184 lines
9.9 KiB
HTML
184 lines
9.9 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="zh-CN">
|
||
<head>
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1">
|
||
<title>真实评测台账 — Natural Memory v2</title>
|
||
<meta name="description" content="全部 108 条真实评测 episode 的逐条台账:模型逐字回复、判定结果、停止原因、选中记录数与分数,可按来源与判定筛选。">
|
||
<meta name="color-scheme" content="dark">
|
||
<meta name="theme-color" content="#0a0a0a">
|
||
<!-- 动效的初始隐藏态只在 JS 可用时生效;脚本被禁用时内容照常可见 -->
|
||
<script>document.documentElement.classList.add("js");</script>
|
||
<meta property="og:type" content="website">
|
||
<meta property="og:title" content="真实评测台账 — Natural Memory v2">
|
||
<meta property="og:description" content="全部 108 条真实评测 episode 的逐条台账:模型逐字回复、判定结果、停止原因、选中记录数与分数,可按来源与判定筛选。">
|
||
<meta name="twitter:card" content="summary_large_image">
|
||
<link rel="icon" href="assets/favicon.svg" type="image/svg+xml">
|
||
<link rel="apple-touch-icon" href="assets/favicon.svg">
|
||
<link rel="preload" href="assets/fonts/archivo-latin-wdth-normal.woff2" as="font" type="font/woff2" crossorigin>
|
||
<link rel="preload" href="assets/fonts/geist-mono-latin-wght-normal.woff2" as="font" type="font/woff2" crossorigin>
|
||
<!-- 资源带构建指纹:内容一变 URL 就变,浏览器不可能再用到旧 JS/CSS -->
|
||
<link rel="stylesheet" href="assets/css/site.css?v=a9c21ef3a8">
|
||
</head>
|
||
<body data-page="ledger" data-layout="docs">
|
||
<a class="skip" href="#doc">跳到正文</a>
|
||
|
||
<header class="site" id="site">
|
||
<div class="topbar">
|
||
<a class="brand" href="./" aria-label="Natural Memory v2 发布页">
|
||
<svg class="brand__mark" viewBox="0 0 32 32" aria-hidden="true">
|
||
<rect class="dim" x="2" y="2" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="12" y="2" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="22" y="2" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="2" y="12" width="7" height="7" rx="1.5"/>
|
||
<rect class="on" x="12" y="12" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="22" y="12" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="2" y="22" width="7" height="7" rx="1.5"/>
|
||
<rect class="dim" x="12" y="22" width="7" height="7" rx="1.5"/>
|
||
<rect class="on" x="22" y="22" width="7" height="7" rx="1.5"/>
|
||
</svg>
|
||
<span class="brand__name">Natural Memory</span>
|
||
<span class="pill pill--acc">v2</span>
|
||
</a>
|
||
<span class="crumb">
|
||
<span class="crumb__n">06</span>
|
||
<span class="crumb__t">真实评测台账</span>
|
||
</span>
|
||
<span class="topbar__spacer"></span>
|
||
<nav class="topnav" aria-label="快速导航">
|
||
<a class="topnav__a" href="./">发布页</a> <a class="topnav__a" href="./mechanism">机制</a> <a class="topnav__a" href="./results">测量</a> <a class="topnav__a" href="./nm21">NM2.1</a> <a class="topnav__a is-on" href="./ledger" aria-current="page">台账</a> <a class="topnav__a" href="./limits">边界</a> <a class="topnav__a" href="./reproduce">复现</a>
|
||
</nav>
|
||
<button class="palbtn" id="palBtn" type="button" aria-label="检索全站内容(快捷键 /)">
|
||
<span class="palbtn__t">检索</span><span class="kbd">/</span>
|
||
</button>
|
||
<span class="pill" id="serverChip" title="本站服务端运行时读数">
|
||
<i class="dot"></i><span id="serverChipText">读取中</span>
|
||
</span>
|
||
</div>
|
||
<div class="progress" id="progress"></div>
|
||
</header>
|
||
|
||
<div class="shell">
|
||
<aside class="side">
|
||
<nav class="side__in" aria-label="章节导航">
|
||
<a class="side__back" href="./">← 返回发布页</a>
|
||
<p class="side__grp">原理</p>
|
||
<ul class="side__list">
|
||
<li><a class="side__a" href="./division"><span class="side__n">01</span><span class="side__t">记忆与 KV 的分工</span></a></li>
|
||
<li><a class="side__a" href="./mechanism"><span class="side__n">02</span><span class="side__t">一次读取与一次写入</span></a></li>
|
||
</ul>
|
||
<p class="side__grp">证据</p>
|
||
<ul class="side__list">
|
||
<li><a class="side__a" href="./results"><span class="side__n">03</span><span class="side__t">测量结果</span></a></li>
|
||
<li><a class="side__a" href="./nm21"><span class="side__n">04</span><span class="side__t">NM2.1 · 之后做了什么</span></a></li>
|
||
<li><a class="side__a" href="./examples"><span class="side__n">05</span><span class="side__t">实测样例</span></a></li>
|
||
<li><a class="side__a is-on" href="./ledger" aria-current="page"><span class="side__n">06</span><span class="side__t">真实评测台账</span></a></li>
|
||
</ul>
|
||
<p class="side__grp">工程</p>
|
||
<ul class="side__list">
|
||
<li><a class="side__a" href="./cost"><span class="side__n">07</span><span class="side__t">代价账本</span></a></li>
|
||
<li><a class="side__a" href="./capacity"><span class="side__n">08</span><span class="side__t">容量与存储</span></a></li>
