select-venue

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Select Venue

选择投稿场地

Turn "where should I submit this paper?" into a ranked shortlist of venue-track pairs with scores, deadlines, page budgets, and an explicit verification status — grounded in the repo's

venues/

profiles, not vibes.

将“我该把这篇论文投到哪里？”转化为带评分、截止日期、页数预算和明确验证状态的场地-赛道配对排名短名单——基于仓库的

venues/

配置文件，而非主观判断。

When to use

使用场景

The user asks where to submit a paper, for target-venue recommendations, or to compare candidate venues/tracks.
The user asks "does my paper fit venue X?" or "research track or industry track?"
The user mentions CORE rank, h5-index, CCF class, acceptance rates, or upcoming CS conference deadlines in a submission-planning context.

Not for: parsing one specific CFP into a profile (

parse-cfp

), adapting a draft to an already-chosen venue (

tailor-to-venue

), or pre-submission compliance checks (

preflight-check

用户询问论文投稿去向、目标场地推荐，或比较候选场地/赛道。
用户询问“我的论文适合场地X吗？”或“投研究赛道还是工业赛道？”
用户在投稿规划场景中提及CORE排名、h5-index、CCF等级、录用率或即将到来的计算机科学会议截止日期。

不适用于：将单个特定CFP解析为配置文件（

parse-cfp

）、根据已选场地调整草稿（

tailor-to-venue

）或投稿前合规检查（

preflight-check

）。

Inputs

输入信息

Topic — one or two sentences on what the paper is about.
Contribution type — classify using
```
references/track-fit.md
```
; ask the user if ambiguous.
Constraints — earliest realistic submission date, prestige goals (and whether CCF class matters), page-budget reality of the current draft, blind-level conflicts (e.g. an already-public preprint), travel/registration constraints.

Venue data —

venues/conferences/*.yml

profiles (schema in

venues/schema.yml

), surfaced by

scripts/list_venues.py

主题：1-2句话说明论文内容。
贡献类型：参考
```
references/track-fit.md
```
进行分类；若存在歧义，询问用户。
约束条件：最早可行投稿日期、声望目标（以及CCF等级是否重要）、当前草稿的实际页数预算、盲审级别冲突（例如已公开的预印本）、差旅/注册限制。

场地数据：

venues/conferences/*.yml

配置文件（schema位于

venues/schema.yml

），通过

scripts/list_venues.py

调用。

Process

流程

Elicit the inputs. Confirm topic, contribution type, and constraints in one round of questions. The contribution type changes the shortlist more than the topic — pin it down first (
```
references/track-fit.md
```
, "Contribution taxonomy").
Survey profiled venues. Run:
```
python3 scripts/list_venues.py
```
This lists every profile with deadline proximity, blind level, submission system, and per-track page budgets, sorted by next upcoming submission deadline. Useful flags:
```
--upcoming-only
```
,
```
--family <name>
```
,
```
--track <name>
```
,
```
--json
```
(full data incl. track notes),
```
--today YYYY-MM-DD
```
(reproducible runs). Never compute date arithmetic by hand. Caveat: some venues (e.g. SIGSPATIAL) have per-track deadlines that differ from the top-level ones — they live in each track's
```
notes
```
field; read them in the
```
--json
```
output.
Build the candidate set. Combine (a) profiled venues that plausibly match the topic, and (b) venues you know fit the topic but have no profile yet. For unprofiled candidates, resolve identity via DBLP:
```
CONTACT_EMAIL=you@example.org python3 scripts/dblp_venue_lookup.py search "<venue name>"
```
Optionally gauge venue size with
```
dblp_venue_lookup.py toc-count <dblp_key> <year>
```
. Mark every unprofiled candidate clearly and suggest
```
parse-cfp
```
to profile it. Aim for 5-10 candidate venue-track pairs before scoring.
Gather prestige signals. For each candidate, look up CORE rank, h5-index, CCF class (if the user cares), and acceptance rate following
```
references/ranking-sources.md
```
. Hard rule: every number carries a source + edition/year, or is labeled "unverified — indicative" / "unknown". Never state a rank or acceptance rate from memory as fact, and never invent one.
Score and rank. Apply the 0-10 rubric in
```
references/track-fit.md
```
(topic fit 0-3, track fit 0-3, prestige fit 0-2, deadline feasibility 0-2), then apply its tie-breakers and red-flag vetoes (embargoes, dual-submission bans, attendance mandates).
Re-verify the top picks against live CFPs — mandatory. For the top 3 venues, fetch each profile's
```
cfp_url
```
and confirm the facts the user will act on: deadlines (and their timezone — AoE vs PT matters), page limits and what they exclude, blind level, submission system. Profiles are a starting point, never ground truth; a stale page limit causes a desk reject. Record what was verified and when in the output. If a CFP cannot be reached, mark that venue "NOT re-verified" — do not silently present profile data as confirmed.
Deliver the shortlist (format below) and offer next steps:
```
parse-cfp
```
for unprofiled picks,
```
tailor-to-venue
```
once a target is chosen,
```
plan-submission
```
for the timeline.

