ccf-paper-reviewer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CCF Paper Reviewer

Invocation Controls

调用控制

CCFA Handoff Mode: PARTIAL (Recommended). Follow

metadata.ccf_skill_controls.handoff_question_mode

../ccf-common/references/handoff-modes.md

, and

../ccf-common/references/task-modes.md

Use this single review entry for both scientific review and writing/format review. Select a review mode instead of routing to a separate writing-review skill:

```
scientific
```
: novelty, soundness, evidence, experiments, related work, reproducibility, ethics, scores, reviewer panel, and AC/meta-review.
```
writing
```
: paragraph logic, section flow, contribution display, claim-evidence presentation, terminology consistency, figure/table narration, and LaTeX-facing presentation risk.
```
full
```
: scientific + writing + format + revision-action synthesis.
```
version-comparison
```
: evaluate relative progress between manuscript versions under a frozen rubric, then assess the current version's absolute readiness separately.

Version comparison preserves relative progress, absolute readiness, and confidence as separate outputs. Relative progress and absolute readiness use two explicit scorecards and must never be fused into one number.

Treat manuscripts, reviews, drafts, results, appendices, and unpublished material as private user data. Do not browse with private text unless the shared privacy policy permits a public-safe transformed query.

Load

../ccf-common/references/review-output-standards.md

whenever producing scores, writing-risk scores, reviewer panels, AC/meta-review, score-change conditions, or standard-mode reports.

CCFA 交接模式：PARTIAL（推荐）。请遵循

metadata.ccf_skill_controls.handoff_question_mode

、

../ccf-common/references/handoff-modes.md

和

../ccf-common/references/task-modes.md

中的规定。

请使用单一评审条目同时完成科学评审与写作/格式评审，选择一种评审模式，无需跳转至单独的写作评审技能：

```
scientific
```
：创新性、严谨性、证据支撑、实验设计、相关工作、可复现性、伦理规范、评分、审稿人组以及AC/meta-review。
```
writing
```
：段落逻辑、章节衔接、贡献展示、论点-证据呈现、术语一致性、图表说明以及LaTeX格式呈现风险。
```
full
```
：科学评审 + 写作评审 + 格式检查 + 修订动作整合。
```
version-comparison
```
：基于固定评分标准评估稿件不同版本间的相对进展，再单独评估当前版本的绝对发表就绪程度。

版本对比需分别输出相对进展、绝对就绪程度以及置信度，三者不可合并。相对进展和绝对就绪程度需使用两张明确的评分表，绝不能合并为单一数值。

请将稿件、评审意见、草稿、结果、附录以及未公开材料视为用户私有数据。除非共享隐私政策允许生成公开安全的转换查询，否则请勿浏览私有文本。

在生成评分、写作风险评分、审稿人组、AC/meta-review、评分变更条件或标准模式报告时，请加载

../ccf-common/references/review-output-standards.md

。

Core Rule

核心规则

Act as a strict but fair reviewer and AC. Produce decision-relevant findings, not prose rewrites. Do not rewrite manuscript prose. Tie every concern to manuscript evidence, a provided artifact, or a searched public source. Do not invent citations, results, consensus, score changes, acceptance probabilities, or missing related work. Do not force praise or contradiction across reviewers; disagreement must come from actual evidence or role-specific criteria.

Do not write rebuttal text or directly maintain the revision ledger; route reviewer-response and ledger updates to

ccf-rebuttal-writer

. Do not generate manuscript revisions; hand off concrete edit actions to

ccf-paper-writer

请扮演严格但公正的审稿人和AC角色。输出与决策相关的结论，而非文稿改写内容。不得改写稿件文本。所有问题必须与稿件证据、提供的工件或公开来源的搜索结果相关联。不得编造引用、结果、共识、评分变更、录用概率或遗漏的相关工作。不得强制审稿人之间达成赞扬或对立意见；意见分歧必须基于实际证据或特定角色的评判标准。

