superlab 0.1.17 → 0.1.18

package/lib/auto_runner.cjs

@@ -270,6 +270,9 @@ async function startAutoMode({ targetDir, now = new Date() }) {
     requiredTerminalEvidence: evalProtocol.requiredTerminalEvidence,
     experimentLadder: evalProtocol.experimentLadder,
     metricGlossary: evalProtocol.metricGlossary,
+    backgroundSources: evalProtocol.backgroundSources,
+    methodAndBaselineSourcePapers: evalProtocol.methodAndBaselineSourcePapers,
+    methodAndBaselineImplementationSource: evalProtocol.methodAndBaselineImplementationSource,
     metricSourcePapers: evalProtocol.metricSourcePapers,
     metricImplementationSource: evalProtocol.metricImplementationSource,
     comparisonSourcePapers: evalProtocol.comparisonSourcePapers,
@@ -755,6 +758,9 @@ function stopAutoMode({ targetDir, now = new Date() }) {
     requiredTerminalEvidence: evalProtocol.requiredTerminalEvidence,
     experimentLadder: evalProtocol.experimentLadder,
     metricGlossary: evalProtocol.metricGlossary,
+    backgroundSources: evalProtocol.backgroundSources,
+    methodAndBaselineSourcePapers: evalProtocol.methodAndBaselineSourcePapers,
+    methodAndBaselineImplementationSource: evalProtocol.methodAndBaselineImplementationSource,
     metricSourcePapers: evalProtocol.metricSourcePapers,
     metricImplementationSource: evalProtocol.metricImplementationSource,
     comparisonSourcePapers: evalProtocol.comparisonSourcePapers,

package/lib/auto_state.cjs

@@ -146,6 +146,9 @@ function renderAutoOutcome(outcome, { lang = "en" } = {}) {
 - 必要终局证据: ${outcome.requiredTerminalEvidence || ""}
 - 实验阶梯: ${outcome.experimentLadder || ""}
 - 指标释义: ${outcome.metricGlossary || ""}
+- 背景来源: ${outcome.backgroundSources || ""}
+- 方法与基线来源论文: ${outcome.methodAndBaselineSourcePapers || ""}
+- 方法与基线实现来源: ${outcome.methodAndBaselineImplementationSource || ""}
 - 指标来源论文: ${outcome.metricSourcePapers || ""}
 - 指标实现来源: ${outcome.metricImplementationSource || ""}
 - 对比方法来源论文: ${outcome.comparisonSourcePapers || ""}
@@ -180,6 +183,9 @@ function renderAutoOutcome(outcome, { lang = "en" } = {}) {
 - Required terminal evidence: ${outcome.requiredTerminalEvidence || ""}
 - Experiment ladder: ${outcome.experimentLadder || ""}
 - Metric glossary: ${outcome.metricGlossary || ""}
+- Background sources: ${outcome.backgroundSources || ""}
+- Method and baseline source papers: ${outcome.methodAndBaselineSourcePapers || ""}
+- Method and baseline implementation source: ${outcome.methodAndBaselineImplementationSource || ""}
 - Metric source papers: ${outcome.metricSourcePapers || ""}
 - Metric implementation source: ${outcome.metricImplementationSource || ""}
 - Comparison source papers: ${outcome.comparisonSourcePapers || ""}

package/lib/context.cjs

@@ -101,6 +101,9 @@ function renderSummary(lang, data) {
 - 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"}
@@ -156,6 +159,9 @@ function renderSummary(lang, data) {
 - 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"}
@@ -266,6 +272,9 @@ ${data.problem || "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"}
@@ -332,6 +341,9 @@ ${data.problem || "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"}
@@ -586,6 +598,9 @@ function buildContextSnapshot(targetDir) {
     evalRequiredTerminalEvidence: evalProtocol.requiredTerminalEvidence,
     evalTablePlan: evalProtocol.tablePlan,
     evalMetricGlossary: evalProtocol.metricGlossary,
+    evalBackgroundSources: evalProtocol.backgroundSources,
+    evalMethodAndBaselineSourcePapers: evalProtocol.methodAndBaselineSourcePapers,
+    evalMethodAndBaselineImplementationSource: evalProtocol.methodAndBaselineImplementationSource,
     evalMetricSourcePapers: evalProtocol.metricSourcePapers,
     evalMetricImplementationSource: evalProtocol.metricImplementationSource,
     evalComparisonSourcePapers: evalProtocol.comparisonSourcePapers,