获取输入信息：通过一轮提问确认主题、贡献类型和约束条件。贡献类型对短名单的影响大于主题——首先明确这一点（参考
```
references/track-fit.md
```
中的“贡献分类体系”）。
检索已配置场地：运行：
```
python3 scripts/list_venues.py
```
该命令会列出所有配置文件，包含截止日期临近度、盲审级别、投稿系统和各赛道的页数预算，并按下一个即将到来的投稿截止日期排序。实用参数：
```
--upcoming-only
```
（仅显示即将到来的）、
```
--family <name>
```
（指定场地系列）、
```
--track <name>
```
（指定赛道）、
```
--json
```
（包含赛道说明的完整数据）、
```
--today YYYY-MM-DD
```
（可复现运行）。切勿手动计算日期。注意：部分场地（如SIGSPATIAL）的各赛道截止日期与顶层截止日期不同——这些信息位于各赛道的
```
notes
```
字段中；请查看
```
--json
```
输出内容。
构建候选集：结合(a)与主题合理匹配的已配置场地，以及(b)你知道适合主题但尚未配置的场地。对于未配置的候选场地，通过DBLP确认身份：
```
CONTACT_EMAIL=you@example.org python3 scripts/dblp_venue_lookup.py search "<venue name>"
```
可选择使用
```
dblp_venue_lookup.py toc-count <dblp_key> <year>
```
评估场地规模。清晰标记所有未配置的候选场地，并建议使用
```
parse-cfp
```
进行配置。评分前目标候选场地-赛道配对数量为5-10个。
收集声望指标：针对每个候选场地，参考
```
references/ranking-sources.md
```
查找CORE排名、h5-index、CCF等级（若用户在意）和录用率。硬性规则：每个数据都需附带来源+版本/年份，或标记为“未验证——仅供参考”/“未知”。切勿凭记忆陈述排名或录用率作为事实，也切勿编造数据。
评分与排名：应用
```
references/track-fit.md
```
中的0-10评分标准（主题匹配度0-3分、赛道匹配度0-3分、声望匹配度0-2分、截止日期可行性0-2分），然后应用其中的平局规则和红牌否决项（禁运、禁止双重投稿、强制参会要求）。
对照实时CFP重新验证首选场地——强制步骤：针对排名前三的场地，获取每个配置文件的
```
cfp_url
```
并确认用户将依据的关键信息：截止日期（及其时区——AoE与PT差异很大）、页数限制及例外情况、盲审级别、投稿系统。配置文件仅为起点，绝非事实依据；过时的页数限制会导致直接拒稿。在输出中记录验证内容和时间。若无法访问CFP，标记该场地“未重新验证”——切勿将配置文件数据默认为已确认信息。
交付短名单（格式如下）并提供后续步骤：为未配置的候选场地使用
```
parse-cfp
```
，选定目标场地后使用
```
tailor-to-venue
```
，使用
```
plan-submission
```
规划时间线。

