import { initSite } from './site-shell.js';
import { mountain } from './mountain.js';
'use strict';
const $ = id => document.getElementById(id);
const metricKeys = ['perfect', 'partial_replication', 'compilation_success', 'coefficient_direction', 'significance_level'];
const en = Object.fromEntries([...document.querySelectorAll('[data-i18n]')].map(el => [el.dataset.i18n, el.innerHTML]));
Object.assign(en, {
  model: 'Model / API alias', rank: '#', score: 'Score', evidenceCol: 'Evidence', pp: 'pp',
  passed: 'successes', metricUnknown: 'metric unknown', review: 'Evidence gaps',
  config: 'Config', recordsLink: 'Results', allSealed: 'Archived',
  taskUnknown: 'task status unknown', invalid: 'invalid evidence', interruptions: 'interruptions',
  historicalStatus: 'Historical status; task unknown count not exported',
  groupLocal: 'Local paper profile', groupHF: 'HF-style profile · parity unverified',
  loading: 'Loading archived results…', searchPlaceholder: 'Search models…',
  matched: '{n} of {total} models', localProfile: 'local-paper-v1', hfProfile: 'hf-leaderboard-v1 · parity unverified',
  matchedRuns: '{n} of {total} runs', protocol: 'Protocol', independentRun: 'Independent · alias unverified',
  published: 'Published {date}',
  perfectDesc: 'Coefficient and standard-error relative errors ≤ 1%, and p-value absolute error ≤ 0.01, all at once.',
  partial_replicationDesc: 'Coefficient relative error ≤ 5%. No standard-error or p-value condition.',
  compilation_successDesc: 'Verified code execution completed successfully; a valid prediction JSON is not required.',
  coefficient_directionDesc: 'The coefficient has the same strictly positive or negative sign as the reference.',
  significance_levelDesc: 'Matching p-value category: p < .01, p < .05, p < .1, or otherwise. No direction condition.',
});
const zh = {
  dataset: '数据集 ↗', archive: '结果存档 ↗', edition: '研究榜单 · 2026 年 9 月',
  title: 'InferenceNet 挑战赛排行榜',
  intro: '模型与 Harness 在 1,000 道计量经济学复现任务上的表现。',
  models: '种模型别名', groups: '组实验', tasks: '题 / 组', records: '条任务记录', published: '发布于 {date}',
  single: '单次 Agent', harness: '全部 Harness 实验', deepagents: 'DeepAgents',
  dsh: 'DeepSeek Harness · 独立实验',
  dshDesc: '使用官方 DSH SDK，请求 v4-pro API 别名。按固定规则纳入技术补测，底层模型权重未经核实。',
  dshNoticeTitle: 'DSH 作为独立实验展示。',
  dshNotice: '请求使用 deepseek-v4-pro 别名，底层模型权重未经核实。固定的 1,000 题结果包含 87 次技术补测替换（其中 27 题调整了输入 schema 提示），仍有 30 题状态未知；不纳入 DeepAgents 配对提升计算。',
  dshProtocol: '查看运行协议与证据 ↗',
  singleDesc: '一次模型调用生成代码，然后执行；不进行多轮 Agent 循环。',
  harnessDesc: 'DeepAgents 进行规划、工具调用与代码修订；最多 6 次模型调用，最后执行。',
  resultsLabel: '01 / 评测结果', rankings: 'Agent 与 Harness 对照榜单', research: '研究结果 · 阶段版',
  scope: '基于已存档结果的本地评分，尚未验证与官方评分器完全一致。两组预算及不同批次协议存在差异，提升值用于描述观察结果，不代表等成本对比。',
  compare: 'Baseline / DeepAgents 配对', download: '下载 CSV ↓', metric: '评分指标',
  perfect: '完整复现率 · 本地口径', partial_replication: '部分复现率 · HF 口径',
  compilation_success: '执行成功率 · HF 口径', coefficient_direction: '系数方向正确率 · HF 口径',
  significance_level: '显著性水平正确率 · HF 口径',
  sort: '排序方式', harnessScore: 'DeepAgents 组成绩', singleScore: '单次组成绩', lift: '提升', search: '查找模型',
  error: '结果加载失败，请重试或打开结果存档。', retry: '重试', empty: '没有匹配的模型。',
  denominator: '所有指标固定以 1,000 题为分母，未知和无效记录不计为成功。',
