YICHEN013's picture
Clarify dataset access before downloading the task list
176b56a verified
Raw
History Blame Contribute Delete
12.7 kB
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="icon" href="data:image/svg+xml,%3Csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 32 32'%3E%3Crect width='32' height='32' rx='6' fill='%230c1219'/%3E%3Ctext x='5' y='23' font-family='sans-serif' font-size='21' fill='%2378dbc0'%3EiN%3C/text%3E%3C/svg%3E">
<meta name="color-scheme" content="light dark">
<meta name="description" content="Explore the pinned Selected_1000 benchmark: methods, journals, task structure and dataset access.">
<title>Data — InferenceNet Challenge</title>
<link rel="stylesheet" href="./leaderboard.css">
<link rel="stylesheet" href="./portal.css">
<script type="module" src="./portal.js">
</script>
</head>
<body>
<a class="skip" href="#main">
<span data-en="Skip to content" data-zh="跳转到正文" >Skip to content</span>
</a>
<div class="page">
<nav class="topbar" aria-label="Main navigation">
<a class="brand" href="./index.html">InferenceNet <small>CHALLENGE</small>
</a>
<div class="nav-links">
<a href="./index.html">
<span data-en="Home" data-zh="主页" >Home</span>
</a>
<a href="./data.html" aria-current="page">
<span data-en="Data" data-zh="数据" >Data</span>
</a>
<a href="./leaderboard.html">
<span data-en="Leaderboard" data-zh="榜单" >Leaderboard</span>
</a>
<a href="./agent.html">
<span data-en="Agent / Harness" data-zh="Agent / Harness" >Agent / Harness</span>
</a>
<button id="language" type="button" aria-label="Switch to Chinese">中文</button>
<button id="theme" type="button" aria-pressed="false">
<span class="theme-icon" aria-hidden="true">
</span>
<span id="theme-label">Light</span>
</button>
</div>
</nav>
<main id="main">
<header class="portal-hero">
<p class="eyebrow">DATA · SELECTED_1000</p>
<h1 data-en="The benchmark, task by task." data-zh="逐题了解评测数据。" >The benchmark, task by task.</h1>
<p data-en="Each task names an outcome, a treatment, controls, an estimation method and a data file. The goal is to recover one reported effect: its coefficient, standard error and p-value." data-zh="每道任务指定结果变量、处理变量、控制变量、估计方法与数据文件,要求复现一个研究效应的系数、标准误和 p 值。" class="portal-lead">Each task names an outcome, a treatment, controls, an estimation method and a data file. The goal is to recover one reported effect: its coefficient, standard error and p-value.</p>
<div class="actions">
<a href="https://huggingface.co/datasets/CamoAiLab/InferenceNet" class="action primary" target="_blank" rel="noopener noreferrer">
<span data-en="Open the dataset ↗" data-zh="打开数据集 ↗" >Open the dataset ↗</span>
</a>
<a href="https://huggingface.co/datasets/CamoAiLab/InferenceNet/resolve/59f9512a38e594528807744214a60ee00367434e/Selected_1000/1000_new.csv?download=true" class="action" target="_blank" rel="noopener noreferrer">
<span data-en="Download task list ↓" data-zh="下载任务清单 ↓" >Download task list ↓</span>
</a>
</div>
<p class="source-note" data-en="Dataset downloads require a Hugging Face account with access. Open the dataset to request access before using the download link." data-zh="下载数据需要登录 Hugging Face 并获得访问权限;请先打开数据集申请访问,再使用下载链接。">Dataset downloads require a Hugging Face account with access. Open the dataset to request access before using the download link.</p>
</header>
<div class="scale-strip">
<div>
<strong>1,000</strong>
<span data-en="fixed evaluation tasks" data-zh="固定评测任务" >fixed evaluation tasks</span>
</div>
<div>
<strong>15</strong>
<span data-en="journals in this subset" data-zh="子集涵盖期刊" >journals in this subset</span>
</div>
<div>
<strong>286</strong>
<span data-en="distinct article titles" data-zh="不同论文标题" >distinct article titles</span>
</div>
<div>
<strong>5</strong>
<span data-en="estimation classes" data-zh="估计方法大类" >estimation classes</span>
</div>
</div>
