superlab 0.1.71 → 0.1.73

package/package-assets/shared/lab/.managed/scripts/validate_section_draft.py

@@ -261,10 +261,102 @@ INTERNAL_CONFIG_LABEL_PATTERN = re.compile(
     r"\b[a-z]{1,4}\d+(?:[-_][a-z]?\d+(?:\.\d+)?){1,4}\b",
     flags=re.IGNORECASE,
 )
+ISOLATED_INSIGHT_HEADING_PATTERN = re.compile(
+    r"\\(?:sub)*section\*?\s*\{\s*(?:our\s+)?insights?\s*\}|"
+    r"\\(?:sub)*section\*?\s*\{\s*(?:核心)?洞见\s*\}",
+    flags=re.IGNORECASE,
+)
+
+
+def has_insight_contrast(text: str) -> bool:
+    return contains_any(
+        text,
+        (
+            "counterintuitively",
+            "we observe",
+            "we find",
+            "a closer inspection",
+            "while it might seem",
+            "existing work assumes",
+            "common assumption",
+            "suggesting that",
+            "reveals that",
+            "反直觉",
+            "我们观察到",
+            "我们发现",
+            "进一步检查",
+            "通常假设",
+            "常规认知",
+            "这表明",
+            "揭示",
+        ),
+    )
+
+
+def has_mechanism_explanation(text: str) -> bool:
+    return contains_any(
+        text,
+        (
+            "because",
+            "mechanism",
+            "attributed to",
+            "explains",
+            "to capture",
+            "to model",
+            "based on",
+            "therefore",
+            "causal",
+            "causes",
+            "amplifies",
+            "propagates",
+            "因为",
+            "机制",
+            "归因于",
+            "解释",
+            "为了刻画",
+            "为了建模",
+            "基于",
+            "因此",
+            "因果",
+            "放大",
+            "传播",
+        ),
+    )
+
+
+def has_diagnostic_interpretation(text: str) -> bool:
+    return contains_any(
+        text,
+        (
+            "supports our hypothesis",
+            "supports the hypothesis",
+            "diagnostic",
+            "mechanism",
+            "ablation shows",
+            "ablation indicates",
+            "this suggests",
+            "rather than",
+            "not merely",
+            "we attribute",
+            "验证了",
+            "支持假设",
+            "诊断",
+            "机制",
+            "消融表明",
+            "这表明",
+            "并非只是",
+            "不是单纯",
+            "归因于",
+        ),
+    )
 
 
 def check_common_section_gate_risks(text: str, issues: list[str]):
     prose_text = strip_latex_commands(text)
+    if ISOLATED_INSIGHT_HEADING_PATTERN.search(text):
+        issues.append(
+            "paper prose should not isolate insight under an 'Our Insights' style heading; weave the insight into the section's motivation, mechanism, evidence, and boundary"
+        )
     if contains_any(prose_text, SERVICE_STYLE_PHRASES):
         issues.append(
             "service-style or AI-assistant meta language appears in reader-facing prose; rewrite it as academic manuscript text"
@@ -530,6 +622,8 @@ def check_abstract(text: str, issues: list[str]):
         issues.append("abstract should state the core challenge or gap")
     if not contains_any(text, ("boundary", "bounded", "limitation", "however", "but", "局限", "边界", "限制")):
         issues.append("abstract should include a bounded result or explicit limitation")
+    if not (has_insight_contrast(text) or has_mechanism_explanation(text)):
+        issues.append("abstract should include a one-sentence insight or mechanism, not only task, method, and metric results")
 
 
 def check_introduction(text: str, issues: list[str]):
@@ -568,6 +662,10 @@ def check_introduction(text: str, issues: list[str]):
         ),
     ):
         issues.append("introduction should explain what is missing in prior work")
+    if not has_insight_contrast(text):
+        issues.append("introduction should create an insight contrast, such as common assumption versus observed mechanism")
+    if not has_mechanism_explanation(text):
+        issues.append("introduction should state the root mechanism or explanation behind the gap")
 
 
 def check_related_work(text: str, issues: list[str]):
@@ -592,6 +690,8 @@ def check_method(text: str, issues: list[str]):
         issues.append("method should explain the concrete design")
     if not contains_any(text, ("advantage", "benefit", "improves", "优势", "收益")):
         issues.append("method should explain the technical advantage")
+    if not has_mechanism_explanation(text):
+        issues.append("method should present design choices as consequences of the core insight or mechanism, not as an API-style module list")
 