  methodLabel: '02 / 如何解读', methodTitle: '每个成绩都有据可查。', historical: '查看历史榜单 ↗',
  fixedTasks: '固定的题目集合', fixedDesc: '所有组使用相同的 Selected_1000 题号和数据集版本。成绩 = 成功数 ÷ 1,000，失败和未知记录始终保留在分母中。',
  separateMetrics: '两套评分口径', profilesDesc: '完整复现率采用本地论文口径。其余四项 HF 指标由本地实现复现网页定义，尚未验证与官方评分器一致。',
  budgetTitle: '结合预算看提升', budgetDesc: '单次组使用 1 次模型调用；DeepAgents 和 DSH 每次尝试最多 6 次模型调用、4 次试运行工具调用。DSH 额外进行了 87 次技术补测，完整环境和推理设定是否一致尚未核实；不计算 DSH 配对提升，也不能据此判断等成本的因果效果。',
  evidence: '证据状态与指标定义',
  unknownDesc: '“指标未知”表示该指标无法判断，可能源于执行失败或输出缺失；它与“任务最终状态未知”不同。两者均不剔除，也不计为成功。',
  evidenceCaption: '各组已接收存档中的状态', model: '模型 / API 别名', protocol: '执行方式',
  verification: '四项 HF 指标已与逐题存档标记核对。Sol 和 Opus 的完整复现率来自已接收汇总；其余实验（含 DSH）均可逐题核对本地评分标记。本次网页更新没有重新运行或重新评分实验。',
  archiveNote: '各组原始存档及当时的发布元数据保持不变，本页是基于存档的新展示。本版不包含 GPT-5.5 和尚未存档的实验。',
  footer: '衡量计量经济学复现能力。', source: '来源快照 ↗', json: '数据 JSON ↗', project: '项目页 ↗',
  rank: '#', score: '成绩', evidenceCol: '证据', pp: '百分点', passed: '题成功', metricUnknown: '指标未知', review: '存在证据缺口',
  config: '配置', recordsLink: '逐题结果', allSealed: '已存档', taskUnknown: '任务状态未知', invalid: '无效证据', interruptions: '中断记录',
  historicalStatus: '历史存档，未导出任务未知总数', groupLocal: '本地论文口径', groupHF: 'HF 网页口径 · 一致性待验证',
  loading: '正在加载存档结果…', searchPlaceholder: '搜索模型…', matched: '显示 {n} / {total} 个模型',
  matchedRuns: '显示 {n} / {total} 组实验', independentRun: '独立实验 · 别名权重未核实',
  localProfile: 'local-paper-v1 · 本地口径', hfProfile: 'hf-leaderboard-v1 · 一致性待验证',
  perfectDesc: '系数与标准误的相对误差均 ≤ 1%，同时 p 值绝对误差 ≤ 0.01。',
  partial_replicationDesc: '系数相对误差 ≤ 5%，不要求标准误或 p 值达标。',
  compilation_successDesc: '有可信证据证明代码完整执行成功，不要求生成有效的预测 JSON。',
  coefficient_directionDesc: '预测系数与参考系数具有相同的严格正号或负号。',
  significance_levelDesc: 'p 值类别一致：p < .01、p < .05、p < .1 或其他，不要求系数方向一致。',
};
let language = 'en';
try { language = localStorage.getItem('inferencenet-language') === 'zh' ? 'zh' : 'en'; } catch (_) {}
let data = null;
let view = 'all';
let display = 'table';
let sortBy = 'deepagents';
const t = key => (language === 'zh' ? zh[key] : en[key]) ?? en[key] ?? key;
const esc = value => String(value).replace(/[&<>"']/g, char => ({'&':'&amp;', '<':'&lt;', '>':'&gt;', '"':'&quot;', "'":'&#39;'}[char]));
const sourceURL = (path, tree = false) => `https://huggingface.co/spaces/CamoAiLab/InferenceNet-Leaderboard/${tree ? 'tree' : 'blob'}/${data.source_revision}/${path}`;
const external = (url, label) => `<a href="${esc(url)}" target="_blank" rel="noopener noreferrer">${esc(label)} ↗</a>`;


Object.assign(en, {
  publicationNote: 'Research snapshot · local scoring; official scorer parity unverified. Run budgets differ.',
  all: 'All results', website: 'Project website ↗', tableView: 'Table', mountainView: 'Mountain view',
  evaluationDetails: 'Evaluation protocol, definitions & evidence', detailsLink: 'Details ↗',
  dshShort: 'DSH: model weights unverified; 87 technical replacements, 30 unknown task outcomes. Excluded from paired lift.',
  harnessColumn: 'Harness', noHarness: 'None', independentLabel: 'Independent',
  light: 'Light', dark: 'Dark', fullShort: 'Full replication', partialShort: 'Partial replication',
  executionShort: 'Execution success', directionShort: 'Coefficient direction', significanceShort: 'Significance level',