<p data-en="Selected_1000 · Counts from the pinned task list, revision 59f9512." data-zh="Selected_1000 · 按固定任务清单统计,版本 59f9512。" class="source-note">Selected_1000 · Counts from the pinned task list, revision 59f9512.</p>
<section class="portal-section">
<div class="portal-heading">
<p data-en="01 / DISTRIBUTION" data-zh=" 01 / DISTRIBUTION" class="eyebrow">01 / DISTRIBUTION</p>
<h2 data-en="Different research questions. Different demands." data-zh="不同的研究问题,不同的复现要求。" >Different research questions. Different demands.</h2>
</div>
<div class="distribution-grid">
<figure class="distribution">
<figcaption>
<h3 data-en="Estimation methods" data-zh="估计方法" >Estimation methods</h3>
<p data-en="Five classes · 1,000 tasks" data-zh="五大类 · 1,000 题" >Five classes · 1,000 tasks</p>
</figcaption>
<div id="method-chart" class="bar-chart" role="status">
<span data-en="Loading distributions…" data-zh="正在加载分布…" >Loading distributions…</span>
</div>
<p data-en="OLS includes panel OLS; IV includes IV-2SLS. Other combines Probit, Logit, negative binomial, LMM, PSM and Cox models." data-zh="OLS 包含面板 OLS,IV 包含 IV-2SLS;其他类合并 Probit、Logit、负二项、LMM、PSM 与 Cox 模型。" class="source-note">OLS includes panel OLS; IV includes IV-2SLS. Other combines Probit, Logit, negative binomial, LMM, PSM and Cox models.</p>
</figure>
<figure class="distribution">
<figcaption>
<h3 data-en="Journal coverage" data-zh="期刊分布" >Journal coverage</h3>
<p data-en="The five largest sources; all 15 below" data-zh="五个最大的任务来源;展开可查看全部 15 本" >The five largest sources; all 15 below</p>
</figcaption>
<div id="journal-chart" class="bar-chart" role="status">
<span data-en="Loading distributions…" data-zh="正在加载分布…" >Loading distributions…</span>
</div>
<details class="journal-rest">
<summary>
<span data-en="All 15 journals" data-zh="全部 15 本期刊" >All 15 journals</span>
</summary>
<div id="journal-table">
</div>
</details>
</figure>
</div>
<p data-en="Percentages use all 1,000 tasks. These distributions are recomputed from the pinned CSV, not from the moving dataset main branch." data-zh="百分比均以 1,000 题为分母;分布重新统计自固定版本的 CSV,不随数据集主分支变化。" class="source-note">Percentages use all 1,000 tasks. These distributions are recomputed from the pinned CSV, not from the moving dataset main branch.</p>
</section>
<section class="portal-section">
<div class="portal-heading">
<p data-en="02 / TASK FORMAT" data-zh=" 02 / TASK FORMAT" class="eyebrow">02 / TASK FORMAT</p>
<h2 data-en="A clear input and output contract." data-zh="明确任务输入与输出。" >A clear input and output contract.</h2>
</div>
<div class="anatomy-grid">
<article>
<h3 data-en="What the agent receives" data-zh="Agent 的输入" >What the agent receives</h3>
<p data-en="Target and explanatory variables, controls, estimator, analysis requirements, and mounted source data." data-zh="目标变量与解释变量、控制变量、估计方法、分析要求,以及挂载的数据文件。" >Target and explanatory variables, controls, estimator, analysis requirements, and mounted source data.</p>
</article>
<article>
<h3 data-en="What the agent produces" data-zh="Agent 的输出" >What the agent produces</h3>
<p data-en="An executable program and a result JSON containing coefficient, standard_error and p_value." data-zh="可执行程序,以及包含 coefficient、standard_error、p_value 的结果 JSON。" >An executable program and a result JSON containing coefficient, standard_error and p_value.</p>
</article>
<article>
<h3 data-en="What the evaluator keeps separate" data-zh="评测侧独立保存的内容" >What the evaluator keeps separate</h3>
<p data-en="Reference answers and replication programs are kept outside the model input during evaluation. Dataset downloads can contain references." data-zh="评测时参考答案与复现程序不进入模型输入;数据集下载文件可能包含这些参考资料。" >Reference answers and replication programs are kept outside the model input during evaluation. Dataset downloads can contain references.</p>
</article>
</div>
</section>
<section class="portal-section">
<div class="portal-heading">