Output

输出格式

A ranked shortlist in chat (offer to save as

venue-shortlist.md

#	Venue / track	Score	Deadline (tz)	Pages	Blind	Rank signals	Verified
1	SIGSPATIAL 2026 / Research	9/10	abstract 2026-05-29, paper 2026-06-05 (PT)	10p excl refs +2p appendix	single	CORE2023 A (verify)	live CFP 2026-06-11

Below the table, per venue: 2-4 lines of rationale (the four rubric scores with one-line justifications), the red flags checked, and — for any venue whose deadline has passed — the next expected cycle. Close with the explicit disclaimer that the user must confirm all critical facts on the venue's own CFP page before planning around them.

聊天界面中的排名短名单（可提供保存为

venue-shortlist.md

的选项）：

#	场地/赛道	评分	截止日期（时区）	页数	盲审级别	声望指标	验证状态
1	SIGSPATIAL 2026 / Research	9/10	摘要 2026-05-29，论文 2026-06-05（PT）	10页（不含参考文献）+2页附录	单盲	CORE2023 A（待验证）	实时CFP 2026-06-11

表格下方，针对每个场地：2-4行理由（四个评分项各配一句简短说明）、已检查的红牌项，以及——若场地截止日期已过——下一个预期周期。结尾需明确声明：用户在规划前必须在场地自身的CFP页面确认所有关键信息。

Bundled resources

配套资源

```
references/ranking-sources.md
```
— CORE, h5-index, acceptance rates, CCF, deadline aggregators: where each lives, how to interpret, how to cite.
```
references/track-fit.md
```
— contribution taxonomy, track archetypes, the scoring rubric, tie-breakers, red flags.
```
scripts/list_venues.py
```
— stdlib-only profile lister + deadline math.
```
scripts/dblp_venue_lookup.py
```
— polite DBLP venue resolver (rate-limited ≤1 req/s, cached under
```
.cache/
```
, needs
```
CONTACT_EMAIL
```
).

```
references/ranking-sources.md
```
——CORE、h5-index、录用率、CCF、截止日期聚合器：各数据来源、解读方式、引用方式。
```
references/track-fit.md
```
——贡献分类体系、赛道原型、评分标准、平局规则、红牌项。
```
scripts/list_venues.py
```
——仅依赖标准库的配置文件列表工具+日期计算。
```
scripts/dblp_venue_lookup.py
```
——合规的DBLP场地解析工具（速率限制≤1请求/秒，缓存于
```
.cache/
```
，需设置
```
CONTACT_EMAIL
```
）。

Guardrails

约束规则

Profiles and this skill's tables are never ground truth — re-verify deadlines, page limits, and policies against the live
```
cfp_url
```
(step 6) and say so in the output.
Never fabricate ranks, h5-indexes, acceptance rates, or citations; route any bibliographic citation through
```
verify-citations
```
.
Never submit to, register with, or create accounts on any submission system on the user's behalf.
Fetch venue/CFP pages on demand and process them transiently; do not copy paper abstracts or full text into the repo (metadata is fine).
Prestige caps at 2 of 10 points by design — do not let "it's A*" override fit, and do not present prestige as publication advice ("aim lower/higher") unless the user asked for that judgment.

配置文件和本工具生成的表格绝非事实依据——必须对照实时
```
cfp_url
```
重新验证截止日期、页数限制和政策（步骤6），并在输出中说明这一点。
切勿编造排名、h5-index、录用率或引用信息；所有文献引用均需通过
```
verify-citations
```
处理。
切勿代表用户向任何投稿系统投稿、注册或创建账户。
按需获取场地/CFP页面并临时处理；请勿将论文摘要或全文复制到仓库中（元数据除外）。
声望得分在总分10分中最高占2分——切勿让“这是A*级场地”凌驾于匹配度之上，除非用户明确要求此类判断，否则切勿将声望作为投稿建议（“投低/高等级场地”）。