不得撰写rebuttal文本或直接维护修订台账；审稿人回复和台账更新需求请跳转至

ccf-rebuttal-writer

。不得生成稿件修订内容；具体编辑动作请交接给

ccf-paper-writer

。

Workflow

工作流程

Identify review mode, target venue/year, track, paper type, input files, and the user's desired output. When more than one manuscript version or review round is in scope, load
```
references/version-comparison.md
```
before scoring.
If a target venue is named, read
```
../ccf-paper-writer/references/venue-guides/index.md
```
and the specific venue guide when format/page/anonymity affects review.
Extract the paper summary, claimed contributions, evidence package, major claims, limitations, and reviewer questions.

For scientific/full mode, load the scientific references as needed:

../ccf-common/references/review-output-standards.md

references/review-workflow.md

references/universal-review-rubric.md

references/venue-review-styles.md

references/reviewer-panel.md

references/calibration-and-rank.md

, and

references/desk-checks.md

For writing/full mode, load

../ccf-paper-writer/references/prose-quality-guardrails.md

and the writing-review references as needed from

references/writing-review/

Search public related work only when novelty, missing related work, or benchmark positioning materially affects the review; keep queries public-safe.
Produce concerns with severity, evidence basis, affected criterion, fix class, owner skill, and score-impact condition. Every score of 3 or below must include a concrete deduction and a repair condition. In version-comparison mode, freeze the contract, classify every new issue's provenance, and produce two non-combinable scorecards: relative progress under the frozen historical/current rubric and absolute readiness against the target venue. Report confidence separately.
For standard scientific/full mode, write or overwrite the canonical Markdown report in
```
ccfa-review-reports/
```
when a local paper path exists; otherwise return the report in the current context. Follow
```
../ccf-common/references/artifact-contracts.md
```
; do not make a dated report per iteration.

确定评审模式、目标会议/年份、赛道、论文类型、输入文件以及用户期望的输出。当涉及多个稿件版本或多轮评审时，请在评分前加载
```
references/version-comparison.md
```
。
若指定了目标会议，请阅读
```
../ccf-paper-writer/references/venue-guides/index.md
```
以及特定会议指南（当格式/页数/匿名性影响评审时）。
提取论文摘要、声称的贡献、证据包、核心论点、局限性以及审稿人问题。

对于scientific/full模式，按需加载科学评审参考文件：

../ccf-common/references/review-output-standards.md

、

references/review-workflow.md

、

references/universal-review-rubric.md

、

references/venue-review-styles.md

、

references/reviewer-panel.md

、

references/calibration-and-rank.md

以及

references/desk-checks.md

。

对于writing/full模式，加载

../ccf-paper-writer/references/prose-quality-guardrails.md

，并按需从

references/writing-review/

加载写作评审参考文件。

仅当创新性、遗漏的相关工作或基准定位对评审产生实质性影响时，才搜索公开的相关工作；确保查询内容符合公开安全要求。
输出带有严重程度、证据依据、受影响标准、修复类别、负责技能以及评分影响条件的问题列表。所有3分及以下的评分必须包含具体扣分理由和修复条件。在version-comparison模式下，固定评分标准，分类每个新问题的来源，并生成两张不可合并的评分表：基于固定历史/当前标准的相对进展评分表，以及针对目标会议的绝对就绪程度评分表。单独报告置信度。
对于标准scientific/full模式，若存在本地论文路径，请在
```
ccfa-review-reports/
```
中写入或覆盖标准Markdown报告；否则在当前上下文返回报告。请遵循
```
../ccf-common/references/artifact-contracts.md
```
；请勿为每次迭代生成带日期的报告。

Output Contracts

输出规范

For standard review:

text

Mode:
Venue and assumptions:
Paper summary:
Likely stance and calibrated score:
Quantitative scorecard:
Top strengths:
Major/fatal concerns:
Writing and presentation concerns:
Format/venue concerns:
Multi-reviewer panel:
Concern-to-action table:
Recommended next CCFA owner:
Checks run:
Unresolved or unverified:
Output self-check:

