feat: audit K3 open model artifacts

2026-07-29 12:44:37 +08:00
parent c3d332680c
commit be2b291a04
13 changed files with 2387 additions and 29 deletions
@@ -75,6 +75,10 @@ const overview = await evaluate(`(() => ({
  paperGroups: document.querySelectorAll("#papers .paper-group").length,
  labTabs: document.querySelectorAll("[data-k3-tab]").length,
  labPanels: document.querySelectorAll("[data-k3-panel]").length,
+  artifactTabs: document.querySelectorAll("[data-artifact-tab]").length,
+  artifactPanels: document.querySelectorAll("[data-artifact-panel]").length,
+  artifactLayers: document.querySelectorAll("[data-layer-cell]").length,
+  artifactMismatch: document.querySelector("#artifacts")?.textContent.includes("A_log [128] ≠ expected [96]"),
  nativeVisionCorrected: document.body.textContent.includes("MoonViT‑V2 从头训练") &&
    document.body.textContent.includes("同一个 next-token prediction objective"),
  staleVisionClaim: document.body.textContent.includes("先固定语言模型训练视觉组件"),
@@ -159,12 +163,100 @@ const labs = await evaluate(`(() => {
  };
 })()`);

+const artifacts = await evaluate(`(() => {
+  const root = document.querySelector("[data-k3-artifact-lab]");
+  const panel = () => root.querySelector("[data-artifact-panel]:not([hidden])").dataset.artifactPanel;
+  const text = (selector) => root.querySelector(selector).textContent.trim();
+  const input = (selector, value) => {
+    const node = root.querySelector(selector);
+    node.value = value;
+    node.dispatchEvent(new Event("input", { bubbles: true }));
+  };
+
+  const initial = {
+    panel: panel(),
+    layer: text("[data-layer-number]"),
+    attention: text("[data-layer-attention]"),
+    ffn: text("[data-layer-ffn]"),
+    block: text("[data-layer-block]"),
+  };
+  input("[data-layer-slider]", "93");
+  const terminal = {
+    layer: text("[data-layer-number]"),
+    attention: text("[data-layer-attention]"),
+    ffn: text("[data-layer-ffn]"),
+    copy: text("[data-layer-special]"),
+  };
+
+  root.querySelector('[data-artifact-tab="tensors"]').click();
+  const tensors = {
+    panel: panel(),
+    groups: root.querySelectorAll("[data-tensor-tab]").length,
+    expertRows: root.querySelector('[data-tensor-panel="expert"]').querySelectorAll(":scope > div").length,
+    entries: root.textContent.includes("497,220"),
+    share: root.textContent.includes("92.67%"),
+  };
+  root.querySelector('[data-tensor-tab="mla"]').click();
+  const mla = {
+    visible: !root.querySelector('[data-tensor-panel="mla"]').hidden,
+    rows: root.querySelector('[data-tensor-panel="mla"]').querySelectorAll(":scope > div").length,
+    has576: root.querySelector('[data-tensor-panel="mla"]').textContent.includes("576 × 7168"),
+  };
+
+  root.querySelector('[data-artifact-tab="parameters"]').click();
+  const parameterInitial = {
+    panel: panel(),
+    shape: text("[data-parameter-shape]"),
+    conflict: root.textContent.includes("A_log [128]") && root.textContent.includes("A_log [H] = [96]"),
+  };
+  input("[data-parameter-select]", "dt");
+  const parameterChanged = {
+    shape: text("[data-parameter-shape]"),
+    count: text("[data-parameter-count]"),
+  };
+
+  root.querySelector('[data-artifact-tab="reproduction"]').click();
+  const reproductionInitial = {
+    panel: panel(),
+    flash: text("[data-benchmark-flash]"),
+    fla: text("[data-benchmark-fla]"),
+    speedup: text("[data-benchmark-speedup]"),
+    cv: text("[data-router-cv]"),
+    zero: text("[data-router-zero]"),
+  };
+  input("[data-benchmark-device]", "gb200");
+  input("[data-benchmark-case]", "Varlen, \\\`seq_lens\\\`=\\\`1024 x 8\\\`");
+  input("[data-router-mode]", "bias");
+  const reproductionChanged = {
+    flash: text("[data-benchmark-flash]"),
+    speedup: text("[data-benchmark-speedup]"),
+    cv: text("[data-router-cv]"),
+    zero: text("[data-router-zero]"),
+  };
+
+  const first = root.querySelector('[data-artifact-tab="layers"]');
+  first.focus();
+  first.dispatchEvent(new KeyboardEvent("keydown", { key: "ArrowRight", bubbles: true }));
+  return {
+    initial, terminal, tensors, mla, parameterInitial, parameterChanged,
+    reproductionInitial, reproductionChanged,
+    keyboardSelected: root.querySelector('[data-artifact-tab][aria-selected="true"]').dataset.artifactTab,
+    keyboardVisible: panel(),
+  };
+})()`);
+
 await evaluate(`(() => {
  document.querySelector("[data-k3-lab]").scrollIntoView({ block: "start", behavior: "instant" });
  window.scrollBy(0, -82);
 })()`);
 await pause(180);
 await screenshot("/tmp/llm-atlas-k3-lab-desktop.png");
+await evaluate(`(() => {
+  document.querySelector("[data-k3-artifact-lab]").scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -82);
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-artifact-desktop.png");