  mountainTitle: 'The climb to full replication', summit: '100% · every task succeeds',
  mountainNote: 'Height represents the selected score. Run protocols and budgets differ.',
  scoreDetails: 'Successes / tasks; metric unknown', comparisonNote: 'Paired view includes baseline and DeepAgents only. DSH remains a separate result.',
});
Object.assign(zh, {
  publicationNote: '研究快照 · 本地评分，尚未验证与官方评分器一致；各组运行预算存在差异。',
  all: '全部结果', website: '项目官网 ↗', tableView: '成绩表', mountainView: '登山图',
  evaluationDetails: '评测协议、指标定义与证据', detailsLink: '查看详情 ↗',
  dshShort: 'DSH：模型权重未核实，含 87 次技术补测替换、30 题状态未知；不纳入配对提升。',
  harnessColumn: 'Harness', noHarness: '无', independentLabel: '独立实验',
  light: '浅色', dark: '深色', fullShort: '完整复现率', partialShort: '部分复现率',
  executionShort: '执行成功率', directionShort: '系数方向', significanceShort: '显著性水平',
  mountainTitle: '向完整复现迈进', summit: '100% · 每道任务均成功',
  mountainNote: '高度表示所选指标得分。各组运行协议与预算存在差异。',
  scoreDetails: '成功数 / 题数；指标未知', comparisonNote: '配对视图仅比较单次组与 DeepAgents；DSH 单独展示。',
  metric: '排名指标', single: '单次生成', harness: '模型 + Harness', compare: '配对提升',
});
const shortKeys = ['fullShort', 'partialShort', 'executionShort', 'directionShort', 'significanceShort'];
function applyLanguage() {
  document.documentElement.lang = language === 'zh' ? 'zh-CN' : 'en';
  document.querySelectorAll('[data-i18n]').forEach(el => { el.innerHTML = t(el.dataset.i18n); });
  $('language').textContent = language === 'en' ? '中文' : 'EN';
  $('language').setAttribute('aria-label', language === 'en' ? 'Switch to Chinese' : 'Switch to English');
  $('search').placeholder = t('searchPlaceholder');
  $('load-state').textContent = t('loading');
  document.querySelector('[data-group=local]').label = t('groupLocal');
  document.querySelector('[data-group=hf]').label = t('groupHF');
  $('definitions').innerHTML = metricKeys.map(key => `<li><strong>${esc(t(key))}:</strong> ${esc(t(key + 'Desc'))}</li>`).join('');
  render();
}

function validate(candidate) {
  if (candidate.schema_version !== 1 || candidate.models?.length !== 6 || ![12, 13].includes(candidate.groups) || candidate.records !== candidate.groups * 1000 || candidate.tasks_per_group !== 1000 || candidate.official_parity_verified !== false || !/^[a-f0-9]{40}$/.test(candidate.source_revision) || !/^\d{4}-\d{2}-\d{2}$/.test(candidate.published_date)) throw new Error('Invalid leaderboard snapshot');
  const ids = new Set();
  let groups = 0;
  for (const model of candidate.models) {
    if (!/^[a-z0-9.-]+$/.test(model.id) || ids.has(model.id) || typeof model.name !== 'string') throw new Error('Invalid model');
    ids.add(model.id);
    if (!model.arms?.baseline || !model.arms?.deepagents) throw new Error('Missing paired arm');
    for (const armId of Object.keys(model.arms)) {
      if (!['baseline', 'deepagents'].includes(armId) && !(model.id === 'deepseek-v4-pro' && armId === 'dsh')) throw new Error('Unexpected arm');
      const arm = model.arms?.[armId];
      if (arm?.path !== `results/${model.id}/${armId}` || typeof arm.complete !== 'boolean') throw new Error('Invalid arm');
