: every example pack carries a `data_origin`
-badge in its report header and in `result.json.meta`:
+Both public examples are **manually curated literature demonstrations** (`manual_curated`). A generated report does not establish that an agent completed the nine-stage research workflow. The coding case contains 12 findings from 8 sources; the workplace case contains 4 findings from 3 sources. See [the workplace evidence notes](docs/demo-workplace-ai.md) for source versions and limitations.
 
-- `examples/ai-coding-assistant-evidence/` — **flagship, real literature**: 8 sources with
-  registry-verified DOIs (Crossref/DataCite audit: `benchmarks/doi-audit/report.md`),
-  engine-computed confidence; data_origin=`manual_curated`.
-- `examples/ai-coding-assistant/`, `ai-tutor/`, `ai-writing-assistant/` — real-source
-  walkthrough packs.
-- `examples/esl-academic-writing-ai/`, `highschool-math-ai-tutor/` — **synthetic
-  demonstrations** (data_origin=`synthetic`). Their numbers and citations are illustrative,
-  not real studies; reports carry a loud SYNTHETIC badge. Do not cite them as evidence.
+Four older teaching demos have moved to `tests/fixtures/legacy-examples/` for compatibility tests. They are excluded from public catalogs and distribution; their unverified or synthetic findings must not be cited as research evidence. The old `ai-coding-assistant` path remains a compatibility alias.
 
 ### Start your own research in ~30 minutes
 
@@ -307,9 +305,19 @@ bash scripts/bake_pack.sh <pack_dir>                     # 5-theme bilingual rep
 python3 scripts/citation_check.py --pack <pack_dir> --write-back   # DOI ✓ badges
 ```
 
+## Studio in use
+
+Select a graph node to trace source → finding → claim. The flow is a visual aid; it does not signal an active research run.
+
+![Actual provenance graph](assets/readme/studio-graph.png)
+
+Read the same evidence through five independent report themes, with bilingual and brief/full views.
+
+![Actual report reading room](assets/readme/studio-reports.png)
+
 ## Visualization: Bilingual HTML Report + Infographics + Academic Figures
 
-After research completes, `result.json` is rendered into three visualization outputs by deterministic Python adapters. The adapters themselves use the standard library; the optional Web Studio chart enhancement has a separate browser dependency.
+After research completes, `result.json` is rendered into three visualization outputs by deterministic Python adapters. The adapters themselves use the standard library; legacy ECharts enhancement is optional and is not required by the new Research Studio.
 
 ```text
 result.json + result.zh.json (Chinese parallel data)
@@ -328,9 +336,13 @@ result.json + result.zh.json (Chinese parallel data)
 - **Static-first**: decision, matrix, tribunal, intervention and sources remain readable without JavaScript; ECharts is an optional enhancement.
 - **Integrity gate**: chart numbers are checked against result.json item by item; publishing is blocked with `REPORT_INVALID` on mismatch.
 
-**Local Web Studio** (`python3 scripts/dashboard_server.py --port 8765`) has exactly three read-only views: Dashboard, Report Browser and Data Visualization. It loads ECharts 5.4.3 from jsDelivr for interactive charts; the submission package does not bundle that runtime, so Web interactivity requires network access. The baked report's static HTML/SVG remains the offline artifact.
+**Research Studio** is a read-only research workspace. Start `python3 scripts/dashboard_server.py --port 8765` and open `/studio/` to inspect projects, evidence, sources, recorded runs, committed revisions and five report identities. Skill Autoevolve has a separate observation view; the console cannot start research, mutate evidence or dispatch agents.
+
+The React + TypeScript frontend ships as static assets: Node is needed only for development, not for running the packaged Skill. Its charts do not depend on a remote ECharts CDN and never compute a pooled effect in the browser. Local research remains local; GitHub Pages exports public example packs only. Report themes are generated from complete bilingual inputs with explicit missing-data states, not fabricated fallback claims.
+
+See [Research Studio workflow and delivery guide](docs/research-studio-guide.zh-CN.md).
 