 
 def check_experiments(text: str, issues: list[str]):
@@ -621,6 +721,8 @@ def check_experiments(text: str, issues: list[str]):
         ),
     ):
         issues.append("experiments should include benchmark scene notes")
+    if not has_diagnostic_interpretation(text):
+        issues.append("experiments should interpret results as diagnostic evidence for the paper's mechanism or insight, not only restate table values")
 
 
 def check_conclusion(text: str, issues: list[str]):
@@ -628,6 +730,23 @@ def check_conclusion(text: str, issues: list[str]):
         issues.append("conclusion should state at least one limitation or boundary")
     if not contains_any(text, ("future work", "next step", "future direction", "下一步", "未来工作")):
         issues.append("conclusion should state one next step or future direction")
+    if not contains_any(
+        text,
+        (
+            "broader principle",
+            "suggests",
+            "indicates",
+            "implies",
+            "takeaway",
+            "principle",
+            "更广泛",
+            "表明",
+            "意味着",
+            "启示",
+            "原则",
+        ),
+    ):
+        issues.append("conclusion should state the broader principle or takeaway implied by the evidence")
 
 
 SECTION_CHECKS = {

package/package-assets/shared/lab/.managed/scripts/validate_stage_report.py

@@ -8,11 +8,14 @@ from pathlib import Path
 REQUIRED_SECTIONS = {
     "Rule Preflight": [r"^##\s+Rule Preflight\s*$", r"^##\s+规则预检\s*$"],
     "Stage Identity": [r"^##\s+Stage Identity\s*$", r"^##\s+阶段身份\s*$"],
+    "Requested Outcome Mapping": [r"^##\s+Requested Outcome Mapping\s*$", r"^##\s+请求结果映射\s*$"],
     "Core Explanation Table": [r"^##\s+Core Explanation Table\s*$", r"^##\s+核心说明表\s*$"],
     "Evidence And Artifacts": [r"^##\s+Evidence And Artifacts\s*$", r"^##\s+证据与工件\s*$"],
     "Next Action": [r"^##\s+Next Action\s*$", r"^##\s+下一步动作\s*$"],
 }
 
+REPAIR_CONTROL_SECTION = [r"^##\s+Repair Control\s*$", r"^##\s+修复控制\s*$"]
+
 REQUIRED_CORE_ROWS = {
     "stage": ("这是什么阶段", "what stage is this", "stage"),
     "background": ("背景是什么", "background"),
@@ -86,6 +89,148 @@ WHY_MARKERS = (
     "避免",
 )
 