 await command("Emulation.setDeviceMetricsOverride", {
  width: 390,
@@ -183,8 +275,10 @@ const mobile = await evaluate(`(() => {
    menuVisible: getComputedStyle(toggle).display !== "none",
    menuOpen: toggle.getAttribute("aria-expanded"),
    tabs: root.querySelectorAll("[data-k3-tab]").length,
+    artifactTabs: document.querySelectorAll("[data-artifact-tab]").length,
+    artifactLayers: document.querySelectorAll("[data-layer-cell]").length,
    offenders: [...document.querySelectorAll("body *")]
-      .filter((node) => !node.closest(".paper-chain, .spec-table-wrap, .cache-strip, .architecture-explorer, [data-k3-lab]"))
+      .filter((node) => !node.closest(".paper-chain, .spec-table-wrap, .cache-strip, .architecture-explorer, [data-k3-lab], [data-k3-artifact-lab]"))
      .filter((node) => node.getBoundingClientRect().right > document.documentElement.clientWidth + 1)
      .slice(0, 15)
      .map((node) => ({
@@ -201,17 +295,24 @@ await evaluate(`(() => {
 })()`);
 await pause(180);
 await screenshot("/tmp/llm-atlas-k3-mobile.png");
+await evaluate(`(() => {
+  document.querySelector("[data-k3-artifact-lab]").scrollIntoView({ block: "start", behavior: "instant" });
+  window.scrollBy(0, -64);
+})()`);
+await pause(180);
+await screenshot("/tmp/llm-atlas-k3-artifact-mobile.png");

-const report = { overview, labs, mobile, exceptions };
+const report = { overview, labs, artifacts, mobile, exceptions };
 console.log(JSON.stringify(report, null, 2));