-> Open the example directly: `examples/ai-coding-assistant/EduEvidence_Report.html`
+> Open the example directly: `examples/ai-coding-assistant-evidence/EduEvidence_Report.html`
 
 ## Architecture
 
@@ -360,14 +372,14 @@ EduEvidence/  (= one Skill package)
 │                            bilingual HTML composer + V2 project surfaces)
 │
 ├─ Quality assurance
-│  ├─ tests/                 pytest test matrix (V1–V4, 752 test functions / 73 files — docs/metrics.json)
+│  ├─ tests/                 pytest test matrix (V1–V4, current counts in docs/metrics.json)
 │  └─ benchmarks/            V1 questions + benchmarks/v2/ (graph/contract metrics)
 │
 └─ Demos & distribution
    ├─ examples/              Research & Decision Packs + full-research-cycle-fixture (synthetic)
    ├─ docs/                  architecture / methodology / benchmark / demo / reproducibility
    ├─ install.sh             one-click install (local / multi-agent Skill) + self-check
-   ├─ pyproject.toml         packaging metadata (wheel ships CLI + engine; stdlib-only core)
+   ├─ pyproject.toml         packaging metadata (wheel ships CLI, engine and installed runtime resources; stdlib-only core)
    └─ README(.en).md         bilingual docs
 ```
 
@@ -419,7 +431,7 @@ Agent MCP is a **performance & reliability enhancement layer, not a prerequisite
 
 > 🔒 Agent MCP principle: **Scan first. Recommend second. Ask the user. Execute only after explicit confirmation.** No spawn without user approval; reject → fall back to Native.
 
-![Controlled Multi-Agent Research](assets/multi-agent-research.jpg)
+![Controlled Multi-Agent Research](assets/readme/controlled-execution.svg)
 
 
 ## Usage
@@ -427,31 +439,31 @@ Agent MCP is a **performance & reliability enhancement layer, not a prerequisite
 ```bash
 # 1. Validate data against the schema contracts
 python3 scripts/validate_schema.py --schema schemas/evidence.schema.json \
-    --data examples/ai-coding-assistant/evidence.jsonl
+    --data examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 2. Compute evidence quality scores and Confidence
-python3 scripts/evidence_score.py examples/ai-coding-assistant/evidence.jsonl
+python3 scripts/evidence_score.py examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 3. Generate the Evidence Matrix (one of the core views)
-python3 scripts/evidence_matrix.py examples/ai-coding-assistant/evidence.jsonl
+python3 scripts/evidence_matrix.py examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 4. Run the Citation Audit (claim-evidence traceability)
 python3 scripts/claim_audit.py --claims claims.jsonl --evidence evidence.jsonl
 
 # 5. Render the Research & Decision Pack (Markdown)
 python3 scripts/render_report.py \
-    --frame examples/ai-coding-assistant/frame.json \
-    --evidence examples/ai-coding-assistant/evidence.jsonl \
-    --methodology examples/ai-coding-assistant/methodology.json \
-    --verdict examples/ai-coding-assistant/verdict.json \
-    --intervention examples/ai-coding-assistant/intervention.json \
-    --evaluation examples/ai-coding-assistant/evaluation.json \
+    --frame examples/ai-coding-assistant-evidence/frame.json \
+    --evidence examples/ai-coding-assistant-evidence/evidence.jsonl \
+    --methodology examples/ai-coding-assistant-evidence/methodology.json \
+    --verdict examples/ai-coding-assistant-evidence/verdict.json \
+    --intervention examples/ai-coding-assistant-evidence/intervention.json \
+    --evaluation examples/ai-coding-assistant-evidence/evaluation.json \
     --out REPORT.md
 
 # 6. Render the single-file bilingual HTML report (main deliverable)
 python3 visualization/eduevidence-report/scripts/build_report.py \
-    --result examples/ai-coding-assistant/result.json \
-    --out examples/ai-coding-assistant/EduEvidence_Report.html
+    --result examples/ai-coding-assistant-evidence/result.json \
+    --out examples/ai-coding-assistant-evidence/EduEvidence_Report.html
 