|
||
<li><a class="side__a" href="./limits"><span class="side__n">09</span><span class="side__t">我们不宣称的内容</span></a></li>
|
||
<li><a class="side__a" href="./roadmap"><span class="side__n">10</span><span class="side__t">已解决的与下一步</span></a></li>
|
||
<li><a class="side__a" href="./reproduce"><span class="side__n">11</span><span class="side__t">复现实验</span></a></li>
|
||
</ul>
|
||
</nav>
|
||
</aside>
|
||
<main class="doc" id="doc">
|
||
<header class="doc__hd">
|
||
<span class="kicker">06 / FULL LEDGER</span>
|
||
<h1 class="doc__h">真实评测台账</h1>
|
||
<p class="doc__lede">全部 108 条真实评测 episode 的逐条台账:模型逐字回复、判定结果、停止原因、选中记录数与分数,可按来源与判定筛选。</p>
|
||
<p class="doc__figure">
|
||
<span class="mega">108<small></small></span>
|
||
<span class="doc__figure-n">条真实评测 episode,含全部失败</span>
|
||
</p>
|
||
</header>
|
||
<p class="lede2">
|
||
这一页不是挑出来的样例,是<strong>全部 108 条真实评测 episode 的逐条台账</strong>。
|
||
每条都带模型的逐字回复、判定结果、停止原因、选中记录数与分数。
|
||
</p>
|
||
<p class="small" id="ledgerIntro"></p>
|
||
|
||
<div class="ledger-bar">
|
||
<div class="seg" id="ledgerSrc" role="group" aria-label="按来源筛选"></div>
|
||
<div class="seg" id="ledgerVerdict" role="group" aria-label="按判定筛选"></div>
|
||
</div>
|
||
|
||
<div class="ledger-count">
|
||
<span class="mono" id="ledgerCount"></span>
|
||
<span class="tiny" id="ledgerBreak"></span>
|
||
</div>
|
||
|
||
<div class="ledger" id="ledgerList"></div>
|
||
|
||
<p class="tiny" style="margin-top:var(--sp-2xl)">
|
||
数据来自 <code>runtime_score_bands.json</code> 与 <code>nm2_1_final_runtime_e2e.json</code>,
|
||
由 <code>tools/make_ledger.py</code> 生成 <code>assets/js/ledger.js</code>,
|
||
<strong>字段逐字复制,未做改写、润色或换算</strong>。模型输出里的错字、冗余和编造的内容都按原样保留。
|
||
期望锚点是评测里的随机码(形如 <code>VAL-XXXXXXX</code>),它只出现在唯一一条候选事实里,
|
||
因此可以用来检测「证据混用」。
|
||
</p>
|
||
|
||
<nav class="pn" aria-label="章节切换"><a class="pn__a pn__a--prev" href="./examples" data-dir="prev"><span class="pn__k">上一节 · 05</span><span class="pn__t">实测样例</span><span class="kbd">←</span></a><a class="pn__a pn__a--next" href="./cost" data-dir="next"><span class="pn__k">下一节 · 07</span><span class="pn__t">代价账本</span><span class="kbd">→</span></a></nav>
|
||
</main>
|
||
</div>
|
||
|
||
<footer class="footer">
|
||
<div class="wrap footer__in">
|
||
<div class="footer__col">
|
||
<p class="footer__h">作者</p>
|
||
<div class="author">
|
||
<a class="author__a" href="https://wpyw.site" target="_blank" rel="noopener">
|
||
<span class="author__k">个人网站</span><span class="author__v">wpyw.site</span>
|
||
</a>
|
||
<a class="author__a" href="mailto:[email protected]">
|
||
<span class="author__k">邮箱</span><span class="author__v">[email protected]</span>
|
||
</a>
|
||
</div>
|
||
</div>
|
||
<div class="footer__col footer__col--wide">
|
||
<p class="footer__h">来源</p>
|
||
<div class="readout" id="footFiles"></div>
|
||
<p class="footer__h" style="margin-top:20px">服务端读数</p>
|
||
<div class="readout mono" id="footServer"><span>读取中…</span></div>
|
||
</div>
|
||
<div class="footer__col footer__col--wide">
|
||
<p class="footer__h">说明</p>
|
||
<p class="footer__note" id="disclaimer"></p>
|
||
<p class="footer__meta">构建于 2026-09-16 20:39 · 所有数字取自工程内的正式报告,未做外推或估算。</p>
|
||
</div>
|
||
</div>
|
||
</footer>
|
||
|
||
<!-- 全站检索:客户端索引,无后端、无网络请求 -->
|
||
<div class="pal" id="pal" hidden>
|
||
<div class="pal__mask" id="palMask"></div>
|
||
<div class="pal__box" role="dialog" aria-modal="true" aria-label="检索全站内容">
|
||
<div class="pal__hd">
|
||
<span class="pal__ico" aria-hidden="true"></span>
|
||
<input class="pal__in" id="palInput" type="text" role="combobox" aria-expanded="true"
|
||
aria-controls="palList" autocomplete="off" spellcheck="false"
|
||
placeholder="检索全站内容:章节、数字、术语…">
|
||
<span class="kbd">Esc</span>
|
||
</div>
|
||
<div class="pal__list" id="palList" role="listbox" aria-label="检索结果"></div>
|
||
<div class="pal__ft">
|
||
<span><span class="kbd">↑</span><span class="kbd">↓</span> 选择</span>
|
||
<span><span class="kbd">↵</span> 打开</span>
|
||
<span class="pal__n mono" id="palN"></span>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
<script src="assets/js/data.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/examples.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/restart.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/nm21.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/ledger.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/search.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/space.js?v=a9c21ef3a8"></script>
|
||
<script src="assets/js/site.js?v=a9c21ef3a8"></script>
|
||
</body>
|
||
</html>
|