+IMPROVEMENT_NEEDED_MARKERS = (
+    "need improvement",
+    "needs improvement",
+    "needs revision",
+    "must improve",
+    "should improve",
+    "needs repair",
+    "needs rerun",
+    "需要改进",
+    "需要修复",
+    "需要重跑",
+    "需要继续",
+    "仍需",
+)
+
+NO_IMPROVEMENT_MARKERS = (
+    "no improvement needed",
+    "does not need improvement",
+    "not need improvement",
+    "无需改进",
+    "不需要改进",
+    "不需改进",
+)
+
+STOP_DECISION_MARKERS = (
+    "decision: stop",
+    "decision：stop",
+    "decision: 停止",
+    "decision：停止",
+    "决策: stop",
+    "决策：stop",
+    "决策: 停止",
+    "决策：停止",
+)
+
+TERMINAL_BOUNDARY_MARKERS = (
+    "budget exhausted",
+    "budget boundary",
+    "exceeded budget",
+    "fatal",
+    "safety",
+    "invalid artifact",
+    "invalid metric",
+    "frozen core",
+    "outside the envelope",
+    "outside approved envelope",
+    "user requested stop",
+    "approval required",
+    "requires approval",
+    "escalation boundary",
+    "impossible",
+    "not allowed",
+    "terminal boundary",
+    "integrity",
+    "ethics",
+    "预算耗尽",
+    "预算边界",
+    "超过预算",
+    "致命",
+    "安全",
+    "无效工件",
+    "无效指标",
+    "冻结核心",
+    "超出边界",
+    "超出已批准",
+    "用户要求停止",
+    "需要批准",
+    "升级边界",
+    "不可能",
+    "不允许",
+    "终止边界",
+    "诚信",
+    "伦理",
+)
+
+REPAIR_CONTROL_FIELDS = (
+    ("Repair budget:", "修复预算："),
+    ("Repair attempts used:", "已用修复次数："),
+    ("Current failure class:", "当前失败类型："),
+    ("Repair hypothesis:", "修复假设："),
+    ("Evidence-changing knobs changed:", "改变证据解释的旋钮："),
+    ("Ordinary engineering fixes allowed:", "允许的普通工程修复："),
+    ("Frozen core unchanged:", "冻结核心不变："),
+    ("Forbidden repairs avoided:", "已避免的禁用修复："),
+    ("Confirmation check:", "确认验证："),
+)
+
+FORBIDDEN_REPAIR_PATTERNS = (
+    r"\b(changed|modified|relaxed|lowered|loosened|rewrote)\s+(the\s+)?(primary\s+)?metric\b",
+    r"\b(changed|modified|relaxed|lowered|loosened)\s+(the\s+)?(target|threshold|target\s+range)\b",
+    r"\b(drop|dropped|delete|deleted|remove|removed|exclude|excluded)\s+(hard|failed|bad)\s+(cases|examples|samples)\b",
+    r"\b(changed|modified|rewrote)\s+(labels?|ground\s+truth)\b",
+    r"\b(changed|modified|swapped|replaced)\s+(the\s+)?(final\s+)?test\s+split\b",
+    r"\b(changed|modified|expanded)\s+(the\s+)?(paper-facing\s+)?claim\b",
+    r"\b(changed|modified|switched)\s+(the\s+)?(threat\s+model|reviewer\s+profile|dataset\s+scope)\b",
+    r"修改(主)?指标",
+    r"放宽(目标|阈值|目标区间)",
+    r"(删除|移除|剔除)(困难|失败|坏)(样本|案例)",
+    r"修改(标签|真值|测试集|主张|威胁模型|数据集范围)",
+)
+
+REPAIR_SUCCESS_MARKERS = (
+    "repair passed",
+    "repair succeeded",
+    "passed after repair",
+    "promotion is planned",
+    "promote",
+    "promotion",
+    "修复通过",
+    "修复成功",
+    "准备推广",
+    "推广",
+)
+
+NO_CONFIRMATION_MARKERS = (
+    "not needed",
+    "not required",
+    "none",
+    "n/a",
+    "无需",
+    "不需要",
+    "无",
+)
+
+CONFIRMATION_MARKERS = (
+    "confirmation",
+    "confirm",
+    "holdout",
+    "control",
+    "new seed",
+    "seed",
+    "batch",
+    "rerun",
+    "复验",
+    "确认",
+    "留出",
+    "对照",
+    "新 seed",
+    "批次",
+    "重跑",
+)
+
 
 def parse_args():
     parser = argparse.ArgumentParser(description="Validate a plain-language lab stage report.")
@@ -162,6 +307,16 @@ def has_marker_with_value(body: str, markers: tuple[str, ...]) -> bool:
     return False
 
 
+def marker_value(body: str, markers: tuple[str, ...]) -> str:
+    for line in body.splitlines():
+        stripped = line.strip()
+        for marker in markers:
+            if marker not in stripped:
+                continue
+            return stripped.split(marker, 1)[1].strip()
+    return ""
+
+
 def is_shallow(value: str | None) -> bool:
     if value is None:
         return True
@@ -174,6 +329,32 @@ def has_why(value: str) -> bool:
     return any(marker in lowered for marker in WHY_MARKERS)
 
 
+def improvement_is_needed(value: str | None) -> bool:
+    lowered = normalize(value or "")
+    if any(marker in lowered for marker in NO_IMPROVEMENT_MARKERS):
+        return False
+    return any(marker in lowered for marker in IMPROVEMENT_NEEDED_MARKERS)
+
+
+def next_action_is_stop(body: str) -> bool:
+    lowered = normalize(body)
+    if any(marker in lowered for marker in STOP_DECISION_MARKERS):
+        return True
+    return re.search(r"^\s*-\s*(decision|决策)\s*[:：]\s*(stop|停止)\b", body, flags=re.IGNORECASE | re.MULTILINE) is not None
+
+
+def has_terminal_boundary(value: str) -> bool:
+    lowered = normalize(value)
+    return any(marker in lowered for marker in TERMINAL_BOUNDARY_MARKERS)
+
+
+def parse_repair_attempts(value: str) -> int | None:
+    match = re.search(r"\d+", value or "")
+    if not match:
+        return None
+    return int(match.group(0))
+
+
 def validate_core_table(text: str) -> list[str]:
     issues = []
     rows = parse_core_table_rows(text)
@@ -217,6 +398,63 @@ def validate_evidence_section(text: str) -> list[str]:
     return issues
 