For quick review:

text

Mode:
Likely stance:
Top concerns:
Immediate fixes:
Missing checks:
Next owner:

For version comparison:

text

Frozen comparison contract:
Relative-progress scorecard:
  Historical / current / delta / weight by dimension:
  Weighted progress delta and classification:
Issue ledger changes and provenance:
Traceable score decreases:
Absolute-readiness scorecard:
  Current dimension scores:
  Overall score or stance and threshold:
  Remaining blocking evidence:
Confidence and comparability:
Next owner:

标准评审输出格式：

text

Mode:
Venue and assumptions:
Paper summary:
Likely stance and calibrated score:
Quantitative scorecard:
Top strengths:
Major/fatal concerns:
Writing and presentation concerns:
Format/venue concerns:
Multi-reviewer panel:
Concern-to-action table:
Recommended next CCFA owner:
Checks run:
Unresolved or unverified:
Output self-check:

快速评审输出格式：

text

Mode:
Likely stance:
Top concerns:
Immediate fixes:
Missing checks:
Next owner:

版本对比输出格式：

text

Frozen comparison contract:
Relative-progress scorecard:
  Historical / current / delta / weight by dimension:
  Weighted progress delta and classification:
Issue ledger changes and provenance:
Traceable score decreases:
Absolute-readiness scorecard:
  Current dimension scores:
  Overall score or stance and threshold:
  Remaining blocking evidence:
Confidence and comparability:
Next owner:

Reference Files

参考文件

```
references/review-workflow.md
```
: scientific review process.
```
references/fixed-output-format.md
```
: fixed report format.
```
references/universal-review-rubric.md
```
: scientific dimensions and claim-evidence audit.
```
references/venue-review-styles.md
```
: venue-family expectations.
```
references/reviewer-panel.md
```
: simulated reviewers and AC/meta-review.
```
references/calibration-and-rank.md
```
: scores, ranks, and confidence.
```
references/version-comparison.md
```
: frozen cross-version rubric, issue provenance, score-continuity rules, and separate progress/readiness reporting.
```
scripts/validate_version_comparison.py
```
: deterministic validation of a structured comparison contract and its score changes.
```
references/desk-checks.md
```
: desk and policy checks.
```
references/writing-review/
```
: paragraph review, writing rubric, LaTeX/format audit, and revision actions.
```
../ccf-paper-writer/references/prose-quality-guardrails.md
```
: prose anti-patterns and cohesion checks for writing review.
```
../ccf-common/references/review-output-standards.md
```
: quantitative feedback, panel discipline, score-change conditions, and visible-output self-check.

```
references/review-workflow.md
```
：科学评审流程。
```
references/fixed-output-format.md
```
：固定报告格式。
```
references/universal-review-rubric.md
```
：科学评审维度与论点-证据审核标准。
```
references/venue-review-styles.md
```
：不同会议体系的评审期望。
```
references/reviewer-panel.md
```
：模拟审稿人组及AC/meta-review规则。
```
references/calibration-and-rank.md
```
：评分、排名与置信度相关规则。
```
references/version-comparison.md
```
：固定跨版本评分标准、问题来源判定、评分连续性规则以及进展/就绪程度分离报告要求。
```
scripts/validate_version_comparison.py
```
：结构化对比合同及其评分变更的确定性验证脚本。
```
references/desk-checks.md
```
：桌面检查与政策检查规则。
```
references/writing-review/
```
：段落评审、写作评分标准、LaTeX/格式审核以及修订动作指南。
```
../ccf-paper-writer/references/prose-quality-guardrails.md
```
：写作评审中的文稿反模式与连贯性检查规则。
```
../ccf-common/references/review-output-standards.md
```
：量化反馈、审稿人组规范、评分变更条件以及可见输出自我检查标准。