superlab 0.1.26 → 0.1.28

package/README.md

@@ -246,6 +246,7 @@ This installer also writes `.lab/config/workflow.json`, which is the global cont
 - `figures_root`
 - `deliverables_root`
 - `paper_template_root`
+- `paper_language_finalization_decision`
 
 Stages should follow that file rather than guess language locally.
 
@@ -325,6 +326,8 @@ Internal writing-control artifacts stay under:
 If `paper_template_root` is configured, `/lab:write` should inspect that template directory first and align drafting to it.
 If no template is configured, the first manuscript-writing round should ask once whether to continue with the managed default LaTeX scaffold or attach a template directory first.
 If the user approves the default scaffold, persist that choice in `.lab/config/workflow.json` and stop asking on ordinary rounds.
+Ordinary manuscript drafting rounds should follow `workflow_language`.
+If `workflow_language` and `paper_language` differ, the first final-draft or export round should ask once whether to keep the draft language or convert the final manuscript to `paper_language`, then persist that decision.
 At the final export or final-draft boundary, if the project is still on the default scaffold and no attached template exists, ask one final reminder question before finalizing.
 For final-draft or export rounds, `/lab:write` should materialize real LaTeX tables, figure placeholders with figure intent, a non-empty `references.bib`, and pass `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper` before stopping.
 

package/README.zh-CN.md

@@ -244,6 +244,7 @@ superlab init --lang en
 - `figures_root`
 - `deliverables_root`
 - `paper_template_root`
+- `paper_language_finalization_decision`
 
 后续 stage 应该按这个配置决定语言和论文格式，而不是各模板自己猜。
 
@@ -310,6 +311,8 @@ Codex 和 Claude 的命令入口不一样：
 如果配置了 `paper_template_root`，`/lab:write` 应先检查该模板目录并按其结构写作。
 如果没有配置模板，第一次进入论文 `.tex` 写作时应先追问一次：继续使用内置默认 LaTeX scaffold，还是先接入模板目录。
 如果用户确认先用默认 scaffold，就把这个决定持久化到 `.lab/config/workflow.json`，后续普通轮次不再重复追问。
+普通论文起草轮次应先跟随 `workflow_language`。
+如果 `workflow_language` 和 `paper_language` 不一致，则在第一次进入最终定稿或导出轮次时追问一次：保持当前草稿语言，还是把最终稿转换成 `paper_language`，并把这个决定持久化。
 但在最终导出或最终定稿节点，如果项目仍在使用默认 scaffold 且没有接入模板，应再提醒一次，给用户最后切换模板的机会。
 在最终定稿或导出轮次里，`/lab:write` 还应物化真正的 LaTeX 表格、带图意图的 figure placeholders、非空的 `references.bib`，并在停止前通过 `.lab/.managed/scripts/validate_manuscript_delivery.py --paper-dir <deliverables_root>/paper`。
 

package/bin/superlab.cjs

@@ -677,6 +677,17 @@ function validateWorkflowConfig(config) {
   ) {
     issues.push("invalid paper_template_final_reminder_acknowledged");
   }
+  const validLanguageFinalizationDecisions = new Set([
+    "unconfirmed",
+    "keep-workflow-language",
+    "convert-to-paper-language",
+  ]);
+  if (
+    config.paper_language_finalization_decision !== undefined &&
+    !validLanguageFinalizationDecisions.has(config.paper_language_finalization_decision)
+  ) {
+    issues.push("invalid paper_language_finalization_decision");
+  }
   if (
     typeof config.paper_template_root === "string" &&
     config.paper_template_root.trim() !== "" &&

package/lib/auto_contracts.cjs

@@ -42,7 +42,7 @@ const PROMOTION_CANONICAL_FILES = [
   path.join(".lab", "context", "data-decisions.md"),
   path.join(".lab", "context", "decisions.md"),
   path.join(".lab", "context", "state.md"),
-  path.join(".lab", "context", "session-brief.md"),
+  path.join(".lab", "context", "workflow-state.md"),
 ];
 