 
+def validate_requested_outcome_mapping(text: str) -> list[str]:
+    issues = []
+    body = extract_section(text, REQUIRED_SECTIONS["Requested Outcome Mapping"])
+    marker_groups = (
+        ("Original request:", "原始请求："),
+        ("Requested deliverables:", "请求交付物："),
+        ("Completion mapping:", "完成映射："),
+        ("Response shape:", "回答形态："),
+    )
+    if not body:
+        return ["Requested Outcome Mapping section is empty"]
+    for group in marker_groups:
+        if not any(marker in body for marker in group):
+            issues.append(f"Requested Outcome Mapping is missing '{group[0]}'")
+            continue
+        if not has_marker_with_value(body, group):
+            issues.append(f"Requested Outcome Mapping field '{group[0]}' must have a non-empty value")
+    return issues
+
+
+def validate_repair_control(text: str, expected_stage: str) -> list[str]:
+    body = extract_section(text, REPAIR_CONTROL_SECTION)
+    is_auto_stage = expected_stage.lower() == "auto"
+    if not body:
+        if is_auto_stage:
+            return ["Repair Control section is required for auto stage reports"]
+        return []
+
+    issues = []
+    for group in REPAIR_CONTROL_FIELDS:
+        if not any(marker in body for marker in group):
+            issues.append(f"Repair Control is missing '{group[0]}'")
+            continue
+        if not has_marker_with_value(body, group):
+            issues.append(f"Repair Control field '{group[0]}' must have a non-empty value")
+
+    for pattern in FORBIDDEN_REPAIR_PATTERNS:
+        if re.search(pattern, body, flags=re.IGNORECASE):
+            issues.append(f"Repair Control contains forbidden repair: {pattern}")
+
+    attempts = parse_repair_attempts(marker_value(body, ("Repair attempts used:", "已用修复次数：")))
+    confirmation = marker_value(body, ("Confirmation check:", "确认验证："))
+    whole_text = normalize(text)
+    repair_succeeded = any(marker in whole_text for marker in REPAIR_SUCCESS_MARKERS)
+    if attempts and attempts > 0 and repair_succeeded:
+        normalized_confirmation = normalize(confirmation)
+        if (
+            any(marker in normalized_confirmation for marker in NO_CONFIRMATION_MARKERS)
+            or not any(marker in normalized_confirmation for marker in CONFIRMATION_MARKERS)
+        ):
+            issues.append(
+                "Repair Control requires a confirmation check after a successful repair before promotion or final success"
+            )
+
+    return issues
+
+
 def validate_rule_preflight(text: str) -> list[str]:
     body = extract_section(text, REQUIRED_SECTIONS["Rule Preflight"])
     marker_groups = (
@@ -248,6 +486,12 @@ def validate_next_action(text: str) -> list[str]:
         return ["Next Action must choose continue, stop, revise, rerun, escalate, or handoff"]
     if not has_why(body):
         return ["Next Action must include why the next step is appropriate"]
+    rows = parse_core_table_rows(text)
+    improve_value = find_row_value(rows, REQUIRED_CORE_ROWS["improve_why"]) or ""
+    if improvement_is_needed(improve_value) and next_action_is_stop(body) and not has_terminal_boundary(body):
+        return [
+            "Next Action cannot stop after a recoverable improvement need without an explicit terminal boundary; choose continue, revise, rerun, or escalate, or state the budget/frozen-core/safety boundary"
+        ]
     return []
 
 
@@ -279,6 +523,8 @@ def validate(path: Path, expected_stage: str = "") -> list[str]:
     if not missing_sections:
         issues.extend(validate_rule_preflight(text))
         issues.extend(validate_stage_identity(text, expected_stage))
+        issues.extend(validate_requested_outcome_mapping(text))
+        issues.extend(validate_repair_control(text, expected_stage))
         issues.extend(validate_core_table(text))
         issues.extend(validate_evidence_section(text))
         issues.extend(validate_next_action(text))

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

@@ -9,6 +9,9 @@
 ## Reader Summary
 
 - One-sentence conclusion:
+- Core insight:
+- Evidence that supports the insight:
+- Decision or action implication:
 - What is validated:
 - What is still unproven:
 - Biggest reporting risk:
@@ -35,6 +38,8 @@
 
 - Approved method name:
 - Plain-language method summary:
+- Mechanism tested or explained:
+- Why the design follows from the insight:
 - What this method changes relative to prior work:
 - Most relevant prior work or baseline anchors:
 - What those prior methods do:
@@ -115,10 +120,16 @@
 
 Summarize validated iteration outcomes.
 
