research-wiki

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Wiki: Persistent Research Knowledge Base

Research Wiki：持久化研究知识库

Subcommand: $ARGUMENTS

子命令：$ARGUMENTS

Overview

概述

The research wiki is a persistent, per-project knowledge base that accumulates structured knowledge across the entire ARIS research lifecycle. Unlike one-off literature surveys that are used and forgotten, the wiki compounds — every paper read, idea tested, experiment run, and review received makes the wiki smarter.

Inspired by Karpathy's LLM Wiki pattern: compile knowledge once, keep it current, don't re-derive on every query.

Research Wiki是一个针对单个项目的持久化知识库，可在整个ARIS研究生命周期中积累结构化知识。与用过即弃的一次性文献调研不同，该Wiki具备复利效应——每读一篇论文、测试一个想法、完成一次实验、收到一次评审意见，都会让Wiki变得更完善。

灵感源自Karpathy的LLM Wiki模式：一次性整理知识，持续更新，无需在每次查询时重新推导。

Core Concepts

核心概念

Four Entity Types

四种实体类型

Entity	Directory	Node ID format	What it represents
Paper	`papers/`	`paper:<slug>`	A published or preprint research paper
Idea	`ideas/`	`idea:<id>`	A research idea (proposed, tested, or failed)
Experiment	`experiments/`	`exp:<id>`	A concrete experiment run with results
Claim	`claims/`	`claim:<id>`	A testable scientific claim with evidence status

实体类型	目录	节点ID格式	代表内容
Paper	`papers/`	`paper:<slug>`	已发表或预印本研究论文
Idea	`ideas/`	`idea:<id>`	研究想法（已提出、已测试或已失败）
Experiment	`experiments/`	`exp:<id>`	已完成的具体实验及结果
Claim	`claims/`	`claim:<id>`	可验证的科学主张及证据状态

Typed Relationships (

graph/edges.jsonl

)

类型化关系（

graph/edges.jsonl

）

Edge type	From → To	Meaning
`extends`	paper → paper	Builds on prior work
`contradicts`	paper → paper	Disagrees with results/claims
`addresses_gap`	paper\|idea → gap	Targets a known field gap
`inspired_by`	idea → paper	Idea sourced from this paper
`tested_by`	idea\|claim → exp	Tested in this experiment
`supports`	exp → claim\|idea	Experiment confirms claim
`invalidates`	exp → claim\|idea	Experiment disproves claim
`supersedes`	paper → paper	Newer work replaces older

Edges are stored in

graph/edges.jsonl

only. The

## Connections

section on each page is auto-generated from the graph — never hand-edit it.

关系类型	起点 → 终点	含义
`extends`	paper → paper	基于前人研究成果
`contradicts`	paper → paper	与已有结果/主张相悖
`addresses_gap`	paper\|idea → gap	针对已知领域空白
`inspired_by`	idea → paper	想法来源于该论文
`tested_by`	idea\|claim → exp	在该实验中被验证
`supports`	exp → claim\|idea	实验证实该主张/想法
`invalidates`	exp → claim\|idea	实验推翻该主张/想法
`supersedes`	paper → paper	新研究替代旧研究

关系仅存储在

graph/edges.jsonl

中。每个页面的

## Connections

部分由图谱自动生成，请勿手动编辑。

Wiki Directory Structure

Wiki目录结构

research-wiki/
  index.md               # categorical index (auto-generated)
  log.md                 # append-only timeline
  gap_map.md             # field gaps with stable IDs (G1, G2, ...)
  query_pack.md          # compressed summary for /idea-creator (auto-generated, max 8000 chars)
  papers/
    <slug>.md            # one page per paper
  ideas/
    <idea_id>.md         # one page per idea
  experiments/
    <exp_id>.md          # one page per experiment
  claims/
    <claim_id>.md        # one page per testable claim
  graph/
    edges.jsonl          # materialized current relationship graph

research-wiki/
  index.md               # 分类索引（自动生成）
  log.md                 # 仅追加式时间线
  gap_map.md             # 带稳定ID的领域空白（G1、G2……）
  query_pack.md          # 供/idea-creator使用的压缩摘要（自动生成，最大8000字符）
  papers/
    <slug>.md            # 单篇论文对应一个页面
  ideas/
    <idea_id>.md         # 单个想法对应一个页面
  experiments/
    <exp_id>.md          # 单个实验对应一个页面
  claims/
    <claim_id>.md        # 单个可验证主张对应一个页面
  graph/
    edges.jsonl          # 实例化的当前关系图谱

Subcommands

子命令

/research-wiki init

/research-wiki init

Initialize the wiki for the current project:

Create
```
research-wiki/
```
directory structure
Create empty
```
index.md
```
,
```
log.md
```
,
```
gap_map.md
```
Create empty
```
graph/edges.jsonl
```
Log: "Wiki initialized"

为当前项目初始化Wiki：

创建
```
research-wiki/
```
目录结构
创建空白的
```
index.md
```
、
```
log.md
```
、
```
gap_map.md
```
创建空白的
```
graph/edges.jsonl
```
日志记录："Wiki已初始化"

/research-wiki ingest "<paper title>" — arxiv: <id>

/research-wiki ingest "<paper title>" --arxiv: <id>

Add a paper to the wiki. This subcommand is thin wrapping around the canonical helper

python3 tools/research_wiki.py ingest_paper …

, which is the single implementation of paper ingest in ARIS (per

shared-references/integration-contract.md

— one helper, no copies). The helper does all of:

Fetch metadata — queries the arXiv Atom API when
```
--arxiv-id
```
is given

Generate slug —

<first_author_last_name><year>_<keyword>

Check dedup — skip an existing page unless
```
--update-on-exist
```
Create page —
```
papers/<slug>.md
```
with the schema below
Rebuild
index.md
and
```
query_pack.md
```
Append
log.md

Edge extraction (step 5/8 in the old manual flow) is not in

ingest_paper

; do it as a follow-up with

add_edge

per relationship identified:

bash

undefined

将论文添加到Wiki。该子命令是对标准辅助工具

python3 tools/research_wiki.py ingest_paper …

的轻量封装，该工具是ARIS中论文导入的唯一实现（遵循

shared-references/integration-contract.md

——单一辅助工具，无重复实现）。该工具会完成以下所有操作：

获取元数据——当指定
```
--arxiv-id
```
时，调用arXiv Atom API查询

生成slug——格式为

<first_author_last_name><year>_<keyword>

查重——若页面已存在则跳过，除非指定
```
--update-on-exist
```
创建页面——生成
```
papers/<slug>.md
```
，遵循下方的页面 schema
**重建
```
index.md
```
**和
```
query_pack.md
```
追加到
log.md

关系提取（旧手动流程的第5/8步）不包含在

ingest_paper

中；需在识别到关系后，使用

add_edge

作为后续步骤完成：

bash

undefined

arXiv-known paper

arXiv收录的论文

python3 tools/research_wiki.py ingest_paper research-wiki/
--arxiv-id 2501.12345 --thesis "One-line claim from abstract."

python3 tools/research_wiki.py ingest_paper research-wiki/
--arxiv-id 2501.12345 --thesis "摘要中的核心主张一句话总结。"

Venue paper with no arXiv mirror

无arXiv镜像的会议期刊论文

python3 tools/research_wiki.py ingest_paper research-wiki/
--title "Attention Is All You Need"
--authors "Ashish Vaswani, Noam Shazeer, …" --year 2017 --venue "NeurIPS"

Manual edge after ingest

导入后手动添加关系

python3 tools/research_wiki.py add_edge research-wiki/
--from "paper:vaswani2017_attention_all_you"
--to "paper:chen2025_factorized_gap"
--type "extends" --evidence "Section 3.2: adapts the encoder block …"


Other skills (`/research-lit`, `/arxiv`, `/alphaxiv`, `/deepxiv`,
`/semantic-scholar`, `/exa-search`) call the same helper directly in
their own last step — they don't re-route through `/research-wiki
ingest` as a subcommand, so they don't need an LLM roundtrip.


其他技能（`/research-lit`、`/arxiv`、`/alphaxiv`、`/deepxiv`、`/semantic-scholar`、`/exa-search`）会在自身流程的最后一步直接调用该辅助工具——无需通过`/research-wiki ingest`子命令中转，因此无需LLM往返调用。

/research-wiki sync — arxiv-ids <id1>,<id2>,...

/research-wiki sync --arxiv-ids <id1>,<id2>,...

Batch backfill: ingest one or more arXiv IDs that were read earlier without being ingested (e.g., because

research-wiki/

was set up after the reading happened, or a hook didn't fire).

bash

undefined

批量补全：导入之前已阅读但未导入的arXiv ID（例如，

research-wiki/

是在阅读完成后才创建的，或钩子未触发）。

bash

undefined

Explicit list

显式指定ID列表

python3 tools/research_wiki.py sync research-wiki/
--arxiv-ids 2310.06770,1706.03762

From a file (one id per line, # comments ok)

从文件读取（每行一个ID，支持#注释）

python3 tools/research_wiki.py sync research-wiki/ --from-file ids.txt


Dedup is handled per-id; already-ingested papers are skipped silently.
This is the recommended **manual repair** step (see integration
contract §5 Backfill). `sync` does not scan session traces — callers
declare the ids explicitly.

**Paper page schema** (exactly what `ingest_paper` emits — do not
handwrite alternative fields; `lint` will flag drift):

```markdown
---
type: paper
node_id: paper:<slug>
title: "<full title>"
authors: ["First A. Author", "Second B. Author"]
year: 2025
venue: "arXiv"
external_ids:
  arxiv: "2501.12345"
  doi: null
  s2: null
tags: ["tag1", "tag2"]
added: 2026-04-07T10:12:00Z
---

python3 tools/research_wiki.py sync research-wiki/ --from-file ids.txt


会按ID处理查重；已导入的论文将被静默跳过。这是推荐的**手动修复**步骤（见集成协议第5节补全）。`sync`不会扫描会话轨迹——调用者需显式声明ID。

**论文页面schema**（与`ingest_paper`生成的完全一致——请勿手写其他字段；`lint`会标记偏差）：

```markdown
---
type: paper
node_id: paper:<slug>
title: "<完整标题>"
authors: ["First A. Author", "Second B. Author"]
year: 2025
venue: "arXiv"
external_ids:
  arxiv: "2501.12345"
  doi: null
  s2: null
tags: ["tag1", "tag2"]
added: 2026-04-07T10:12:00Z
---

<full title>

<完整标题>

One-line thesis

核心主张一句话总结

[Single sentence capturing the paper's core contribution]

[提炼论文核心贡献的单句内容]

Problem / Gap

问题/领域空白

Method

方法

Key Results

关键结果

Assumptions

假设前提

Limitations / Failure Modes

局限性/失效模式

Reusable Ingredients

可复用要素

[Techniques, datasets, or insights that could be repurposed]

[可被复用的技术、数据集或见解]

Open Questions

开放问题

Claims

研究主张

[Reference claim pages: claim:C1, claim:C2, etc.]

[引用主张页面：claim:C1、claim:C2等]

Connections

关联关系

[AUTO-GENERATED from graph/edges.jsonl — do not edit manually]

[由graph/edges.jsonl自动生成——请勿手动编辑]

Relevance to This Project

与本项目的相关性

[Why this paper matters for our specific research direction]


_Additionally, when the paper was ingested via `--arxiv-id` and the arXiv
API returned an abstract, the helper appends an `## Abstract (original)`
section after `Relevance to This Project` containing the raw abstract
text as a blockquote. Manual ingests (no `--arxiv-id`) do not include
this section._

[该论文为何对我们的特定研究方向重要]


_此外，当通过`--arxiv-id`导入论文且arXiv API返回摘要时，辅助工具会在`与本项目的相关性`之后追加`## 原始摘要`部分，以块引用形式包含原始摘要文本。手动导入（未指定`--arxiv-id`）不会包含此部分。_

/research-wiki query "<topic>"

/research-wiki query "<topic>"

Generate

query_pack.md

— a compressed, context-window-friendly summary:

Fixed budget (max 8000 chars / ~2000 tokens):

Section	Budget	Content
Project direction	300 chars	From CLAUDE.md or RESEARCH_BRIEF.md
Top 5 gaps	1200 chars	From gap_map.md, ranked by: unresolved + linked ideas + failed experiments
Paper clusters	1600 chars	3-5 clusters by tag overlap, 2-3 sentences each
Failed ideas	1400 chars	Always included — highest anti-repetition value
Top papers	1800 chars	8-12 pages ranked by: linked gaps, linked ideas, centrality, relevance flag
Active chains	900 chars	limitation → opportunity relationship chains
Open unknowns	500 chars	Unresolved questions across the wiki

Pruning priority (when over budget): low-ranked papers > cluster detail > chain detail. Never prune failed ideas or top gaps first.

Key rule: Read from short fields only (frontmatter, one-line thesis, gap summary, failure note). Do not summarize full page bodies every time.

生成

query_pack.md

——一个压缩的、适配上下文窗口的摘要：

固定容量（最大8000字符/约2000 tokens）：

章节	容量	内容
项目方向	300字符	来自CLAUDE.md或RESEARCH_BRIEF.md
顶级5个领域空白	1200字符	来自gap_map.md，按未解决程度+关联想法+失败实验排序
论文聚类	1600字符	按标签重叠度分为3-5个聚类，每个聚类2-3句话
失败想法	1400字符	必含——具有最高的防重复价值
顶级论文	1800字符	8-12篇论文，按关联空白、关联想法、中心度、相关性标记排序
活跃关系链	900字符	局限性→机遇的关系链
未知问题	500字符	Wiki中未解决的问题

裁剪优先级（超出容量时）：低排名论文 > 聚类细节 > 关系链细节。请勿优先裁剪失败想法或顶级领域空白。

**核心规则：**仅读取短字段（前置元数据、核心主张一句话总结、空白摘要、失败说明）。无需每次都总结完整页面内容。

/research-wiki update <node_id> — <field>: <value>

/research-wiki update <node_id> -- <field>: <value>

Update a specific entity:

/research-wiki update paper:chen2025 — relevance: core
/research-wiki update idea:001 — outcome: negative
/research-wiki update claim:C1 — status: invalidated

After any update: rebuild

query_pack.md

, update

log.md

更新特定实体：

/research-wiki update paper:chen2025 -- relevance: core
/research-wiki update idea:001 -- outcome: negative
/research-wiki update claim:C1 -- status: invalidated

任何更新完成后：重建

query_pack.md

，更新

log.md

。

/research-wiki lint

/research-wiki lint

Health check the wiki:

Orphan pages — entities with zero edges
Stale claims — claims with
```
status: reported
```
older than 14 days
Contradictions — claims with both
```
supports
```
and
```
invalidates
```
edges
Missing connections — papers sharing 2+ tags but no explicit relationship
Dead ideas —
```
stage: proposed
```
ideas that were never tested
Sparse pages — pages with 3+ empty sections

Output a

LINT_REPORT.md

with suggested fixes.

对Wiki进行健康检查：

孤立页面——无任何关系的实体
过期主张——
```
status: reported
```
状态超过14天的主张
矛盾关系——同时存在
```
supports
```
和
```
invalidates
```
关系的主张
缺失关联——共享2个以上标签但无明确关系的论文
停滞想法——
```
stage: proposed
```
状态但从未被测试的想法
内容稀疏页面——存在3个以上空白章节的页面

输出包含修复建议的

LINT_REPORT.md

。

/research-wiki stats

/research-wiki stats

Quick overview:

📚 Research Wiki Stats
Papers: 28 (12 core, 10 related, 6 peripheral)
Ideas: 7 (2 active, 3 failed, 1 partial, 1 succeeded)
Experiments: 12
Claims: 15 (5 supported, 3 invalidated, 7 reported)
Edges: 64
Gaps: 8 (3 unresolved)
Last updated: 2026-04-07T10:12:00Z

快速概览：

📚 Research Wiki统计数据
论文：28篇（12篇核心、10篇相关、6篇外围）
想法：7个（2个活跃、3个失败、1个部分完成、1个成功）
实验：12次
主张：15个（5个已证实、3个已推翻、7个已报告）
关系：64条
领域空白：8个（3个未解决）
最后更新时间：2026-04-07T10:12:00Z

Integration with Existing Workflows

与现有工作流的集成

All paper-reading skills follow the same integration contract (see

shared-references/integration-contract.md

single predicate —
```
[ -d research-wiki/ ]
```

single canonical helper —

python3 tools/research_wiki.py ingest_paper …

concrete artifact —
```
papers/<slug>.md
```
+
```
log.md
```
entry
backfill —
```
sync --arxiv-ids …
```
diagnostic —
```
tools/verify_wiki_coverage.sh
```

所有论文阅读技能遵循相同的集成协议（见

shared-references/integration-contract.md

）：

单一判断条件——
```
[ -d research-wiki/ ]
```

单一标准辅助工具——

python3 tools/research_wiki.py ingest_paper …

具体产物——
```
papers/<slug>.md
```
+
```
log.md
```
条目
补全——
```
sync --arxiv-ids …
```
诊断——
```
tools/verify_wiki_coverage.sh
```

Hook 1: After

/research-lit

finds papers

钩子1：

/research-lit

找到论文后

undefined

undefined

At end of research-lit, after synthesis:

在research-lit流程末尾，完成合成后：

if research-wiki/ exists: for paper in top_relevant_papers (limit 8-12): python3 tools/research_wiki.py ingest_paper research-wiki/
--arxiv-id <id> [--thesis "..."] [--tags "..."] for each explicit relation to existing wiki paper: python3 tools/research_wiki.py add_edge research-wiki/
--from "paper:<slug>" --to "<target>"
--type <extends|contradicts|addresses_gap|...>
--evidence "..." log "research-lit ingested N papers"


Each paper-reading skill ships its own Step "Update Research Wiki (if
active)" that calls the same helper once per paper it touched. The
business logic is not duplicated — only the loop over that skill's
specific result set differs.

if research-wiki/ 存在: for paper in top_relevant_papers（限制8-12篇）: python3 tools/research_wiki.py ingest_paper research-wiki/
--arxiv-id <id> [--thesis "..."] [--tags "..."] for each explicit relation to existing wiki paper: python3 tools/research_wiki.py add_edge research-wiki/
--from "paper:<slug>" --to "<target>"
--type <extends|contradicts|addresses_gap|...>
--evidence "..." log "research-lit已导入N篇论文"


每个论文阅读技能都自带“更新Research Wiki（若启用）”步骤，会针对其处理的每篇论文调用一次该辅助工具。业务逻辑不会重复——仅遍历该技能特定结果集的循环有所不同。

Hook 2:

/idea-creator

reads AND writes wiki

钩子2：

/idea-creator

读取并写入Wiki

Before ideation:

if research-wiki/query_pack.md exists (and < 7 days old):
    prepend query_pack to landscape context
    treat failed ideas as banlist
    treat top gaps as search seeds
    still run fresh literature search for last 3-6 months

After ideation (THIS IS CRITICAL — without it, ideas/ stays empty):

for idea in all_generated_ideas (recommended + killed):
    /research-wiki upsert_idea(idea)
    for paper_id in idea.based_on:
        add_edge(idea.node_id, paper_id, "inspired_by")
    for gap_id in idea.target_gaps:
        add_edge(idea.node_id, gap_id, "addresses_gap")
rebuild query_pack
log "idea-creator wrote N ideas to wiki"

构思前：

if research-wiki/query_pack.md 存在（且创建时间<7天）:
    将query_pack前置到领域背景中
    将失败想法视为禁用列表
    将顶级领域空白视为搜索种子
    仍需针对过去3-6个月的文献进行全新搜索

构思后（这一步至关重要——否则ideas/目录将为空）：

for idea in all_generated_ideas（推荐+已否决）:
    /research-wiki upsert_idea(idea)
    for paper_id in idea.based_on:
        add_edge(idea.node_id, paper_id, "inspired_by")
    for gap_id in idea.target_gaps:
        add_edge(idea.node_id, gap_id, "addresses_gap")
重建query_pack
log "idea-creator已向Wiki写入N个想法"

Hook 3: After

/result-to-claim

verdict

钩子3：

/result-to-claim

得出结论后

undefined

undefined

Create experiment page

创建实验页面

exp_id = upsert_experiment(experiment_data)

Update each claim's status

更新每个主张的状态

for claim_id in resolved_claims: if verdict == "yes": set_claim_status(claim_id, "supported") add_edge(exp_id, claim_id, "supports") elif verdict == "partial": set_claim_status(claim_id, "partial") add_edge(exp_id, claim_id, "supports") # partial else: set_claim_status(claim_id, "invalidated") add_edge(exp_id, claim_id, "invalidates")

for claim_id in resolved_claims: if verdict == "yes": set_claim_status(claim_id, "supported") add_edge(exp_id, claim_id, "supports") elif verdict == "partial": set_claim_status(claim_id, "partial") add_edge(exp_id, claim_id, "supports") # 部分证实 else: set_claim_status(claim_id, "invalidated") add_edge(exp_id, claim_id, "invalidates")

Update idea outcome

更新想法结果

update_idea(active_idea_id, outcome=verdict)

If failed, record WHY for future ideation

若失败，记录原因供未来构思参考

if verdict in ("no", "partial"): update_idea failure_notes with specific metrics and reasons

rebuild query_pack log "result-to-claim: exp_id updated, verdict=..."

undefined

if verdict in ("no", "partial"): update_idea failure_notes with specific metrics and reasons

重建query_pack log "result-to-claim: exp_id已更新，verdict=..."

undefined

Re-ideation Trigger

重新构思触发条件

After significant wiki updates, suggest re-running

/idea-creator

≥5 new papers ingested since last ideation
≥3 new failed/partial ideas since last ideation
New contradiction discovered in the graph
New gap identified that no existing idea addresses

The system suggests but does not auto-trigger. User decides.

当Wiki发生重大更新后，建议重新运行

/idea-creator

：

自上次构思以来导入了≥5篇新论文
自上次构思以来新增了≥3个失败/部分完成的想法
在图谱中发现新的矛盾关系
发现了现有想法未覆盖的新领域空白

系统仅给出建议，不会自动触发。由用户决定是否执行。

Key Rules

核心规则

One source of truth for relationships:
```
graph/edges.jsonl
```
. Page
```
Connections
```
sections are auto-generated views.
Canonical node IDs everywhere:
```
paper:<slug>
```
,
```
idea:<id>
```
,
```
exp:<id>
```
,
```
claim:<id>
```
,
```
gap:<id>
```
. Never use raw titles or inconsistent shorthands.
Failed ideas are the most valuable memory. Never prune them from query_pack.
query_pack.md is hard-budgeted at 8000 chars. Deterministic generation, not open-ended summarization.
Append to log.md for every mutation. The log is the audit trail.
Reviewer independence applies. When the wiki is read by cross-model review skills, pass file paths only — do not summarize wiki content for the reviewer.

关系的唯一数据源：
```
graph/edges.jsonl
```
。页面的
```
Connections
```
部分是自动生成的视图。
统一使用标准节点ID：
```
paper:<slug>
```
、
```
idea:<id>
```
、
```
exp:<id>
```
、
```
claim:<id>
```
、
```
gap:<id>
```
。请勿使用原始标题或不一致的简写。
失败想法是最有价值的记忆。请勿从query_pack中移除它们。
query_pack.md有严格容量限制：8000字符。采用确定性生成，而非开放式总结。
每次修改都要追加到log.md。日志是审计追踪记录。
保持评审独立性。当跨模型评审技能读取Wiki时，仅传递文件路径——请勿为评审者总结Wiki内容。

Acknowledgements

致谢

Inspired by Karpathy's LLM Wiki — "compile knowledge once, keep it current, don't re-derive on every query."

灵感来源于Karpathy的LLM Wiki——“一次性整理知识，持续更新，无需在每次查询时重新推导。”

research-wiki

Original

Translation

Research Wiki: Persistent Research Knowledge Base

Research Wiki：持久化研究知识库

Overview

概述

Core Concepts

核心概念

Four Entity Types

四种实体类型

Typed Relationships (graph/edges.jsonl)

类型化关系（graph/edges.jsonl）

Wiki Directory Structure

Wiki目录结构

Subcommands

子命令

/research-wiki init

/research-wiki init

/research-wiki ingest "<paper title>" — arxiv: <id>

/research-wiki ingest "<paper title>" --arxiv: <id>

arXiv-known paper

arXiv收录的论文

Venue paper with no arXiv mirror

无arXiv镜像的会议期刊论文

Manual edge after ingest

导入后手动添加关系

/research-wiki sync — arxiv-ids <id1>,<id2>,...

/research-wiki sync --arxiv-ids <id1>,<id2>,...

Explicit list

显式指定ID列表

From a file (one id per line, # comments ok)

从文件读取（每行一个ID，支持#注释）

<full title>

<完整标题>

One-line thesis

核心主张一句话总结

Problem / Gap

问题/领域空白

Method

方法

Key Results

关键结果

Assumptions

假设前提

Limitations / Failure Modes

局限性/失效模式

Reusable Ingredients

可复用要素

Open Questions

开放问题

Claims

研究主张

Connections

关联关系

Relevance to This Project

与本项目的相关性

/research-wiki query "<topic>"

/research-wiki query "<topic>"

/research-wiki update <node_id> — <field>: <value>

/research-wiki update <node_id> -- <field>: <value>

/research-wiki lint

/research-wiki lint

/research-wiki stats

/research-wiki stats

Integration with Existing Workflows

与现有工作流的集成

Hook 1: After /research-lit finds papers

钩子1：/research-lit找到论文后

At end of research-lit, after synthesis:

在research-lit流程末尾，完成合成后：

Hook 2: /idea-creator reads AND writes wiki

钩子2：/idea-creator读取并写入Wiki

Hook 3: After /result-to-claim verdict

钩子3：/result-to-claim得出结论后

Create experiment page

创建实验页面

Update each claim's status

更新每个主张的状态

Update idea outcome

Typed Relationships (
`graph/edges.jsonl`
)

类型化关系（
`graph/edges.jsonl`
）

`/research-wiki init`

`/research-wiki init`

`/research-wiki ingest "<paper title>" — arxiv: <id>`

`/research-wiki ingest "<paper title>" --arxiv: <id>`

`/research-wiki sync — arxiv-ids <id1>,<id2>,...`

`/research-wiki sync --arxiv-ids <id1>,<id2>,...`

`/research-wiki query "<topic>"`

`/research-wiki query "<topic>"`

`/research-wiki update <node_id> — <field>: <value>`

`/research-wiki update <node_id> -- <field>: <value>`

`/research-wiki lint`

`/research-wiki lint`

`/research-wiki stats`

`/research-wiki stats`

Hook 1: After
`/research-lit`
finds papers

钩子1：
`/research-lit`
找到论文后

Hook 2:
`/idea-creator`
reads AND writes wiki

钩子2：
`/idea-creator`
读取并写入Wiki

Hook 3: After
`/result-to-claim`
verdict

钩子3：
`/result-to-claim`
得出结论后