diff --git a/PROGRESS.md b/PROGRESS.md index 7404c86..b73e42e 100644 --- a/PROGRESS.md +++ b/PROGRESS.md @@ -296,7 +296,7 @@ - [x] 全局切断 64 个 depth mixer 与 output mixer 的 softmax/query/key source-gradient paths 后,contrast / peak 平均相对“降幅”为 `−2.00% / −0.84%`,三 seed 均略微上升,不支持材料级降低。将 learned value-backward coefficients 换成 `1/N` 后,contrast / peak 平均下降 `70.20% / 37.03%`,三 seed 都超过 20% 阈值,peak layer 全部移到 layer 2。 - [x] mixer 观察关联与反向干预分层:layers 19–28 的 MLP latest weight 对 normalized gradient Pearson / Spearman 为 `.690 / .693`,MLP entropy 为 `−.636 / −.640`;相关性只提供候选机制,全局干预只支持 value-route sensitivity,不冒充局部 mixer attribution。 - [x] K3 Round 06 五视图实验室完成:训练轨迹、六位置谱、12 格 reduction 稳健性、same-forward 三规则干预与 mixer 散点/证据阶梯可交互;protocol、scoping、audit、runner、analyzer、raw/aggregate/compact/reproduction 全部进入公开树。 -- [x] Round 06 本地闸门通过:97 个 Astro 文件零诊断,21 个页面、1,151 个站内引用、12 个跨页锚点零失败;Round 04/05/06 三套冻结数据、三套专项与 K3 全量真实 Chrome 回归通过,桌面/390px 移动端零文档级溢出、零 offender、零运行时异常。 +- [x] Round 06 本地闸门通过:97 个 Astro 文件零诊断,21 个页面、1,151 个站内引用、12 个跨页锚点零失败;Round 04/05/06 三套冻结数据、三套专项、K3 全量与全站 22 套真实 Chrome 回归通过,桌面/390px 移动端零文档级溢出、零 offender、零运行时异常;首页首发卡与陈旧跨页断言同步到 Round 06。 ## 正在进行 diff --git a/scripts/check-agents-browser.mjs b/scripts/check-agents-browser.mjs index e650528..fc3c25c 100644 --- a/scripts/check-agents-browser.mjs +++ b/scripts/check-agents-browser.mjs @@ -228,7 +228,7 @@ if (numeric(reliability.initial.passAt) <= numeric(reliability.k2.passAt) || num if (reliability.nonIdempotent.sideRisk === "LOW") failures.push("非幂等写操作风险没有提升"); if (numeric(rl.wait.utilization) >= numeric(rl.full.utilization) || numeric(rl.wait.lostWork) <= numeric(rl.full.lostWork)) failures.push("wait-all 长尾/重算方向异常"); if (!rl.wait.takeaway.includes("wait-all") || rl.keyboardSelected !== "rl" || rl.keyboardVisible !== "rl") failures.push("长程 RL 解释或键盘导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasAgentFilter || papers.agentVisible < 52) failures.push("论文库 Agent 标签或论文总数异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`); diff --git a/scripts/check-alignment-browser.mjs b/scripts/check-alignment-browser.mjs index b533846..2191823 100644 --- a/scripts/check-alignment-browser.mjs +++ b/scripts/check-alignment-browser.mjs @@ -226,7 +226,7 @@ if (!update.steps[0].includes("Fixed preference")) failures.push("DPO 更新流 if (!recipe.family.includes("Multi-effort") || !recipe.regime.includes("9 RL experts") || !recipe.constraints.includes("verbosity")) failures.push("K3 配方合同异常"); if (!recipe.path.some((step) => step.includes("3 domains × 3 efforts")) || !recipe.path.some((step) => step.includes("MOPD"))) failures.push("K3 配方路径异常"); if (recipe.keyboardSelected !== "recipe" || recipe.keyboardVisible !== "recipe") failures.push("实验 tab 键盘导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasAlignmentFilter || papers.alignmentVisible < 35) failures.push("论文库后训练标签或论文总数异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`); diff --git a/scripts/check-data-browser.mjs b/scripts/check-data-browser.mjs index 2396fdf..b8d1b30 100644 --- a/scripts/check-data-browser.mjs +++ b/scripts/check-data-browser.mjs @@ -234,7 +234,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出"); if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`); if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") { +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") { failures.push("首页 Transformer 新章入口异常"); } if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`); diff --git a/scripts/check-deepseek-browser.mjs b/scripts/check-deepseek-browser.mjs index fae74eb..b2793f5 100644 --- a/scripts/check-deepseek-browser.mjs +++ b/scripts/check-deepseek-browser.mjs @@ -1318,7 +1318,7 @@ if (completionDepth.tasks.panel !== "tasks" || completionDepth.tasks.mathCards ! if (completionDepth.hidden.panel !== "hidden" || completionDepth.hidden.stages !== 29 || completionDepth.hidden.selected !== "layer_07" || completionDepth.hidden.points !== 29 || completionDepth.hidden.exact === "1,537 / 1,537" || numeric(completionDepth.hidden.relative) <= 0) failures.push("29 阶段隐藏状态曲线或交互异常"); if (completionDepth.router.panel !== "router" || completionDepth.router.layers !== 26 || completionDepth.router.selected !== "layer 24" || completionDepth.router.points !== 26 || !completionDepth.router.ordered.includes("%") || !completionDepth.router.setExact.includes("%") || numeric(completionDepth.router.tv) <= 0 || completionDepth.router.reproCards !== 4 || completionDepth.router.links !== 4) failures.push("26 层 MoE 路由曲线或复跑证据异常"); if (completionDepth.keyboardSelected !== "tasks" || completionDepth.keyboardVisible !== "tasks") failures.push("完成度与全深度实验键盘 tab 导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/" || home.paperCount !== "486") failures.push("首页 DeepSeek 首发入口或论文数异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/" || home.paperCount !== "486") failures.push("首页 K3 首发入口或论文数异常"); if (papers.total !