      if (armId === 'dsh' && (arm.paired_comparison !== false || arm.comparison_group !== 'independent' || arm.underlying_model_weights_verified !== false || arm.model_alias !== 'deepseek-v4-pro' || typeof arm.display_name !== 'string' || arm.evidence_class !== 'technical_recovery_view' || arm.protocol_url !== arm.path + '/README.md')) throw new Error('Invalid independent result');
      groups += 1;
      for (const key of metricKeys) {
        const metric = arm.metrics?.[key];
        if (!metric || metric.denominator !== 1000 || !Number.isInteger(metric.count) || !Number.isInteger(metric.unknown) || metric.count < 0 || metric.unknown < 0 || metric.count + metric.unknown > 1000 || !Number.isFinite(metric.score) || Math.abs(metric.score - metric.count / 10) > 1e-8 || metric.profile !== (key === 'perfect' ? 'local-paper-v1' : 'hf-leaderboard-v1')) throw new Error('Invalid metric');
      }
    }
  }
  if (groups !== candidate.groups) throw new Error('Inconsistent group count');
  return candidate;
}

// Pairing is intentionally limited to the two historical arms. Independent
// harness entries have their own rank and can never enter a paired lift.
function rankedEntries(snapshot, selectedView, key, selectedSort, query) {
  const entries = selectedView === 'compare'
    ? snapshot.models.map(model => ({model, armId: null, arm: model.arms.baseline, name: model.name,
        value: selectedSort === 'gain' ? model.arms.deepagents.metrics[key].count - model.arms.baseline.metrics[key].count : model.arms[selectedSort].metrics[key].count}))
    : snapshot.models.flatMap(model => Object.entries(model.arms)
        .filter(([id]) => selectedView === 'all' || (selectedView === 'baseline' ? id === 'baseline' : id !== 'baseline'))
        .map(([armId, arm]) => ({model, armId, arm, name: armId === 'dsh' ? 'DeepSeek API · v4-pro alias' : model.name, value: arm.metrics[key].count})));
  const search = query.toLowerCase().trim();
  const filtered = entries.filter(entry => `${entry.name} ${entry.model.id} ${entry.armId || ''} ${entry.arm.display_name || ''}`.toLowerCase().includes(search))
    .sort((a, b) => b.value - a.value || a.name.localeCompare(b.name) || String(a.armId).localeCompare(String(b.armId)));
  let last = null, rank = 0;
  filtered.forEach((entry, i) => { if (entry.value !== last) rank = i + 1; last = entry.value; entry.rank = rank; });
  return {total: entries.length, entries: filtered};
}
function protocolName(armId) { return armId === 'baseline' ? t('noHarness') : armId === 'dsh' ? 'DSH' : 'DeepAgents'; }
function compactScore(arm, key, active) {
  const m = arm.metrics[key];
  const description = `${m.count} / 1,000 ${t('passed')}; ${t('metricUnknown')}: ${m.unknown}`;
  return `<td class="numeric ${active ? 'selected-metric' : ''}"><span tabindex="0" class="metric-value" aria-label="${esc(m.score.toFixed(1) + '%; ' + description)}">${m.score.toFixed(1)}<small>%</small><span class="metric-tooltip" role="tooltip">${esc(description)}</span></span></td>`;
}
function renderMountain(entries, key) {
  const el = $('ranking-mountain');
  el.hidden = display !== 'mountain' || entries.length === 0 || view === 'compare';
  if (el.hidden) return;
  // Mountain markers use unique ordinal IDs, with tied scores at the same altitude.