 # 7. Validate the benchmark question set
 python3 scripts/benchmark.py --questions benchmarks/questions.jsonl

package/README.zh-CN.md

@@ -1,19 +1,26 @@
+<p align="center">
+  <img src="assets/readme/logo.png" width="88" height="88" alt="EduEvidence logo" />
+</p>
+
 # EduEvidence
 
 > **🌐 [English](README.md) | 中文**
 
-## EduEvidence Research Engine — Evidence-Based Education Decision Skill
+## EduEvidence Research Engine — Evidence Research & Decision Skill
 
-> **From Education Questions to Evidence-Based Decisions.**
-> **从教育问题，到有证据支撑的教育决策。**
+> **From Research Questions to Evidence-Based Decisions.**
+> **从研究问题，到有证据支撑的决策。**
 
-EduEvidence 面向教师、教学研究者与教学管理者，把"是否采用某教学法、课程设计、评估方式或 AI 教学工具"从经验判断转化为**可追溯、可质疑、可验证的证据决策流程**——教学法、课程、评估、学习干预与 AI 工具均是应用域，引擎方法学教育通用。
+EduEvidence 面向研究者与实践决策者，将教育、组织政策和 AI 工具采用等问题转化为**可追溯、可质疑、可验证的证据决策流程**。当前公开案例涵盖编程学习和企业客服，分别使用教育与组织政策领域契约。
 
-- ⚖️ 不是替教师生成答案，而是帮助教师知道：证据支持什么、不能支持什么、适用于谁、应该怎样试点并验证。
+- **三条公开工作流**：Evidence Review（证据综述）、Decision & Pilot（决策与试点）、Evaluate & Update（评估与更新）。完整研究周期将文献证据、有依据的知识缺口、研究设计、新数据和决策修订连接起来。
+- ⚖️ 帮助研究者与实践决策者判断：证据支持什么、不能支持什么、适用于谁、应该怎样试点并验证。
 - 🧪 基于真实研究（示例包含 CHI 2023 / PNAS 2025 / ACL 2025 / Springer 2024 的实证证据），不做无来源断言。
-- 🚦 最终输出不是"允许/禁止"的二元结论，而是 **ADOPT / PILOT / REJECT / INSUFFICIENT EVIDENCE** 四态决策 + 可落地的教学干预与评价方案。
+- 🚦 最终输出不是"允许/禁止"的二元结论，而是 **ADOPT / PILOT / REJECT / INSUFFICIENT EVIDENCE** 四态决策 + 可落地的干预与评价方案。
+
+![实际研究概览：企业客服 AI 证据案例](assets/readme/studio-overview.png)
 
-![EduEvidence 顶层宣传图](assets/top-banner.jpg)
+*本地 Studio 实际截图。案例为人工整理文献，未附研究执行历史。*
 
 ---
 
@@ -52,7 +59,7 @@ bash install.sh              # 一键：venv + 依赖 + 自检 + 测试
 安装后直接打开示例报告：
 
 ```bash
-open examples/ai-coding-assistant/EduEvidence_Report.html
+open examples/ai-coding-assistant-evidence/EduEvidence_Report.html
 ```
 
 > 需要 Python 3.10+；核心零第三方依赖。学术图 PNG/PDF 导出可选装 matplotlib。
@@ -169,7 +176,7 @@ EduEvidence 执行：
 | 155–170s | Teaching Intervention + Evaluation |
 | 170–180s | Benchmark |
 
-完整示例包见 [`examples/ai-coding-assistant/`](examples/ai-coding-assistant/)。
+完整示例包见 [`examples/ai-coding-assistant-evidence/`](examples/ai-coding-assistant-evidence/)。
 
 ## Why Education Evidence Is Hard
 
@@ -238,7 +245,7 @@ EduEvidence 强制区分 20 类 Outcome（`references/outcome-taxonomy.md`）：
 - Can Claim / Cannot Claim 边界
 - 四态决策 + Confidence（规则化计算，不由模型自由生成）
 