== 486 || !papers.hasFilter || papers.visible < 20 || !papers.hasCoder || !papers.hasEngram) failures.push("论文库 DeepSeek 聚光异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4 || mobile.artifactTabs !== 13 || mobile.behaviorTabs !== 4 || mobile.behaviorSources !== 16 || mobile.behaviorEdges !== 10 || mobile.behaviorDeviceCells !== 29 || mobile.completionDepthTabs !== 4 || mobile.completionDepthHiddenStages !== 29 || mobile.completionDepthRouterLayers !== 26 || mobile.artifactHeatCells !== 64 || mobile.corpusCohorts !== 3 || mobile.lengthDeltaCards !== 4 || mobile.templateLayers !== 6 || mobile.templateScopes !== 2 || mobile.templateModes !== 2 || mobile.templateDomainCards !== 4 || mobile.templateDepthCells !== 24 || mobile.historyLayers !== 6 || mobile.historyScopes !== 2 || mobile.historyModes !== 2 || mobile.historyEffects !== 3 || mobile.historyDomainCards !== 4 || mobile.historyDepthCells !== 24 || mobile.distanceLayers !== 6 || mobile.distanceScopes !== 2 || mobile.distanceModes !== 2 || mobile.distanceContrasts !== 2 || mobile.distanceDomainCards !== 4 || mobile.distanceDepthCells !== 24 || mobile.boundaryLayers !== 6 || mobile.boundaryScopes !== 2 || mobile.boundaryModes !== 2 || mobile.boundaryContrasts !== 3 || mobile.boundaryTokenCards !== 4 || mobile.boundaryDomainCards !== 4 || mobile.boundaryDepthCells !== 24 || mobile.roleLayers !== 6 || mobile.roleScopes !== 2 || mobile.roleModes !== 2 || mobile.roleContrasts !== 3 || mobile.roleLevelCards !== 4 || mobile.roleDomainCards !== 4 || mobile.roleDepthCells !== 24 || mobile.specialLayers !== 6 || mobile.specialScopes !== 2 || mobile.specialModes !== 2 || mobile.specialContrasts !== 4 || mobile.specialTokenCards !== 4 || mobile.specialDomainCards !== 4 || mobile.specialDepthCells !== 24 || mobile.roleBlockLayers !== 6 || mobile.roleBlockScopes !== 2 || mobile.roleBlockModes !== 2 || mobile.roleBlockEffects !== 3 || mobile.roleBlockMatrixCards !== 4 || mobile.roleBlockDomainCards !== 4 || mobile.roleBlockDepthCells !== 24) 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:${JSON.stringify(mobile.offenders)}`); diff --git a/scripts/check-evaluation-browser.mjs b/scripts/check-evaluation-browser.mjs index 5ec00bc..c48732a 100644 --- a/scripts/check-evaluation-browser.mjs +++ b/scripts/check-evaluation-browser.mjs @@ -277,7 +277,7 @@ if (numeric(system.initial.success) <= numeric(system.initial.model) || numeric( if (numeric(system.cheap.success) >= numeric(system.initial.success) || numeric(system.cheap.cost) !== 4) failures.push("低预算没有降低成功率 / 成本"); if (numeric(system.locked.unsafe) !== 0 || numeric(system.locked.overrefusal) <= numeric(system.initial.overrefusal)) failures.push("安全壳没有展现危险服从 / 过拒权衡"); if (system.keyboardSelected !== "judge" || system.keyboardVisible !== "judge") failures.push("实验键盘 tab 导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || home.topicCount !== "17" || papers.total !== 486 || !papers.hasFilter || papers.visible < 80) failures.push("首页 / 论文库评测索引异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`); diff --git a/scripts/check-inference-serving-browser.mjs b/scripts/check-inference-serving-browser.mjs index 55b1398..fe8c62f 100644 --- a/scripts/check-inference-serving-browser.mjs +++ b/scripts/check-inference-serving-browser.mjs @@ -264,7 +264,7 @@ if (!fleet.k3.avoided.includes("320K") || fleet.k3.shortSlo !== "PROTECTED") fai if (!fleet.failed.state.includes("SECONDARY RE-PREFILL") || !fleet.failed.recompute.includes("FAILED PRIMARY")) failures.push("缓存故障没有触发原子失效后的重算"); if (fleet.bursty.shortSlo !== "VIOLATED") failures.push("平均并发阈值没有暴露长请求突发"); if (fleet.keyboardSelected !== "phase" || fleet.keyboardVisible !== "phase") failures.push("实验键盘 tab 导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasFilter || papers.visible !== 46) failures.push("论文库推理服务标签或总数异常"); 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:${JSON.stringify(mobile.offenders)}`); diff --git a/scripts/check-multimodal-browser.mjs b/scripts/check-multimodal-browser.mjs index 38a3bd0..6fd3a2a 100644 --- a/scripts/check-multimodal-browser.mjs +++ b/scripts/check-multimodal-browser.mjs @@ -246,7 +246,7 @@ if (ocr.unreported.status !== "OUT OF EVIDENCE" || ocr.unreported.accuracy !== " if (loop.toolsStart.state !== "OPEN" || loop.toolsEnd.state !== "VERIFIED" || loop.toolsEnd.evidence !== "97%" || loop.toolsEnd.tools !== "3") failures.push("vision-in-the-loop 终局异常"); if (loop.cotEnd.state !== "FAILED" || !loop.cotEnd.takeaway.includes("不能凭空增加")) failures.push("文字 CoT 与新观察没有分开"); if (loop.keyboardSelected !== "connector" || loop.keyboardVisible !== "connector") failures.push("实验键盘 tab 导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || papers.total !