  mountain(el, {
    title: t('mountainTitle'), metric: t(shortKeys[metricKeys.indexOf(key)]), unit: '%', max: 100,
    peakLabel: t('summit'), caption: t('mountainNote'),
    items: entries.map((entry, i) => ({rank: i + 1, label: `${entry.name} · ${protocolName(entry.armId)}${entry.armId === 'dsh' ? ' *' : ''}`, value: entry.arm.metrics[key].score, kind: 'internal'})),
    locale: language,
  }, {table: false, aspect: 0.44, compactAspect: 0.75});
}

function scoreCell(arm, key, style) {
  const m = arm.metrics[key];
  return `<td class="score-cell ${style}"><span class="score">${m.score.toFixed(1)}<small>%</small></span><div class="track" aria-hidden="true"><div class="fill" style="width:${m.score}%"></div></div><span class="counts">${m.count} / 1,000 ${esc(t('passed'))}</span><span class="unknown">${esc(t('metricUnknown'))}: ${m.unknown}</span></td>`;
}

function evidenceState(arm) {
  let status = '';
  if (arm.task_unknown_count !== null) status = `${arm.task_unknown_count} ${t('taskUnknown')} · ${arm.invalid_evidence_count} ${t('invalid')}`;
  else status = `${arm.interruption_count ?? '—'} ${t('interruptions')}<span>${esc(t('historicalStatus'))}</span>`;
  return `<td>${status}<span>${external(sourceURL(arm.path + '/config.json'), t('config'))} · ${external(sourceURL(arm.path + '/summary.json'), t('recordsLink'))}</span></td>`;
}

function render() {
  const key = $('metric').value;
  $('metric-description').textContent = t(key + 'Desc');
  if (!data) return;
  const {total, entries} = rankedEntries(data, view, key, sortBy, $('search').value);
  $('published-date').textContent = t('published').replace('{date}', data.published_date);
  $('sort-control').hidden = view !== 'compare';
  $('table-wrap').hidden = entries.length === 0 || (display === 'mountain' && view !== 'compare');
  $('empty').hidden = entries.length !== 0;
  $('result-count').textContent = t(view === 'compare' ? 'matched' : 'matchedRuns').replace('{n}', entries.length).replace('{total}', total);
  $('caption').textContent = `${t(view === 'compare' ? 'compare' : view === 'all' ? 'all' : view === 'baseline' ? 'single' : 'harness')} — ${t(key)}`;
  const th = (text, cls = '') => `<th scope="col" class="${cls}">${esc(text)}</th>`;
  $('table-head').innerHTML = '<tr>' + th(t('rank'), 'rank') + th(t('model'), 'model-heading') + (view === 'compare'
    ? th(t('single'), 'numeric') + th('DeepAgents', 'numeric') + th(t('lift'), 'numeric')
    : th(t('harnessColumn')) + metricKeys.map((metric, i) => `<th scope="col" class="numeric ${metric === key ? 'selected-metric' : ''}" aria-sort="${metric === key ? 'descending' : 'none'}"><button type="button" data-metric="${metric}" title="${esc(t(metric + 'Desc'))}">${esc(t(shortKeys[i]))}${metric === key ? ' ↓' : ''}</button></th>`).join('')) + th(t('evidenceCol'), 'evidence-col') + '</tr>';
  $('table-body').innerHTML = entries.map(entry => {
    const {model, arm, armId, name, rank} = entry;
    const arms = model.arms;
    const identity = `<td class="rank"><span class="rank-number rank-${rank}">${rank}</span></td><th scope="row" class="model-cell">${esc(name)}</th>`;
    let scores = '', sources = '';
    if (view === 'compare') {
      const gain = (arms.deepagents.metrics[key].count - arms.baseline.metrics[key].count) / 10;
      scores = scoreCell(arms.baseline, key, 'baseline') + scoreCell(arms.deepagents, key, 'harness') + `<td class="gain numeric ${gain < 0 ? 'negative' : ''}">${gain > 0 ? '+' : ''}${gain.toFixed(1)}<small>${esc(t('pp'))}</small></td>`;
      sources = external(sourceURL(arms.baseline.path, true), 'A') + external(sourceURL(arms.deepagents.path, true), 'B');
    } else {
      const badge = armId === 'dsh' ? `<a class="independent-tag" href="#protocol-details">${esc(t('independentLabel'))} ↗</a>` : '';