-![Evidence Tribunal Workflow](assets/tribunal-workflow.jpg)
+![Evidence Tribunal Workflow](assets/readme/research-workflow.svg)
 
 ## From Evidence to Action
 
@@ -270,18 +277,30 @@ B4 EduEvidence + Agent MCP      ← 证明多 Agent 增强价值（B3 vs B4）
 
 > **大学一年级 C 语言课程是否应该允许学生使用生成式 AI 编程助手？**
 
-`examples/ai-coding-assistant/` 完整展示了从问题到决策的全过程：
+`examples/ai-coding-assistant-evidence/` 完整展示了从问题到决策的全过程：
 
-- **证据**（7 条，均绑定真实来源）：任务表现提升（Kazemitabaar 2023）、无护栏访问损害独立考试表现 -17%（Bastani 2025, PNAS）、护栏设计消除负效应（Bastani 2025）、形成性反馈写作证据（Marzuki 2024）。
+- **证据**（12 条发现、8 个来源）：任务表现提升（Kazemitabaar 2023）、无护栏访问损害独立考试表现 -17%（Bastani 2025, PNAS）、护栏设计消除负效应（Bastani 2025）、形成性反馈写作证据（Marzuki 2024）。
 - **决策**：**PILOT** —— 任务表现证据强，但大学编程课程的直接学习效应证据缺失，无护栏风险已被证实。
 - **干预**：4 阶段试点（Independent Foundation → Explain Don't Solve → Structured Collaboration → Transfer Check）。
 - **评价**：无 AI 基线/后测/期末考试保持/无 AI 迁移任务 + AI 依赖风险指标。
 
-另外两个示例：AI 写作助手（`examples/ai-writing-assistant/`）、高数 AI Tutor（`examples/ai-tutor/`）——证明 Skill 不是为一个问题写死。
+另一公开案例 `examples/workplace-ai-assistant/` 使用组织政策领域，讨论企业客服是否引入 AI 助手：3 项研究、4 条发现，区分直接客服证据与间接写作/咨询证据，建议有监督试点。详见 [来源核验与边界](docs/demo-workplace-ai.md)。
+
+两个公开案例均为人工整理文献（`manual_curated`），报告生成不等于九阶段模型研究已运行，也不代表试点已经执行。四个旧教学示例迁入 `tests/fixtures/legacy-examples/`，仅供软件兼容测试，排除于公共目录和分发包；未核验或合成数据不能引用为研究证据。旧 `ai-coding-assistant` 路径保留兼容别名。
+
+## Studio 实际界面
+
+点击图谱节点可以追溯“来源 → 发现 → 主张”。连线流动用于辅助阅读，不表示后台研究正在执行。
+
+![实际溯源图谱](assets/readme/studio-graph.png)
+
+同一份证据可以用五个独立主题阅读，支持中英文及简报/全文切换。
+
+![实际报告阅读室](assets/readme/studio-reports.png)
 
