smart-sourcing
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSmart Sourcing
智能溯源
Intelligent sourcing that requires citations only when the cost is justified by the value of verification.
智能溯源仅在验证价值能覆盖成本时才要求提供引用。
Philosophy
核心理念
Full sourcing is prohibitively expensive (10-16x token increase). Smart sourcing targets high-value claims where verification materially improves accuracy.
完全溯源成本极高（Token使用量增加10-16倍）。智能溯源针对那些验证能显著提升准确性的高价值声明。
When to Source
溯源场景判定
REQUIRE Sources
需要溯源的场景
| Claim Type | Example | Why Source |
|---|---|---|
| Version numbers | "Python 3.12 added..." | Versions change, easy to verify |
| Performance claims | "30% faster than..." | Quantitative claims need evidence |
| Security recommendations | "Use bcrypt for..." | Security advice must be current |
| API specifications | "The function accepts..." | APIs change between versions |
| Release dates | "Released in Q4 2025" | Factual, verifiable |
| Pricing/limits | "Free tier allows 1000 requests" | Business terms change |
| Deprecated features | "X was removed in version Y" | Breaking changes need verification |
| 声明类型 | 示例 | 为何需要溯源 |
|---|---|---|
| 版本号 | "Python 3.12 added..." | 版本会更新，易于验证 |
| 性能声明 | "30% faster than..." | 量化声明需要证据支持 |
| 安全建议 | "Use bcrypt for..." | 安全建议必须保持时效性 |
| API规范 | "The function accepts..." | API会随版本迭代变更 |
| 发布日期 | "Released in Q4 2025" | 事实性内容，可验证 |
| 定价/限制 | "Free tier allows 1000 requests" | 商业条款可能变更 |
| 废弃特性 | "X was removed in version Y" | 破坏性变更需要验证 |
DO NOT Require Sources
无需溯源的场景
| Claim Type | Example | Why No Source |
|---|---|---|
| General concepts | "Async improves concurrency" | Foundational knowledge |
| Code examples | Demonstrative snippets | Illustrative, not factual claims |
| Opinion/preference | "Consider using..." | Clearly framed as suggestion |
| Common knowledge | "Git tracks changes" | Universal understanding |
| Logical derivations | "Therefore, X implies Y" | Reasoning, not factual claim |
| Syntax | "Use | Language documentation is stable |
| 声明类型 | 示例 | 为何无需溯源 |
|---|---|---|
| 通用概念 | "Async improves concurrency" | 基础性知识 |
| 代码示例 | 演示代码片段 | 仅作说明用途，非事实声明 |
| 观点/偏好 | "Consider using..." | 明确为建议性质 |
| 常识内容 | "Git tracks changes" | 普遍认知内容 |
| 逻辑推导 | "Therefore, X implies Y" | 推理过程，非事实声明 |
| 语法规则 | "Use | 语言文档相对稳定 |
Decision Framework
决策框架
Is this a factual claim?
├── No → No source needed
└── Yes → Would being wrong cause harm?
├── No (minor inconvenience) → No source needed
└── Yes → Is verification cost-effective?
├── No (>5k tokens for low-value claim) → State uncertainty
└── Yes → Perform web search, cite sourceIs this a factual claim?
├── No → No source needed
└── Yes → Would being wrong cause harm?
├── No (minor inconvenience) → No source needed
└── Yes → Is verification cost-effective?
├── No (>5k tokens for low-value claim) → State uncertainty
└── Yes → Perform web search, cite sourceImplementation
实现方式
Inline Citations
内联引用
When sourcing is warranted:
markdown
Python 3.12 introduced `type` statement for type aliases[1].
Sources:
1. [PEP 695](https://peps.python.org/pep-0695/)当需要溯源时：
markdown
Python 3.12 introduced `type` statement for type aliases[1].