== 486 || !papers.hasFilter || papers.multimodalVisible < 59) failures.push("论文库多模态标签或总数异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (mobile.offenders.length) failures.push(`移动端越界元素:${JSON.stringify(mobile.offenders)}`); diff --git a/scripts/check-numerics-browser.mjs b/scripts/check-numerics-browser.mjs index 7c61ab0..f32dc00 100644 --- a/scripts/check-numerics-browser.mjs +++ b/scripts/check-numerics-browser.mjs @@ -277,7 +277,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出"); if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`); if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") { +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") { failures.push("首页 Transformer 新章入口异常"); } if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`); diff --git a/scripts/check-reasoning-browser.mjs b/scripts/check-reasoning-browser.mjs index ef8beff..80e1f21 100644 --- a/scripts/check-reasoning-browser.mjs +++ b/scripts/check-reasoning-browser.mjs @@ -289,7 +289,7 @@ if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentO } if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`); if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要")) failures.push("首页评测新章入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有")) failures.push("首页 K3 首发入口异常"); if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`); socket.close(); diff --git a/scripts/check-representation-browser.mjs b/scripts/check-representation-browser.mjs index 57db74c..b5f6cad 100644 --- a/scripts/check-representation-browser.mjs +++ b/scripts/check-representation-browser.mjs @@ -288,7 +288,7 @@ if (numeric(residual.attnres.states) !== 9 || !residual.attnres.routeExplain.inc if (!residual.clamp.activation.includes("V4") || !residual.clamp.bound.includes("100")) failures.push("DeepSeek-V4 clamp 展示异常"); if (!residual.situ.activation.includes("KIMI") || !residual.situ.bound.includes("100")) failures.push("K3 SiTU 上界展示异常"); if (residual.keyboardSelected !== "position" || residual.keyboardVisible !== "position") failures.push("实验键盘 tab 导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页表示新章入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || home.topicCount !== "17" || papers.total !== 486 || !papers.hasFilter || papers.visible < 30) failures.push("首页 / 论文库表示索引异常"); 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:${JSON.stringify(mobile.offenders)}`); diff --git a/scripts/check-scaling-browser.mjs b/scripts/check-scaling-browser.mjs index 9541ebe..79742c0 100644 --- a/scripts/check-scaling-browser.mjs +++ b/scripts/check-scaling-browser.mjs @@ -273,7 +273,7 @@ if (layout.navLinks !== 20 || mobile.mobileLinks !== 20 || home.navLinks !== 20) if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出"); if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`); if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") { +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") { failures.push("首页 Transformer 新章入口异常"); } if (home.paperCount !== "486") failures.push(`首页论文总数异常:${home.paperCount}`); diff --git a/scripts/check-training-systems-browser.mjs b/scripts/check-training-systems-browser.mjs index 002fe69..b32dcb9 100644 --- a/scripts/check-training-systems-browser.mjs +++ b/scripts/check-training-systems-browser.mjs @@ -233,7 +233,7 @@ if (layout.articleSections !== 16 || layout.paperLinks !== 37 || layout.labTabs if (layout.documentOverflow > 0 || mobile.documentOverflow > 0 || home.documentOverflow > 0) failures.push("页面存在横向溢出"); if (layout.navGap < 0) failures.push(`桌面导航碰撞:${layout.navGap}px`); if (!mobile.menuVisible || mobile.menuOpen !== "true") failures.push("移动端菜单不可用"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要")) failures.push("首页评测新章入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有")) failures.push("首页 K3 首发入口异常"); if (exceptions.length) failures.push(`浏览器脚本异常:${exceptions.join("; ")}`); socket.close(); diff --git a/scripts/check-transformer-browser.mjs b/scripts/check-transformer-browser.mjs index 799fc7f..0931ec5 100644 --- a/scripts/check-transformer-browser.mjs +++ b/scripts/check-transformer-browser.mjs @@ -236,7 +236,7 @@ if (block.family.trim() !== "Hybrid MoE" || !block.kv.includes("3 KDA : 1 Gated if (!block.path.some((step) => step.includes("KDA × 3")) || !block.note.includes("AttnRes")) failures.push("K3 Block 路径异常"); if (block.context.trim() !== "128K" || numeric(block.mha) !== 400 || numeric(block.kda) !== 1) failures.push("KV 成本缩放异常"); if (block.keyboardSelected !== "block" || block.keyboardVisible !== "block") failures.push("实验 tab 键盘导航异常"); -if (home.releaseCards !== 17 || !home.firstRelease.includes("47 页不再压成摘要") || home.firstHref !== "/k3/") failures.push("首页评测首发入口异常"); +if (home.releaseCards !== 17 || !home.firstRelease.includes("尖峰不是出生时就有") || home.firstHref !== "/k3/") failures.push("首页 K3 首发入口异常"); if (home.paperCount !== "486" || papers.total !== 486 || papers.transformerVisible < 30) failures.push("论文库或首页论文数量异常"); if (!mobile.menuVisible || mobile.menuOpen !== "true" || mobile.tabs !== 4) failures.push("移动端导航或实验异常"); if (exceptions.length) failures.push(`浏览器异常:${exceptions.join(" | ")}`); diff --git a/src/pages/index.astro b/src/pages/index.astro index 1565649..177897c 100644 --- a/src/pages/index.astro +++ b/src/pages/index.astro @@ -128,20 +128,20 @@ const paths = [
-