 function resolveFrozenCoreEntries(rawValue) {

package/lib/auto_runner.cjs

@@ -433,7 +433,7 @@ async function startAutoMode({ targetDir, now = new Date() }) {
       ".lab/context/data-decisions.md",
       ".lab/context/decisions.md",
       ".lab/context/state.md",
-      ".lab/context/session-brief.md",
+      ".lab/context/workflow-state.md",
     ]);
     await runCommandWithPolling({
       targetDir,

package/lib/context.cjs

@@ -983,7 +983,7 @@ function renderResearchState(lang, data) {
 
 ## 当前研究主线
 
-- Current research focus: ${data.immediateAction || data.direction || "待补充"}
+- Current research focus: ${data.direction || "待补充"}
 - Primary metric: ${data.evalPrimaryMetrics || data.threshold || "待补充"}
 - Dataset or benchmark scope: ${data.datasetPackage || data.benchmarkRole || "待补充"}
 
@@ -991,7 +991,7 @@ function renderResearchState(lang, data) {
 
 - Hard constraints: ${data.boundary || "待补充"}
 - Claim boundary: ${data.evalClaimBoundary || "待补充"}
-- Conditions that require reopening the direction: ${data.humanDecision || "待补充"}
+- Conditions that require reopening the direction: ${data.question || "待补充"}
 `;
   }
 
@@ -1011,7 +1011,7 @@ function renderResearchState(lang, data) {
 
 ## Active Research Track
 
-- Current research focus: ${data.immediateAction || data.direction || "TBD"}
+- Current research focus: ${data.direction || "TBD"}
 - Primary metric: ${data.evalPrimaryMetrics || data.threshold || "TBD"}
 - Dataset or benchmark scope: ${data.datasetPackage || data.benchmarkRole || "TBD"}
 
@@ -1019,7 +1019,7 @@ function renderResearchState(lang, data) {
 
 - Hard constraints: ${data.boundary || "TBD"}
 - Claim boundary: ${data.evalClaimBoundary || "TBD"}
-- Conditions that require reopening the direction: ${data.humanDecision || "TBD"}
+- Conditions that require reopening the direction: ${data.question || "TBD"}
 `;
 }
 