Sources:
1. [PEP 695](https://peps.python.org/pep-0695/)Uncertainty Markers
不确定性标记
When sourcing isn't cost-effective but uncertainty exists:
markdown
Python 3.12 introduced the `type` statement (verify in release notes for your version).当溯源成本过高但存在不确定性时：
markdown
Python 3.12 introduced the `type` statement (verify in release notes for your version).Confidence Levels
置信度等级
| Confidence | Action |
|---|---|
| High (stable facts) | State directly |
| Medium (may have changed) | Add verification note |
| Low (uncertain) | Source or acknowledge uncertainty |
| 置信度 | 操作 |
|---|---|
| 高（稳定事实） | 直接陈述 |
| 中（可能已变更） | 添加验证提示 |
| 低（不确定） | 溯源或说明不确定性 |
Token Cost Analysis
Token成本分析
| Approach | Token Cost | Use Case |
|---|---|---|
| No sourcing | Baseline | General knowledge |
| Uncertainty marker | +5-10 tokens | Medium confidence |
| Single source | +2-5k tokens | High-value claim |
| Multiple sources | +10-20k tokens | Research tasks |
| 方案 | Token成本 | 使用场景 |
|---|---|---|
| 不溯源 | 基准值 | 通用知识 |
| 不确定性标记 | +5-10 tokens | 中等置信度场景 |
| 单一引用 | +2-5k tokens | 高价值声明 |
| 多引用 | +10-20k tokens | 研究任务 |
Examples
示例
Good: Source Version-Specific Claim
良好实践：版本相关声明溯源
markdown
User: What's new in FastAPI 0.109?
Response: FastAPI 0.109 added Pydantic v2 support as default[1] and
improved OpenAPI schema generation[2].
Sources:
1. [FastAPI Release Notes](https://fastapi.tiangolo.com/release-notes/)
2. [GitHub Release 0.109.0](https://github.com/tiangolo/fastapi/releases/tag/0.109.0)markdown
User: What's new in FastAPI 0.109?
Response: FastAPI 0.109 added Pydantic v2 support as default[1] and
improved OpenAPI schema generation[2].
Sources:
1. [FastAPI Release Notes](https://fastapi.tiangolo.com/release-notes/)
2. [GitHub Release 0.109.0](https://github.com/tiangolo/fastapi/releases/tag/0.109.0)Good: No Source for General Concept
良好实践：通用概念无需溯源
markdown
User: How does async/await work?
Response: Async/await enables non-blocking I/O by allowing coroutines
to yield control while waiting for operations. The event loop manages
execution, resuming coroutines when their awaited operations complete.markdown
User: How does async/await work?
Response: Async/await enables non-blocking I/O by allowing coroutines
to yield control while waiting for operations. The event loop manages
execution, resuming coroutines when their awaited operations complete.Good: Uncertainty Marker
良好实践：添加不确定性标记
markdown
The connection pool default is typically 10 connections (verify in your
database driver documentation as this varies by library and version).markdown
The connection pool default is typically 10 connections (verify in your
database driver documentation as this varies by library and version).Integration
集成兼容
Works with:
- - Keeps sourced responses concise
conserve:response-compression - - Weighs source cost vs value
conserve:token-conservation - - Full sourcing for knowledge corpus
memory-palace:research
可与以下组件配合使用：
- - 保持溯源后的回复简洁
conserve:response-compression - - 权衡溯源成本与价值
conserve:token-conservation - - 用于知识语料库的完全溯源
memory-palace:research
When To Use Full Sourcing
何时使用完全溯源
When NOT To Use
何时不使用
- Internal project code that doesn't need citations
- Casual conversation without factual claims
Escalate to full sourcing (accept high token cost) for:
- Knowledge corpus entries (permanent documentation)
- Security advisories (safety-critical)
- Compliance/legal claims (audit requirements)
- Research tasks (user expects thorough investigation)
For these cases, use workflow which is designed for comprehensive sourcing.
memory-palace:research- 无需引用的内部项目代码
- 无事实声明的随意对话
当以下情况时，升级为完全溯源（接受高Token成本）：
- 知识语料库条目（永久文档）
- 安全公告（安全关键场景）
- 合规/法律声明（审计要求）
- 研究任务（用户期望深入调查）
对于这些场景，请使用专为全面溯源设计的工作流。
memory-palace:research