wuyang/llm-atlas
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: publish representation and depth chapter

Browse Source
This commit is contained in:
wuyang
2026-07-29 10:32:33 +08:00
parent a9afa12c7c
commit a2c9298d35
28 changed files with 2960 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/check-evaluation-browser.mjs
+3 -3
View File
@@ -263,7 +263,7 @@ if (overview.sections !== 33 || overview.tocLinks !== 33) failures.push("章节
if (overview.paperLinks !== 80) failures.push("正式论文链不是 80 个节点");
if (overview.ledgers !== 22) failures.push("二十二张评测账结构异常");
if (overview.labTabs !== 4 || overview.labPanels !== 4) failures.push("四联实验结构异常");
if (overview.navLinks !== 19 || home.navLinks !== 19 || mobile.mobileLinks !== 19 || overview.activeNav !== "评测安全") failures.push("全站导航未同步评测专题");
if (overview.navLinks !== 20 || home.navLinks !== 20 || mobile.mobileLinks !== 20 || overview.activeNav !== "评测安全") failures.push("全站导航未同步评测专题");
if (overview.documentOverflow > 1 || mobile.documentOverflow > 1) failures.push("桌面或移动端存在文档级横向溢出");
if (metric.initial.visible !== "metric" || numeric(metric.initial.one) !== 80 || numeric(metric.initial.atLeast) !== 80 || numeric(metric.initial.all) !== 80) failures.push("指标实验初始值异常");
if (numeric(metric.search.atLeast) <= 99 || numeric(metric.search.all) >= 30 || !metric.search.explain.includes("搜索")) failures.push("pass@k / pass^k 方向没有分开");
@@ -277,8 +277,8 @@ if (numeric(system.initial.success) <= numeric(system.initial.model) || numeric(
if (numeric(system.cheap.success) >= numeric(system.initial.success) || numeric(system.cheap.cost) !== 4) failures.push("低预算没有降低成功率 / 成本");
if (numeric(system.locked.unsafe) !== 0 || numeric(system.locked.overrefusal) <= numeric(system.initial.overrefusal)) failures.push("安全壳没有展现危险服从 / 过拒权衡");
if (system.keyboardSelected !== "judge" || system.keyboardVisible !== "judge") failures.push("实验键盘 tab 导航异常");
if (home.releaseCards !== 14 || !home.firstRelease.includes("榜单不是体检单") || home.firstHref !== "/evaluation/") failures.push("首页评测首发入口异常");
if (home.paperCount !== "450" || home.topicCount !== "17" || papers.total !== 450 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常");
if (home.releaseCards !== 15 || !home.firstRelease.includes("hidden state") || home.firstHref !== "/architecture/representation/") failures.push("首页评测首发入口异常");
if (home.paperCount !== "480" || home.topicCount !== "17" || papers.total !== 480 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常");
if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常");
if (mobile.offenders.length) failures.push(`移动端越界元素：${JSON.stringify(mobile.offenders)}`);
if (exceptions.length) failures.push(`浏览器异常：${exceptions.join(" | ")}`);