@@ -1078,74 +1078,36 @@ function renderSummary(lang, data) {
 - Mission: ${data.problem || "待补充"}
 - Approved direction: ${data.direction || "待补充"}
 - Active stage: ${data.stage || "待补充"}
+- Current objective: ${data.workflowObjective || "待补充"}
 - Auto mode: ${data.autoStatus || "未启用"}
 - Auto objective: ${data.autoObjective || "待补充"}
-- Auto rung: ${data.autoCurrentRung || "待补充"}
-- Auto watch target: ${data.autoWatchTarget || "待补充"}
 - Auto decision: ${data.autoDecision || "待补充"}
-- Auto terminal goal: ${joinNonEmpty([data.autoGoalType, data.autoGoalTarget], " | ") || "待补充"}
-- Auto goal reached: ${data.autoGoalReached || "待补充"}
-- Auto stop reason: ${data.autoStopReason || "待补充"}
-- Auto final artifact: ${data.autoFinalArtifact || "待补充"}
-- Auto final rung: ${data.autoFinalRung || "待补充"}
 - Collaborator report mode: ${data.reportMode || "待补充"}
 - Canonical context readiness: ${data.reportReadiness || "待补充"}
-- Why this report mode is active: ${data.reportModeReason || "待补充"}
 - Method name: ${data.methodName || "待补充"}
 - Contribution bullets: ${data.contributionBullets || "待补充"}
 - Eval objective: ${data.evalObjective || "待补充"}
 - Primary metrics: ${data.evalPrimaryMetrics || "待补充"}
 - Secondary metrics: ${data.evalSecondaryMetrics || "待补充"}
-- Required terminal evidence: ${data.evalRequiredTerminalEvidence || "待补充"}
-- Table plan: ${data.evalTablePlan || "待补充"}
-- Metric glossary: ${data.evalMetricGlossary || "待补充"}
-- Background sources: ${data.evalBackgroundSources || "待补充"}
-- Method and baseline source papers: ${data.evalMethodAndBaselineSourcePapers || "待补充"}
-- Method and baseline implementation source: ${data.evalMethodAndBaselineImplementationSource || "待补充"}
-- Metric source papers: ${data.evalMetricSourcePapers || "待补充"}
-- Metric implementation source: ${data.evalMetricImplementationSource || "待补充"}
-- Comparison source papers: ${data.evalComparisonSourcePapers || "待补充"}
-- Comparison implementation source: ${data.evalComparisonImplementationSource || "待补充"}
-- Deviation from original implementation: ${data.evalDeviationFromOriginalImplementation || "待补充"}
-- Evaluation setting semantics: ${data.evalEvaluationSettingSemantics || "待补充"}
-- Visibility and leakage risks: ${data.evalVisibilityAndLeakageRisks || "待补充"}
-- Anchor and label policy: ${data.evalAnchorAndLabelPolicy || "待补充"}
-- Scale and comparability policy: ${data.evalScaleAndComparabilityPolicy || "待补充"}
-- Metric validity checks: ${data.evalMetricValidityChecks || "待补充"}
-- Comparison validity checks: ${data.evalComparisonValidityChecks || "待补充"}
-- Statistical validity checks: ${data.evalStatisticalValidityChecks || "待补充"}
-- Claim boundary: ${data.evalClaimBoundary || "待补充"}
-- Integrity self-check: ${data.evalIntegritySelfCheck || "待补充"}
-- Anomaly signals: ${data.evalAnomalySignals || "待补充"}
-- Implementation reality checks: ${data.evalImplementationRealityChecks || "待补充"}
-- Alternative explanations considered: ${data.evalAlternativeExplanationsConsidered || "待补充"}
-- Cross-check method: ${data.evalCrossCheckMethod || "待补充"}
-- Best-supported interpretation: ${data.evalBestSupportedInterpretation || "待补充"}
-- Escalation threshold: ${data.evalEscalationThreshold || "待补充"}
-- Experiment ladder: ${data.evalExperimentLadder || "待补充"}
-- Benchmark ladder: ${data.evalBenchmarkLadder || "待补充"}
-- Promotion gate: ${data.evalPromotionGate || "待补充"}
 - Dataset package: ${data.datasetPackage || "待补充"}
-- Dataset years: ${data.datasetYears || "待补充"}
 - Benchmark role: ${data.benchmarkRole || "待补充"}
-- Benchmark rationale: ${data.benchmarkRationale || "待补充"}
 - Comparison suite: ${data.comparisonMethods || "待补充"}
-- Comparison rationale: ${data.comparisonRationale || "待补充"}
-- Comparison evidence: ${data.comparisonEvidence || "待补充"}
-- Source basis: ${data.datasetSources || "待补充"}
-- Representative papers: ${data.datasetPapers || "待补充"}
 
 ## 最强证据
 
 - Claim: ${data.claim || "待补充"}
+- Supporting artifact: ${data.latestArtifactPath || "待补充"}
+- Caveat: ${data.evalClaimBoundary || data.question || "待补充"}
 
 ## 最大风险
 
 - Risk: ${data.risk || "待补充"}
+- Why it matters: ${data.question || data.blocker || "待补充"}
 
 ## 当前缺口
 
-- Open question: ${data.question || "待补充"}
+- Missing evidence: ${data.question || "待补充"}
+- Missing artifact: ${data.nextArtifact || "待补充"}
 `;
   }
 
@@ -1156,74 +1118,36 @@ function renderSummary(lang, data) {
 - Mission: ${data.problem || "TBD"}
 - Approved direction: ${data.direction || "TBD"}
 - Active stage: ${data.stage || "TBD"}
+- Current objective: ${data.workflowObjective || "TBD"}
 - Auto mode: ${data.autoStatus || "inactive"}
 - Auto objective: ${data.autoObjective || "TBD"}
-- Auto rung: ${data.autoCurrentRung || "TBD"}
-- Auto watch target: ${data.autoWatchTarget || "TBD"}
 - Auto decision: ${data.autoDecision || "TBD"}
-- Auto terminal goal: ${joinNonEmpty([data.autoGoalType, data.autoGoalTarget], " | ") || "TBD"}
-- Auto goal reached: ${data.autoGoalReached || "TBD"}
-- Auto stop reason: ${data.autoStopReason || "TBD"}
-- Auto final artifact: ${data.autoFinalArtifact || "TBD"}
-- Auto final rung: ${data.autoFinalRung || "TBD"}
 - Collaborator report mode: ${data.reportMode || "TBD"}
 - Canonical context readiness: ${data.reportReadiness || "TBD"}
-- Why this report mode is active: ${data.reportModeReason || "TBD"}
 - Method name: ${data.methodName || "TBD"}
 - Contribution bullets: ${data.contributionBullets || "TBD"}
 - Eval objective: ${data.evalObjective || "TBD"}
 - Primary metrics: ${data.evalPrimaryMetrics || "TBD"}
 - Secondary metrics: ${data.evalSecondaryMetrics || "TBD"}
-- Required terminal evidence: ${data.evalRequiredTerminalEvidence || "TBD"}
-- Table plan: ${data.evalTablePlan || "TBD"}
-- Metric glossary: ${data.evalMetricGlossary || "TBD"}
-- Background sources: ${data.evalBackgroundSources || "TBD"}
-- Method and baseline source papers: ${data.evalMethodAndBaselineSourcePapers || "TBD"}
-- Method and baseline implementation source: ${data.evalMethodAndBaselineImplementationSource || "TBD"}
-- Metric source papers: ${data.evalMetricSourcePapers || "TBD"}
-- Metric implementation source: ${data.evalMetricImplementationSource || "TBD"}
-- Comparison source papers: ${data.evalComparisonSourcePapers || "TBD"}
-- Comparison implementation source: ${data.evalComparisonImplementationSource || "TBD"}
-- Deviation from original implementation: ${data.evalDeviationFromOriginalImplementation || "TBD"}
-- Evaluation setting semantics: ${data.evalEvaluationSettingSemantics || "TBD"}
-- Visibility and leakage risks: ${data.evalVisibilityAndLeakageRisks || "TBD"}
-- Anchor and label policy: ${data.evalAnchorAndLabelPolicy || "TBD"}
-- Scale and comparability policy: ${data.evalScaleAndComparabilityPolicy || "TBD"}
-- Metric validity checks: ${data.evalMetricValidityChecks || "TBD"}
-- Comparison validity checks: ${data.evalComparisonValidityChecks || "TBD"}
-- Statistical validity checks: ${data.evalStatisticalValidityChecks || "TBD"}
-- Claim boundary: ${data.evalClaimBoundary || "TBD"}
-- Integrity self-check: ${data.evalIntegritySelfCheck || "TBD"}
-- Anomaly signals: ${data.evalAnomalySignals || "TBD"}
-- Implementation reality checks: ${data.evalImplementationRealityChecks || "TBD"}
-- Alternative explanations considered: ${data.evalAlternativeExplanationsConsidered || "TBD"}
-- Cross-check method: ${data.evalCrossCheckMethod || "TBD"}
-- Best-supported interpretation: ${data.evalBestSupportedInterpretation || "TBD"}
-- Escalation threshold: ${data.evalEscalationThreshold || "TBD"}
-- Experiment ladder: ${data.evalExperimentLadder || "TBD"}
-- Benchmark ladder: ${data.evalBenchmarkLadder || "TBD"}
-- Promotion gate: ${data.evalPromotionGate || "TBD"}
 - Dataset package: ${data.datasetPackage || "TBD"}
-- Dataset years: ${data.datasetYears || "TBD"}
 - Benchmark role: ${data.benchmarkRole || "TBD"}
-- Benchmark rationale: ${data.benchmarkRationale || "TBD"}
 - Comparison suite: ${data.comparisonMethods || "TBD"}
-- Comparison rationale: ${data.comparisonRationale || "TBD"}
-- Comparison evidence: ${data.comparisonEvidence || "TBD"}
-- Source basis: ${data.datasetSources || "TBD"}
-- Representative papers: ${data.datasetPapers || "TBD"}
 
 ## Strongest Evidence
 
 - Claim: ${data.claim || "TBD"}
+- Supporting artifact: ${data.latestArtifactPath || "TBD"}
+- Caveat: ${data.evalClaimBoundary || data.question || "TBD"}
 
 ## Largest Risk
 
 - Risk: ${data.risk || "TBD"}
+- Why it matters: ${data.question || data.blocker || "TBD"}
 
 ## Current Gap
 
-- Open question: ${data.question || "TBD"}
+- Missing evidence: ${data.question || "TBD"}
+- Missing artifact: ${data.nextArtifact || "TBD"}
 `;
 }
 
@@ -1236,18 +1160,18 @@ function renderNextAction(lang, data) {
 - Action: ${data.immediateAction || "待补充"}
 - Success signal: ${data.nextArtifact || data.threshold || "待补充"}
 
-## 如果成功
+## 完成后
 
 - Next action: ${data.successFollowup || "继续推进当前阶段"}
 
-## 如果失败
+## 如果卡住
 
 - Fallback action: ${data.blocker ? `先处理阻塞：${data.blocker}` : "回到 review 或 iterate"}
 
-## 是否需要人工决策
+## 升级条件
 
 - Question: ${data.humanDecision || "无"}
-- 为什么会阻塞：${data.blocker || "无"}
+- Escalate when: ${data.blocker || "无明显阻塞"}
 `;
   }
 
@@ -1258,18 +1182,18 @@ function renderNextAction(lang, data) {
 - Action: ${data.immediateAction || "TBD"}
 - Success signal: ${data.nextArtifact || data.threshold || "TBD"}
 
-## If Success
+## After Completion
 
 - Next action: ${data.successFollowup || "Continue the active stage"}
 
-## If Failure
+## If Blocked
 
 - Fallback action: ${data.blocker ? `Resolve blocker: ${data.blocker}` : "Route back to review or iterate"}
 
-## Human Decision Needed
+## Escalation
 
 - Question: ${data.humanDecision || "none"}
-- Why it blocks progress: ${data.blocker || "none"}
+- Escalate when: ${data.blocker || "no major blocker is known"}
 `;
 }
 
@@ -1280,6 +1204,8 @@ function renderSessionBrief(lang, data) {
 ## 当前阶段
 
 - Stage: ${data.stage || "待补充"}
+- Current objective: ${data.workflowObjective || "待补充"}
+- Immediate next action: ${data.immediateAction || "待补充"}
 
 ## 主线任务
 
@@ -1288,63 +1214,15 @@ ${data.problem || "待补充"}
 ## 当前最优路径
 
 - Approved direction: ${data.direction || "待补充"}
-- Why this is the active path: ${data.why || "当前已批准方向"}
+- Strongest supported claim: ${data.claim || "待补充"}
 - Auto mode: ${data.autoStatus || "未启用"}
 - Auto objective: ${data.autoObjective || "待补充"}
-- Auto rung: ${data.autoCurrentRung || "待补充"}
-- Auto watch target: ${data.autoWatchTarget || "待补充"}
 - Auto decision: ${data.autoDecision || "待补充"}
-- Auto terminal goal: ${joinNonEmpty([data.autoGoalType, data.autoGoalTarget], " | ") || "待补充"}
-- Auto goal reached: ${data.autoGoalReached || "待补充"}
-- Auto stop reason: ${data.autoStopReason || "待补充"}
-- Auto final artifact: ${data.autoFinalArtifact || "待补充"}
-- Auto final rung: ${data.autoFinalRung || "待补充"}
 - Collaborator report mode: ${data.reportMode || "待补充"}
 - Canonical context readiness: ${data.reportReadiness || "待补充"}
-- Why this report mode is active: ${data.reportModeReason || "待补充"}
 - Method name: ${data.methodName || "待补充"}
-- Contribution bullets: ${data.contributionBullets || "待补充"}
-- Eval objective: ${data.evalObjective || "待补充"}
 - Primary metrics: ${data.evalPrimaryMetrics || "待补充"}
 - Secondary metrics: ${data.evalSecondaryMetrics || "待补充"}
-- Required terminal evidence: ${data.evalRequiredTerminalEvidence || "待补充"}
-- Table plan: ${data.evalTablePlan || "待补充"}
-- Metric glossary: ${data.evalMetricGlossary || "待补充"}
-- Background sources: ${data.evalBackgroundSources || "待补充"}
-- Method and baseline source papers: ${data.evalMethodAndBaselineSourcePapers || "待补充"}
-- Method and baseline implementation source: ${data.evalMethodAndBaselineImplementationSource || "待补充"}
-- Metric source papers: ${data.evalMetricSourcePapers || "待补充"}
-- Metric implementation source: ${data.evalMetricImplementationSource || "待补充"}
-- Comparison source papers: ${data.evalComparisonSourcePapers || "待补充"}
-- Comparison implementation source: ${data.evalComparisonImplementationSource || "待补充"}
-- Deviation from original implementation: ${data.evalDeviationFromOriginalImplementation || "待补充"}
-- Evaluation setting semantics: ${data.evalEvaluationSettingSemantics || "待补充"}
-- Visibility and leakage risks: ${data.evalVisibilityAndLeakageRisks || "待补充"}
-- Anchor and label policy: ${data.evalAnchorAndLabelPolicy || "待补充"}
-- Scale and comparability policy: ${data.evalScaleAndComparabilityPolicy || "待补充"}
-- Metric validity checks: ${data.evalMetricValidityChecks || "待补充"}
-- Comparison validity checks: ${data.evalComparisonValidityChecks || "待补充"}
-- Statistical validity checks: ${data.evalStatisticalValidityChecks || "待补充"}
-- Claim boundary: ${data.evalClaimBoundary || "待补充"}
-- Integrity self-check: ${data.evalIntegritySelfCheck || "待补充"}
-- Anomaly signals: ${data.evalAnomalySignals || "待补充"}
-- Implementation reality checks: ${data.evalImplementationRealityChecks || "待补充"}
-- Alternative explanations considered: ${data.evalAlternativeExplanationsConsidered || "待补充"}
-- Cross-check method: ${data.evalCrossCheckMethod || "待补充"}
-- Best-supported interpretation: ${data.evalBestSupportedInterpretation || "待补充"}
-- Escalation threshold: ${data.evalEscalationThreshold || "待补充"}
-- Experiment ladder: ${data.evalExperimentLadder || "待补充"}
-- Benchmark ladder: ${data.evalBenchmarkLadder || "待补充"}
-- Promotion gate: ${data.evalPromotionGate || "待补充"}
-- Dataset package: ${data.datasetPackage || "待补充"}
-- Dataset years: ${data.datasetYears || "待补充"}
-- Benchmark role: ${data.benchmarkRole || "待补充"}
-- Benchmark rationale: ${data.benchmarkRationale || "待补充"}
-- Comparison suite: ${data.comparisonMethods || "待补充"}
-- Comparison rationale: ${data.comparisonRationale || "待补充"}
-- Comparison evidence: ${data.comparisonEvidence || "待补充"}
-- Source basis: ${data.datasetSources || "待补充"}
-- Representative papers: ${data.datasetPapers || "待补充"}
 
 ## 主要风险
 
@@ -1369,6 +1247,8 @@ ${data.problem || "待补充"}
 ## Active Stage
 
 - Stage: ${data.stage || "TBD"}
+- Current objective: ${data.workflowObjective || "TBD"}
+- Immediate next action: ${data.immediateAction || "TBD"}
 