+- Diagnostic interpretation:
+- What this teaches beyond the raw numbers:
+
 ## Ablations
 
 Describe meaningful ablations and what they showed.
 
+- Mechanism tested:
+- What the ablation teaches beyond the delta:
+
 ## Failures
 
 Preserve failed runs and rejected ideas.

package/package-assets/shared/lab/.managed/templates/idea.md

@@ -159,6 +159,24 @@ Suggested levels:
 - Expected advantage:
 - Evidence needed to prove the advantage:
 
+## Contribution vs Insight
+
+- Contribution:
+- Insight:
+- Core insight anchor sentence:
+- Why the insight matters beyond the artifact:
+- Action or community value:
+
+## Insight Evidence Chain
+
+- Observation:
+- Why existing explanations fail:
+- Core insight:
+- Mechanism:
+- Validation tests:
+- Generalization or action implication:
+- Prediction:
+
 ## Rough Approach
 
 - Plain-language description of how this would work:

package/package-assets/shared/lab/.managed/templates/main-tables.md

@@ -36,27 +36,33 @@
 - Table 2 is for:
 - Table 3 is for:
 - Table 4 is for:
+- Diagnostic takeaway:
+- What the tables do not prove:
 
 ## Table 1
 
 - Purpose:
 - Metrics used:
 - Strongest supported claim:
+- Mechanism or insight tested:
 
 ## Table 2
 
 - Purpose:
 - Metrics used:
 - Strongest supported claim:
+- Mechanism or insight tested:
 
 ## Table 3
 
 - Purpose:
 - Metrics used:
 - Strongest supported claim:
+- Mechanism or insight tested:
 
 ## Table 4
 
 - Purpose:
 - Metrics used:
 - Strongest supported claim:
+- Mechanism or insight tested:

package/package-assets/shared/lab/.managed/templates/paper-plan.md

@@ -5,6 +5,7 @@
 - Venue or audience:
 - Paper status:
 - Core story in one sentence:
+- Core insight anchor:
 - Approved framing artifact:
 - Terminology lock:
 
@@ -24,6 +25,14 @@
 - Limitation sources:
 - Claims that still need more evidence:
 
+## Insight Integration Map
+
+- Introduction contrast:
+- Method design consequence:
+- Experiments diagnostic evidence:
+- Conclusion principle or action implication:
+- Alternative explanation to address:
+
 ## Asset Coverage Targets
 
 - Core asset floor:

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

@@ -20,6 +20,35 @@
 - Primary artifact:
 - Next owner:
 
+## Requested Outcome Mapping
+
+- Original request:
+- Requested deliverables:
+- Completion mapping:
+- Response shape:
+
+## Repair Control
+
+- Repair budget:
+- Repair attempts used:
+- Current failure class:
+- Repair hypothesis:
+- Evidence-changing knobs changed:
+- Ordinary engineering fixes allowed:
+- Frozen core unchanged:
+- Forbidden repairs avoided:
+- Confirmation check:
+
+## Revision Pass Discipline
+
+- Logic / evidence pass outcome:
+- Logic / evidence blockers found:
+- Theory / metric / field pass outcome:
+- Theory / metric / field blockers found:
+- Language / reader pass outcome:
+- Was language polish delayed until upstream blockers were resolved:
+- Was user confirmation required between passes, and why:
+
 ## Core Explanation Table
 
 | Question | Plain Answer |

package/package-assets/shared/lab/.managed/templates/write-iteration.md

@@ -38,6 +38,30 @@
 - Terminology consistency:
 - Five-dimension self-review outcome:
 
+## Insight Integration
+
+- Core insight anchor used:
+- Section role in the insight chain:
+- Common assumption or surface explanation challenged:
+- Mechanism or why-explanation added:
+- Evidence or diagnostic result tied to the insight:
+- Did the prose avoid an isolated `Our Insights`-style section:
+- If the section is Introduction, what cognitive contrast was established:
+- If the section is Method, which design choice follows from the insight:
+- If the section is Experiments, which mechanism did the result or ablation diagnose:
+- If the section is Conclusion, what broader principle or action implication was stated:
+
+## Revision Pass Discipline
+
+- Logic pass outcome:
+- Logic blockers found:
+- Theory / field pass outcome:
+- Theory / field blockers found:
+- Language pass outcome:
+- Was language polish delayed until logic and theory blockers were resolved:
+- Was user confirmation required between passes, and why:
+- If a pass failed, what route was chosen: revise / review / iterate / report / ask user:
+
 ## Terminology Clarity
 
 - Key terms introduced or revised this round: