Back to Details

rw-research-novelty

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

RW Research Novelty

RW Research Novelty

把证据空白、冲突和异常转成可追溯的候选创新点，并按贡献、可行性和证伪条件筛选。
Convert evidence gaps, conflicts, and anomalies into traceable candidate innovation points, and screen them based on contribution, feasibility, and falsifiability criteria.

启动

Initiation

  1. 读取 
    references/standalone.md
    、
    references/method.md
    和 
    references/standards.md
    。
  2. 读取用户本轮提供的材料；没有材料时，只完成当前证据允许的部分。
  3. 需要规则判断时检索 
    references/atoms.jsonl
    ；遇到相似任务时读取 
    references/cases.md
    。
  4. 需要选择方法或工具时读取 
    references/domain-guide.md
    ，并使用 
    assets/worksheet.md
    组织交付。
  5. 读取 
    references/acceptance.md
    。
    references/behavior-tests.json
    只用于测试，不作为用户任务事实。
  6. 当前文献、API、报告规范和期刊要求可能变化时，打开 
    references/source-map.md
    中的官方链接核验并记录日期。
  1. Read 
    references/standalone.md
    , 
    references/method.md
    and 
    references/standards.md
    .
  2. Read the materials provided by the user in this round; if no materials are provided, only complete the part allowed by current evidence.
  3. Retrieve 
    references/atoms.jsonl
    when rule judgment is needed; read 
    references/cases.md
    when encountering similar tasks.
  4. Read 
    references/domain-guide.md
    when selecting methods or tools, and use 
    assets/worksheet.md
    to organize delivery.
  5. Read 
    references/acceptance.md
    . 
    references/behavior-tests.json
    is only for testing and not used as task facts for users.
  6. When current literature, API, report specifications, and journal requirements may change, verify and record the date by opening the official links in 
    references/source-map.md
    .

工作阶段

Work Phases

  1. 确认研究领域、目标决策、证据范围和研究者能够使用的数据与资源。
  2. 把证据图中的空白、冲突、异常和共同限制整理成带来源的问题卡。
  3. 围绕每张问题卡，从解释、构念、人群、情境、测量、时间、设计、数据和实施维度生成候选方向。
  4. 为每个候选方向写出替代解释、反例、所需证据和会削弱该方向的结果。
  5. 检索并核验相似研究，区分未发现、尚未核验、已有相似工作和仍有贡献空间。
  6. 分别评估贡献、新颖性置信度、可行性、可证伪性、伦理与资源限制，输出候选清单和排除理由。
  1. Confirm the research field, target decisions, evidence scope, and data and resources available to researchers.
  2. Organize gaps, conflicts, anomalies, and common constraints in the evidence graph into source-attributed problem cards.
  3. For each problem card, generate candidate directions from the dimensions of explanation, construct, population, context, measurement, time, design, data, and implementation.
  4. Write alternative explanations, counterexamples, required evidence, and results that would weaken the direction for each candidate direction.
  5. Retrieve and verify similar studies, distinguishing between undiscovered, unverified, existing similar work, and remaining contribution space.
  6. Evaluate contribution, novelty confidence, feasibility, falsifiability, ethical and resource constraints respectively, and output a candidate list and exclusion reasons.