 ## Mission
 
@@ -1377,63 +1257,15 @@ ${data.problem || "TBD"}
 ## Best Current Path
 
 - Approved direction: ${data.direction || "TBD"}
-- Why this is the active path: ${data.why || "This is the approved direction"}
+- Strongest supported claim: ${data.claim || "TBD"}
 - Auto mode: ${data.autoStatus || "inactive"}
 - Auto objective: ${data.autoObjective || "TBD"}
-- Auto rung: ${data.autoCurrentRung || "TBD"}
-- Auto watch target: ${data.autoWatchTarget || "TBD"}
 - Auto decision: ${data.autoDecision || "TBD"}
-- Auto terminal goal: ${joinNonEmpty([data.autoGoalType, data.autoGoalTarget], " | ") || "TBD"}
-- Auto goal reached: ${data.autoGoalReached || "TBD"}
-- Auto stop reason: ${data.autoStopReason || "TBD"}
-- Auto final artifact: ${data.autoFinalArtifact || "TBD"}
-- Auto final rung: ${data.autoFinalRung || "TBD"}
 - Collaborator report mode: ${data.reportMode || "TBD"}
 - Canonical context readiness: ${data.reportReadiness || "TBD"}
-- Why this report mode is active: ${data.reportModeReason || "TBD"}
 - Method name: ${data.methodName || "TBD"}
-- Contribution bullets: ${data.contributionBullets || "TBD"}
-- Eval objective: ${data.evalObjective || "TBD"}
 - Primary metrics: ${data.evalPrimaryMetrics || "TBD"}
 - Secondary metrics: ${data.evalSecondaryMetrics || "TBD"}
-- Required terminal evidence: ${data.evalRequiredTerminalEvidence || "TBD"}
-- Table plan: ${data.evalTablePlan || "TBD"}
-- Metric glossary: ${data.evalMetricGlossary || "TBD"}
-- Background sources: ${data.evalBackgroundSources || "TBD"}
-- Method and baseline source papers: ${data.evalMethodAndBaselineSourcePapers || "TBD"}
-- Method and baseline implementation source: ${data.evalMethodAndBaselineImplementationSource || "TBD"}
-- Metric source papers: ${data.evalMetricSourcePapers || "TBD"}
-- Metric implementation source: ${data.evalMetricImplementationSource || "TBD"}
-- Comparison source papers: ${data.evalComparisonSourcePapers || "TBD"}
-- Comparison implementation source: ${data.evalComparisonImplementationSource || "TBD"}
-- Deviation from original implementation: ${data.evalDeviationFromOriginalImplementation || "TBD"}
-- Evaluation setting semantics: ${data.evalEvaluationSettingSemantics || "TBD"}
-- Visibility and leakage risks: ${data.evalVisibilityAndLeakageRisks || "TBD"}
-- Anchor and label policy: ${data.evalAnchorAndLabelPolicy || "TBD"}
-- Scale and comparability policy: ${data.evalScaleAndComparabilityPolicy || "TBD"}
-- Metric validity checks: ${data.evalMetricValidityChecks || "TBD"}
-- Comparison validity checks: ${data.evalComparisonValidityChecks || "TBD"}
-- Statistical validity checks: ${data.evalStatisticalValidityChecks || "TBD"}
-- Claim boundary: ${data.evalClaimBoundary || "TBD"}
-- Integrity self-check: ${data.evalIntegritySelfCheck || "TBD"}
-- Anomaly signals: ${data.evalAnomalySignals || "TBD"}
-- Implementation reality checks: ${data.evalImplementationRealityChecks || "TBD"}
-- Alternative explanations considered: ${data.evalAlternativeExplanationsConsidered || "TBD"}
-- Cross-check method: ${data.evalCrossCheckMethod || "TBD"}
-- Best-supported interpretation: ${data.evalBestSupportedInterpretation || "TBD"}
-- Escalation threshold: ${data.evalEscalationThreshold || "TBD"}
-- Experiment ladder: ${data.evalExperimentLadder || "TBD"}
-- Benchmark ladder: ${data.evalBenchmarkLadder || "TBD"}
-- Promotion gate: ${data.evalPromotionGate || "TBD"}
-- Dataset package: ${data.datasetPackage || "TBD"}
-- Dataset years: ${data.datasetYears || "TBD"}
-- Benchmark role: ${data.benchmarkRole || "TBD"}
-- Benchmark rationale: ${data.benchmarkRationale || "TBD"}
-- Comparison suite: ${data.comparisonMethods || "TBD"}
-- Comparison rationale: ${data.comparisonRationale || "TBD"}
-- Comparison evidence: ${data.comparisonEvidence || "TBD"}
-- Source basis: ${data.datasetSources || "TBD"}
-- Representative papers: ${data.datasetPapers || "TBD"}
 
 ## Main Risk