package/lib/eval_protocol.cjs

@@ -39,6 +39,21 @@ const EVAL_PROTOCOL_FIELDS = [
     key: "metricGlossary",
     labels: ["Metric glossary", "指标释义"],
   },
+  {
+    name: "Background sources",
+    key: "backgroundSources",
+    labels: ["Background sources", "背景来源"],
+  },
+  {
+    name: "Method and baseline source papers",
+    key: "methodAndBaselineSourcePapers",
+    labels: ["Method and baseline source papers", "方法与基线来源论文"],
+  },
+  {
+    name: "Method and baseline implementation source",
+    key: "methodAndBaselineImplementationSource",
+    labels: ["Method and baseline implementation source", "方法与基线实现来源"],
+  },
   {
     name: "Metric source papers",
     key: "metricSourcePapers",

package/lib/i18n.cjs

@@ -710,6 +710,23 @@ const ZH_SKILL_FILES = {
 - 次级指标在衡量什么：
 - 健康度/支持性指标在衡量什么，为什么它们不是主结论：
 
+## 背景来源
+
+- 最关键的背景论文或 benchmark 参考：
+- 为什么这些来源足以锚定当前问题：
+
+## 方法与基线来源
+
+- 我们的方法来源或实现基础：
+- baseline 与 comparison 的来源论文：
+- baseline 与 comparison 的实现来源：
+
+## 指标来源
+
+- 指标来源论文：
+- 指标实现来源：
+- 与原始实现的偏差：
+
 ## 怎么看主表
 
 - Table 1 负责回答什么：
@@ -1949,6 +1966,9 @@ ZH_CONTENT[path.join(".lab", "context", "eval-protocol.md")] = `# 评估协议
 ## 指标释义
 
 - 指标释义：
+- 背景来源：
+- 方法与基线来源论文：
+- 方法与基线实现来源：
 - 指标来源论文：
 - 指标实现来源：
 - 对比方法来源论文：

package/package-assets/shared/lab/.managed/templates/final-report.md

@@ -19,6 +19,23 @@
 - Secondary metric plain-language explanation:
 - Health or support metrics and why they are not the main claim:
 
+## Background Sources
+
+- Most important background papers or benchmark references:
+- Why these are the right background anchors:
+
+## Method and Baseline Sources
+
+- Our method source or implementation basis:
+- Baseline and comparison source papers:
+- Baseline and comparison implementation sources:
+
+## Metric Sources
+
+- Metric source papers:
+- Metric implementation source:
+- Deviation from original implementation:
+
 ## Experiment Setup
 
 - Datasets:

package/package-assets/shared/lab/context/eval-protocol.md

@@ -17,6 +17,9 @@ Use this file to define the paper-facing evaluation objective, table plan, gates
 ## Metric Glossary
 
 - Metric glossary:
+- Background sources:
+- Method and baseline source papers:
+- Method and baseline implementation source:
 - Metric source papers:
 - Metric implementation source:
 - Comparison source papers:

package/package-assets/shared/skills/lab/stages/report.md

@@ -6,6 +6,9 @@
 - method overview
 - selected metrics summary
 - plain-language metric guide
+- background sources
+- method and baseline sources
+- metric sources
 - experiment setup
 - validated main results
 - managed main tables artifact under `<deliverables_root>/main-tables.md`
@@ -39,6 +42,8 @@
 - Carry the approved `Primary metrics`, `Secondary metrics`, and `Required terminal evidence` into both the report and the managed main-tables artifact.
 - Explain the selected primary and secondary metrics in plain language for the user: what each metric measures, whether higher or lower is better, and whether it is a main result metric or only a health/support metric.
 - If coverage, completeness, confidence, or similar health metrics appear, explicitly say that they describe experimental reliability rather than the main scientific effect.
+- Pull the core background references, method or baseline references, and metric references out of the approved evaluation protocol instead of hiding them in `.lab/context/*`.
+- Report only the few references a collaborator needs to orient themselves quickly; do not turn `report.md` into a full bibliography dump.
 - If the report depends on a deviation from an original metric or implementation, state that deviation explicitly instead of smoothing it over.
 - If `.lab/config/workflow.json` sets the workflow language to Chinese, write `report.md` and `<deliverables_root>/main-tables.md` in Chinese unless a file path, code identifier, or literal metric name must remain unchanged.
 - Prefer conservative interpretation over marketing language.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlab",
-  "version": "0.1.17",
+  "version": "0.1.18",
   "description": "Strict /lab research workflow installer for Codex and Claude",
   "keywords": [
     "codex",