NEW / K3 ROUND 04 ATTENTION RESIDUALS · PREREGISTERED PROBE

-

真实 K3 权重仍有冲突:先把一个可证伪的深度路由问题完整做完

+

NEW / K3 ROUND 06 SPIKE TRAJECTORY · SAME-FORWARD BACKWARD PATH

+

尖峰不是出生时就有:它在训练中形成,并对 value 路径敏感

- 不裁剪 A_log [128] 冒充 96-head K3 forward;冻结相同主干、初始化、数据窗口和预算, - 从零训练 Baseline / Full / Block 共 9 个 2,000-step 格。两种 AttnRes 的三 seed BPC - 配对方向都为负,但梯度均匀性指标没有复现论文叙述;支持与反证在同一实验室展示。 + 严格复用 Round 05 的 depth-32 Block 正式格,追踪六个训练时点、六个张量位置与四种 + reduction。layer 21–25 的尖峰在 step 500 后形成;全局 uniform value-backward + 让 contrast 平均下降 70.2%,但只判为反向路径敏感性,不冒充因果贡献或训练变体。

-
REPORT
16 Figures · 5 Tables
-
GRID
3 structures × 3 seeds
-
REPLAY
2,000 steps · 8/8 exact
+
FORMAL
3 seeds × 8,000 steps
+
ROBUST
4 reductions · 12/12
+
REPLAY
16 frozen groups exact
- +