 const numeric = (text) => Number.parseFloat(text.replaceAll(",", "").replace("−", "-"));
 const failures = [];
 if (!overview.title.includes("因果环节")) failures.push("K3 二轮标题异常");
-if (overview.sections !== 31 || overview.tocLinks !== 31) failures.push("30 个编号专题加阅读链的目录结构异常");
+if (overview.sections !== 32 || overview.tocLinks !== 32) failures.push("31 个编号专题加阅读链的目录结构异常");
 if (overview.ledgers !== 32 || overview.reportMap !== 9) failures.push("32 张问题账或报告地图异常");
 if (overview.figureAtlas !== 21 || overview.paperLinks !== 100 || overview.paperGroups < 12) failures.push("图表审计或 100 节点阅读链异常");
 if (overview.labTabs !== 8 || overview.labPanels !== 8) failures.push("八联实验结构异常");
+if (overview.artifactTabs !== 4 || overview.artifactPanels !== 4 || overview.artifactLayers !== 93 || !overview.artifactMismatch) failures.push("开放工件四视图、93 层条带或形状冲突异常");
 if (!overview.nativeVisionCorrected || overview.staleVisionClaim) failures.push("原生多模态纠错未生效或旧错误残留");
 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 (labs.memoryInitial.panel !== "memory" || numeric(labs.memoryInitial.additiveError) <= numeric(labs.memoryInitial.deltaError)) failures.push("Delta memory 初始递推异常");
@@ -227,7 +328,16 @@ if (!labs.rlOver.budget.includes("reward 改为 −1")) failures.push("Reasoning
 if (numeric(labs.cacheInitial.hit) !== 2560 || !labs.cacheInitial.recompute.includes("256")) failures.push("Hybrid prefix cache 默认命中异常");
 if (numeric(labs.cacheSparse.hit) >= numeric(labs.cacheInitial.hit) || numeric(labs.cacheSparse.recompute) <= numeric(labs.cacheInitial.recompute)) failures.push("稀疏 KDA checkpoint 未降低 joint hit");
 if (labs.keyboardSelected !== "decay" || labs.keyboardVisible !== "decay") failures.push("实验键盘 tab 导航异常");
-if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 8) failures.push("移动端导航或实验异常");
+if (artifacts.initial.panel !== "layers" || numeric(artifacts.initial.layer) !== 1 || artifacts.initial.attention !== "KDA" || artifacts.initial.ffn !== "DENSE") failures.push("开放工件初始层视图异常");
+if (numeric(artifacts.terminal.layer) !== 93 || artifacts.terminal.attention !== "MLA" || artifacts.terminal.ffn !== "MOE" || !artifacts.terminal.copy.includes("L92 / L93")) failures.push("K3 末层真实配置条带异常");
+if (artifacts.tensors.panel !== "tensors" || artifacts.tensors.groups !== 3 || artifacts.tensors.expertRows !== 6 || !artifacts.tensors.entries || !artifacts.tensors.share) failures.push("checkpoint tensor anatomy 异常");
+if (!artifacts.mla.visible || artifacts.mla.rows !== 5 || !artifacts.mla.has576) failures.push("MLA header shape 视图异常");
+if (artifacts.parameterInitial.panel !== "parameters" || artifacts.parameterInitial.shape !== "[128] F32" || !artifacts.parameterInitial.conflict) failures.push("A_log 工件冲突审计异常");
+if (artifacts.parameterChanged.shape !== "[96,128] F32" || !artifacts.parameterChanged.count.includes("12,288")) failures.push("真实 dt_bias 参数切换异常");
+if (artifacts.reproductionInitial.panel !== "reproduction" || numeric(artifacts.reproductionInitial.speedup) !== 1.85 || numeric(artifacts.reproductionInitial.cv) < 2) failures.push("FlashKDA H20 或 router 初始探针异常");
+if (numeric(artifacts.reproductionChanged.speedup) !== 3.27 || numeric(artifacts.reproductionChanged.flash) !== 0.7064 || numeric(artifacts.reproductionChanged.cv) <= numeric(artifacts.reproductionInitial.cv) || numeric(artifacts.reproductionChanged.zero) <= numeric(artifacts.reproductionInitial.zero)) failures.push("GB200 benchmark 或 synthetic router counterexample 未更新");
+if (artifacts.keyboardSelected !== "tensors" || artifacts.keyboardVisible !== "tensors") failures.push("开放工件键盘 tab 导航异常");
+if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 8 || mobile.artifactTabs !== 4 || mobile.artifactLayers !== 93) 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(" | ")}`);