<p data-en="03 / EXAMPLE" data-zh=" 03 / EXAMPLE" class="eyebrow">03 / EXAMPLE</p>
<h2 data-en="One task, in context." data-zh="一个具体任务。" >One task, in context.</h2>
</div>
<div class="case-summary">
<div>
<p class="eyebrow">TASK 0011 · OLS</p>
<h3 data-en="Economic uncertainty and the “two Spains”" data-zh="经济不确定性与“两个西班牙”" >Economic uncertainty and the “two Spains”</h3>
<p data-en="Recover the relationship between socio-economic conflict and policy uncertainty, with three controls and month-clustered standard errors." data-zh="在加入三个控制变量、按月聚类标准误的设定下,复现社会经济冲突与政策不确定性的关系。" >Recover the relationship between socio-economic conflict and policy uncertainty, with three controls and month-clustered standard errors.</p>
<a href="./agent.html#case" class="text-link">
<span data-en="See the agent walkthrough →" data-zh="查看 Agent 执行过程 →" >See the agent walkthrough →</span>
</a>
</div>
<dl class="compact-spec">
<dt>y</dt>
<dd>
<code>EPU0month_simsn_w</code>
</dd>
<dt>x</dt>
<dd>
<code>Wscmonth_simsn_w</code>
</dd>
<dt>
<span data-en="Data" data-zh="数据" >Data</span>
</dt>
<dd>
<code>data_np.dta</code>
</dd>
<dt>
<span data-en="Sample" data-zh="样本" >Sample</span>
</dt>
<dd>1905–1945 · 977 <span data-en="estimation observations" data-zh="估计样本观测" >estimation observations</span>
</dd>
</dl>
</div>
</section>
<section class="portal-section">
<div class="portal-heading">
<p data-en="04 / SOURCE" data-zh=" 04 / SOURCE" class="eyebrow">04 / SOURCE</p>
<h2 data-en="A fixed, inspectable snapshot." data-zh="固定且可核查的数据版本。" >A fixed, inspectable snapshot.</h2>
</div>
<dl class="provenance">
<dt>
<span data-en="Dataset" data-zh="数据集" >Dataset</span>
</dt>
<dd>
<a href="https://huggingface.co/datasets/CamoAiLab/InferenceNet" class="" target="_blank" rel="noopener noreferrer">
<span data-en="CamoAiLab/InferenceNet ↗" data-zh="CamoAiLab/InferenceNet ↗" >CamoAiLab/InferenceNet ↗</span>
</a>
</dd>
<dt>
<span data-en="Pinned revision" data-zh="固定版本" >Pinned revision</span>
</dt>
<dd>
<code>59f9512a38e594528807744214a60ee00367434e</code>
</dd>
<dt>
<span data-en="Task list" data-zh="任务清单" >Task list</span>
</dt>
<dd>
<code>Selected_1000/1000_new.csv</code>
</dd>
<dt>
<span data-en="Subset labels" data-zh="子集标签" >Subset labels</span>
</dt>
<dd>
<span data-en="1,000 Stata-labelled tasks; 14 raw method labels folded into five classes. Article count is the number of distinct title strings." data-zh="1,000 题均标注为 Stata;14 种原始方法标签归并为五大类。论文数量按不同标题字符串统计。" >1,000 Stata-labelled tasks; 14 raw method labels folded into five classes. Article count is the number of distinct title strings.</span>
</dd>
</dl>
<div class="actions">
<a href="./dataset-summary.json" class="text-link">
<span data-en="Download distribution JSON ↓" data-zh="下载分布 JSON ↓" >Download distribution JSON ↓</span>
</a>
<a href="https://easonai-5589.github.io/inferencenet-challenge/data.html" class="text-link" target="_blank" rel="noopener noreferrer">
<span data-en="Extended data documentation ↗" data-zh="完整数据说明 ↗" >Extended data documentation ↗</span>
</a>
</div>
</section>
</main>
<footer>
<span>InferenceNet <span class="muted">/</span> <span data-en="AI for empirical research." data-zh="面向实证研究的 AI。" >AI for empirical research.</span>
</span>
<div>
<a href="https://huggingface.co/datasets/CamoAiLab/InferenceNet" class="" target="_blank" rel="noopener noreferrer">
<span data-en="Dataset ↗" data-zh="数据集 ↗" >Dataset ↗</span>
</a>
<a href="https://easonai-5589.github.io/inferencenet-challenge/" class="" target="_blank" rel="noopener noreferrer">
<span data-en="Project website ↗" data-zh="项目官网 ↗" >Project website ↗</span>
</a>
<a href="https://easonai-5589.github.io/inferencenet-challenge/teams.html" class="" target="_blank" rel="noopener noreferrer">
<span data-en="Team &amp; contact ↗" data-zh="团队与联系 ↗" >Team &amp; contact ↗</span>
</a>
</div>
</footer>
</div>
</body>
</html>