 ## Visualization: Bilingual HTML Report + Infographics + Academic Figures
 
-After research completes, `result.json` is rendered by three deterministic Python adapters. The adapters use the standard library; the optional Web Studio chart enhancement has a separate browser dependency.
+After research completes, `result.json` is rendered by three deterministic Python adapters. The adapters use the standard library; legacy ECharts enhancement is optional and is not required by the new Research Studio.
 
 ```text
 result.json + result.zh.json
@@ -300,9 +319,13 @@ result.json + result.zh.json
 - **Static-first**: decision, matrix, tribunal, intervention and sources remain readable without JavaScript; ECharts is an optional enhancement.
 - **Integrity gate**: chart numbers are checked against result.json item by item; publishing is blocked with `REPORT_INVALID` on mismatch.
 
-**Local Web Studio** (`python3 scripts/dashboard_server.py --port 8765`) has exactly three read-only views: Dashboard, Report Browser and Data Visualization. It loads ECharts 5.4.3 from jsDelivr for interactive charts; the submission package does not bundle that runtime, so Web interactivity requires network access. The baked report's static HTML/SVG remains the offline artifact.
+**Research Studio 研究观察台**保持只读。运行 `python3 scripts/dashboard_server.py --port 8765`，打开 `/studio/`，即可查看研究项目、证据与来源、实际运行记录、已提交版本及五种风格报告。Skill 自进化实验单独展示；控制台不会启动研究、修改证据或派发代理。
+
+控制台采用 React + TypeScript，分发包已包含静态资源，使用者无需安装 Node。新图表不依赖远程 ECharts CDN，也不在浏览器中计算合并效应量。本地研究不会进入 GitHub Pages 公共导出。五主题从完整双语输入生成，缺失内容明确标记，不补造结论。
+
+详见[研究观察台流程与交付指南](docs/research-studio-guide.zh-CN.md)。
 
-> Open the example directly: `examples/ai-coding-assistant/EduEvidence_Report.html`
+> Open the example directly: `examples/ai-coding-assistant-evidence/EduEvidence_Report.html`
 
 ## Architecture
 
@@ -359,38 +382,38 @@ Agent MCP 是**性能与可靠性增强层，不是 EduEvidence 成立的前提*
 
 > 🔒 Agent MCP 原则：**Scan first. Recommend second. Ask the user. Execute only after explicit confirmation.** 未经用户确认不得 spawn；用户拒绝则回退 Native。
 
-![Controlled Multi-Agent Research](assets/multi-agent-research.jpg)
+![Controlled Multi-Agent Research](assets/readme/controlled-execution.svg)
 
 ## Usage
 
 ```bash
 # 1. 验证数据符合 Schema 契约
 python3 scripts/validate_schema.py --schema schemas/evidence.schema.json \
-    --data examples/ai-coding-assistant/evidence.jsonl
+    --data examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 2. 计算证据质量分与 Confidence
-python3 scripts/evidence_score.py examples/ai-coding-assistant/evidence.jsonl
+python3 scripts/evidence_score.py examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 3. 生成 Evidence Matrix（主产品界面之一）
-python3 scripts/evidence_matrix.py examples/ai-coding-assistant/evidence.jsonl
+python3 scripts/evidence_matrix.py examples/ai-coding-assistant-evidence/evidence.jsonl
 
 # 4. 运行 Citation Audit（Claim-证据追溯）
 python3 scripts/claim_audit.py --claims claims.jsonl --evidence evidence.jsonl
 
 # 5. 渲染 Research & Decision Pack（Markdown）
 python3 scripts/render_report.py \
-    --frame examples/ai-coding-assistant/frame.json \
-    --evidence examples/ai-coding-assistant/evidence.jsonl \
-    --methodology examples/ai-coding-assistant/methodology.json \
-    --verdict examples/ai-coding-assistant/verdict.json \
-    --intervention examples/ai-coding-assistant/intervention.json \
-    --evaluation examples/ai-coding-assistant/evaluation.json \
+    --frame examples/ai-coding-assistant-evidence/frame.json \
+    --evidence examples/ai-coding-assistant-evidence/evidence.jsonl \
+    --methodology examples/ai-coding-assistant-evidence/methodology.json \
+    --verdict examples/ai-coding-assistant-evidence/verdict.json \
+    --intervention examples/ai-coding-assistant-evidence/intervention.json \
+    --evaluation examples/ai-coding-assistant-evidence/evaluation.json \
     --out REPORT.md
 
 # 6. 渲染单文件双语 HTML 报告（主产物）
 python3 visualization/eduevidence-report/scripts/build_report.py \
-    --result examples/ai-coding-assistant/result.json \
-    --out examples/ai-coding-assistant/EduEvidence_Report.html
+    --result examples/ai-coding-assistant-evidence/result.json \
+    --out examples/ai-coding-assistant-evidence/EduEvidence_Report.html
 
 # 7. 校验 Benchmark 题目集
 python3 scripts/benchmark.py --questions benchmarks/questions.jsonl