运行规则

Operational Rules

  • 文献 gap 是输入，不是创新点结论。
  • 没有检索到研究不能直接解释为没有研究。
  • 候选方向必须能回到具体证据节点、冲突或限制。
  • 发散要受证据和研究问题约束，不能只做自由联想。
  • 每个候选方向至少列出两个替代解释和一个反例。
  • 把理论贡献、方法贡献、数据贡献、情境扩展、复现和实施价值分开记录。
  • 只更换国家、人群或变量名称不自动构成创新。
  • 使用既有概念或方法也可能有价值，但要说明新的用途和影响。
  • 新颖性、重要性、严谨性和可行性分别判断，不能用一个总分遮盖短板。
  • 可执行不等于有贡献，有贡献也不等于当前资源可执行。
  • 创新状态在当前检索和领域核验完成前只能标为候选。
  • 保留被排除方向、理由和触发重新评估的条件。
  • 涉及临床、伦理、统计或领域判断时保留人工确认。
  • Literature gaps are inputs, not conclusions of innovation points.
  • The absence of retrieved studies cannot be directly interpreted as the absence of such studies.
  • Candidate directions must be traceable back to specific evidence nodes, conflicts, or constraints.
  • Divergence must be constrained by evidence and research questions; free association alone is not allowed.
  • Each candidate direction must list at least two alternative explanations and one counterexample.
  • Record theoretical contributions, methodological contributions, data contributions, contextual extensions, replication, and implementation value separately.
  • Simply changing country, population, or variable names does not automatically constitute innovation.
  • Using existing concepts or methods may also have value, but the new uses and impacts must be explained.
  • Novelty, importance, rigor, and feasibility are judged separately; a single total score cannot cover up shortcomings.
  • Executability does not equate to contribution, and contribution does not equate to executability with current resources.
  • Innovation status can only be marked as candidate until current retrieval and domain verification are completed.
  • Retain excluded directions, reasons, and conditions that trigger re-evaluation.
  • Reserve manual confirmation when involving clinical, ethical, statistical, or domain judgments.

输出

Output

  • 证据问题卡和 evidence-to-novelty 矩阵。
  • 带来源、替代解释和证伪条件的候选创新点卡。
  • 候选排序、排除理由、未知事项和下一步核验。
  • Evidence problem cards and evidence-to-novelty matrix.
  • Candidate innovation point cards with sources, alternative explanations, and falsifiability criteria.
  • Candidate ranking, exclusion reasons, unknown items, and next-step verification.

停止条件

Stop Conditions

  • 没有结构化证据时，只能输出探索方向，不能声称已发现创新点。
  • 无法核验当前相似研究时，把新颖性标为待核验。
  • 缺少可取得数据、伦理许可或基本资源时，不把方向写成可立即执行。
  • 不生成不存在的论文、数据、DOI、检索结果或领域共识。
  • When there is no structured evidence, only output exploratory directions, and do not claim to have discovered innovation points.
  • When current similar studies cannot be verified, mark novelty as pending verification.
  • When accessible data, ethical approval, or basic resources are lacking, do not present the direction as immediately executable.
  • Do not generate non-existent papers, data, DOI, search results, or domain consensus.

独立运行

Independent Operation

  • 默认不读取私人工作区、个人语料目录或预设 research-lab。
  • 用户提供的文件、文本、链接和数据是当前任务输入，不是安装依赖。
  • 网络不可用时，使用 Skill 内的稳定方法继续；需要当前事实的部分标记为待核验。
  • 本包内其他科研 Skill 存在时可以接续；单独安装时直接返回下一步说明，不停止当前任务。
  • By default, do not read private workspaces, personal corpus directories, or preset research-lab.
  • Files, text, links, and data provided by users are inputs for the current task, not installation dependencies.
  • When the network is unavailable, continue using stable methods within the Skill; mark parts requiring current facts as pending verification.
  • Can connect with other research Skills in this package if present; when installed alone, directly return instructions for the next step without stopping the current task.

来源纪律

Source Discipline

  • 把用户材料、公开来源、当前推断和未知事项分开。
  • 报告规范只检查报告透明度，不自动证明设计质量。
  • 公开来源摘要保存在 Skill 内；需要版本、费用、政策、API 或期刊现状时回到官方页面。
  • 不生成不存在的论文、数据、DOI、工具运行结果或期刊要求。
  • Separate user materials, public sources, current inferences, and unknown items.
  • Report specifications only check report transparency, and do not automatically prove design quality.
  • Public source abstracts are stored within the Skill; when version, cost, policy, API, or journal status is needed, return to the official page.
  • Do not generate non-existent papers, data, DOI, tool operation results, or journal requirements.