      scores = `<td class="protocol-cell"><span class="protocol-label ${armId === 'baseline' ? 'no-harness' : ''}">${esc(protocolName(armId))}</span>${badge}</td>` + metricKeys.map(metric => compactScore(arm, metric, metric === key)).join('');
      sources = external(sourceURL(arm.path + '/results.jsonl'), t('recordsLink')) + (!arm.complete ? `<span class="evidence-gap">${esc(t('review'))}</span>` : '');
    }
    return `<tr data-model="${esc(model.id)}" data-arm="${esc(armId || 'paired')}">${identity}${scores}<td class="source-cell">${sources}</td></tr>`;
  }).join('');
  $('evidence-body').innerHTML = data.models.flatMap(m => Object.entries(m.arms).map(([id, arm]) => `<tr><th scope="row">${esc(arm.display_name || m.name)}</th><td>${esc(id === 'baseline' ? t('single') : id === 'dsh' ? t('dsh') : 'DeepAgents')}</td>${evidenceState(arm)}</tr>`)).join('');
  const dsh = data.models.find(m => m.id === 'deepseek-v4-pro')?.arms.dsh;
  $('independent-notice').hidden = !dsh;
  $('independent-summary').hidden = !dsh || view === 'baseline' || view === 'compare';
  if (dsh) $('dsh-protocol').href = sourceURL(dsh.protocol_url);
  document.querySelector('[data-display="mountain"]').disabled = view === 'compare';
  renderMountain(entries, key);
}

async function loadData() {
  data = null;
  $('retry').disabled = true;
  $('error').hidden = true;
  $('load-state').hidden = false;
  $('table-wrap').hidden = true;
  $('ranking-mountain').hidden = true;
  $('independent-summary').hidden = true;
  $('empty').hidden = true;
  $('result-count').textContent = '';
  $('evidence-body').replaceChildren();
  $('independent-notice').hidden = true;
  for (const id of ['model-count', 'group-count', 'task-count', 'record-count']) $(id).textContent = '—';
  try {
    const response = await fetch('./leaderboard-data.json', {cache: 'no-cache'});
    if (!response.ok) throw new Error(`HTTP ${response.status}`);
    data = validate(await response.json());
    $('model-count').textContent = data.models.length;
    $('group-count').textContent = data.groups;
    $('task-count').textContent = data.tasks_per_group.toLocaleString('en-US');
    $('record-count').textContent = data.records.toLocaleString('en-US');
    $('revision-link').href = sourceURL('results', true);
    render();
  } catch (error) {
    console.error('Leaderboard data could not be loaded:', error);
    $('error').hidden = false;
  } finally {
    $('load-state').hidden = true;
    $('retry').disabled = false;
  }
}

document.querySelectorAll('[data-view]').forEach(button => button.addEventListener('click', () => {
  view = button.dataset.view;
  if (view === 'compare') setDisplay('table');
  document.querySelectorAll('[data-view]').forEach(el => el.setAttribute('aria-pressed', String(el === button)));
  render();
}));
$('metric').addEventListener('change', render);
$('sort').addEventListener('change', event => { sortBy = event.target.value; render(); });
$('search').addEventListener('input', render);
$('retry').addEventListener('click', loadData);
function setDisplay(next) {
  display = next;
  document.querySelectorAll('[data-display]').forEach(el => el.setAttribute('aria-pressed', String(el.dataset.display === next)));
  render();
}
document.querySelectorAll('[data-display]').forEach(button => button.addEventListener('click', () => setDisplay(button.dataset.display)));
$('table-head').addEventListener('click', event => {
  const button = event.target.closest('[data-metric]');
  if (button) { $('metric').value = button.dataset.metric; render(); }
});
document.addEventListener('click', event => {
  if (event.target.closest('a[href="#protocol-details"]')) $('protocol-details').open = true;
});
initSite({ onLanguageChange: next => { language = next; applyLanguage(); } });
applyLanguage();
loadData();