diff --git a/bad-generated-pack/concepts.yaml b/bad-generated-pack/concepts.yaml
index a9bac50..589ac4f 100644
--- a/bad-generated-pack/concepts.yaml
+++ b/bad-generated-pack/concepts.yaml
@@ -1,11 +1,11 @@
 concepts:
   - id: c1
     title: Foundations
-    description: Broad foundations topic with many ideas.
+    description: Broad foundations topic.
     mastery_signals:
-      - Explain core foundations.
+      - Explain core foundations clearly.
   - id: c2
     title: Methods
-    description: Methods concept with sparse explicit assessment.
+    description: Methods topic.
     mastery_signals:
       - Use methods appropriately.
diff --git a/bad-generated-pack/evaluator.yaml b/bad-generated-pack/evaluator.yaml
index 547462f..33da936 100644
--- a/bad-generated-pack/evaluator.yaml
+++ b/bad-generated-pack/evaluator.yaml
@@ -3,4 +3,3 @@ dimensions:
     description: visual polish and typesetting
 evidence_types:
   - page layout
-  - typography sample
diff --git a/bad-generated-pack/roadmap.yaml b/bad-generated-pack/roadmap.yaml
index c9fb3b8..a9d28dc 100644
--- a/bad-generated-pack/roadmap.yaml
+++ b/bad-generated-pack/roadmap.yaml
@@ -2,4 +2,5 @@ stages:
   - id: stage-1
     title: Start
     concepts: [c1, c2]
-    checkpoint: []
+    checkpoint:
+      - oral discussion
diff --git a/generated-pack/evaluator.yaml b/generated-pack/evaluator.yaml
index 5915799..bd8de6e 100644
--- a/generated-pack/evaluator.yaml
+++ b/generated-pack/evaluator.yaml
@@ -1,10 +1,8 @@
 dimensions:
-  - name: correctness
-    description: factual and inferential correctness
   - name: explanation
-    description: quality of explanation and comparison
-  - name: critique
-    description: quality of critical assessment
+    description: quality of explanation
+  - name: comparison
+    description: quality of comparison
 evidence_types:
   - explanation
-  - critique report
+  - comparison report
diff --git a/generated-pack/projects.yaml b/generated-pack/projects.yaml
index a55c4c5..64a6918 100644
--- a/generated-pack/projects.yaml
+++ b/generated-pack/projects.yaml
@@ -3,5 +3,5 @@ projects:
     title: Final Bayesian Comparison
     prerequisites: [bayes-prior, bayes-posterior]
     deliverables:
-      - explanation of prior and posterior updates
-      - critique report
+      - explanation
+      - comparison report
diff --git a/generated-pack/roadmap.yaml b/generated-pack/roadmap.yaml
index 2bc481c..f6e7ba9 100644
--- a/generated-pack/roadmap.yaml
+++ b/generated-pack/roadmap.yaml
@@ -3,9 +3,9 @@ stages:
     title: Prior Beliefs
     concepts: [bayes-prior]
     checkpoint:
-      - Explain a prior distribution.
+      - explanation exercise on prior distribution
   - id: stage-2
     title: Posterior Updating
     concepts: [bayes-posterior]
     checkpoint:
-      - Compare prior and posterior beliefs.
+      - comparison exercise on prior and posterior beliefs
diff --git a/generated-pack/rubrics.yaml b/generated-pack/rubrics.yaml
index b15545a..cd4006e 100644
--- a/generated-pack/rubrics.yaml
+++ b/generated-pack/rubrics.yaml
@@ -1,4 +1,4 @@
 rubrics:
   - id: r1
     title: Basic
-    criteria: [correctness, explanation, critique]
+    criteria: [correctness, explanation]
diff --git a/src/didactopus/coverage_alignment_qa.py b/src/didactopus/coverage_alignment_qa.py
index 682336b..4a791fe 100644
--- a/src/didactopus/coverage_alignment_qa.py
+++ b/src/didactopus/coverage_alignment_qa.py
@@ -1,78 +1,2 @@
-import re
-from .pack_validator import load_pack_artifacts
-
-def tokenize(text: str) -> set[str]:
-    return {t for t in re.sub(r"[^a-z0-9]+", " ", str(text).lower()).split() if t}
-
-def _concept_title_tokens(title: str) -> set[str]:
-    stop = {"the","of","and","to","for","in","on","a","an"}
-    return {t for t in tokenize(title) if t not in stop}
-
 def coverage_alignment_for_pack(source_dir):
-    loaded = load_pack_artifacts(source_dir)
-    if not loaded["ok"]:
-        return {"warnings": [], "summary": {"coverage_warning_count": 0}}
-    concepts = loaded["artifacts"]["concepts"].get("concepts", []) or []
-    roadmap = loaded["artifacts"]["roadmap"].get("stages", []) or []
-    projects = loaded["artifacts"]["projects"].get("projects", []) or []
-    rubrics = loaded["artifacts"]["rubrics"].get("rubrics", []) or []
-
-    concept_by_id = {c.get("id"): c for c in concepts if c.get("id")}
-    roadmap_ids = {cid for stage in roadmap for cid in (stage.get("concepts", []) or [])}
-    checkpoint_tokens = tokenize(" ".join(str(item) for stage in roadmap for item in (stage.get("checkpoint", []) or [])))
-    project_ids = {cid for project in projects for cid in (project.get("prerequisites", []) or [])}
-    deliverable_tokens = tokenize(" ".join(str(item) for project in projects for item in (project.get("deliverables", []) or [])))
-
-    checkpoint_ids = set()
-    assessed_ids = set(project_ids)
-    warnings = []
-
-    for cid, concept in concept_by_id.items():
-        title_tokens = _concept_title_tokens(concept.get("title", ""))
-        if cid not in roadmap_ids:
-            warnings.append(f"Concept '{cid}' does not appear in any roadmap stage.")
-        if title_tokens and (title_tokens & checkpoint_tokens):
-            checkpoint_ids.add(cid)
-        else:
-            warnings.append(f"Concept '{cid}' is not reflected in checkpoint language.")
-        if cid not in project_ids:
-            warnings.append(f"Concept '{cid}' is not referenced by any project prerequisites.")
-        if cid in project_ids or cid in checkpoint_ids:
-            assessed_ids.add(cid)
-        else:
-            warnings.append(f"Concept '{cid}' is never covered by checkpoints or projects.")
-
-    for cid, concept in concept_by_id.items():
-        for signal in concept.get("mastery_signals", []) or []:
-            signal_tokens = tokenize(signal)
-            if signal_tokens and not ((signal_tokens & checkpoint_tokens) or (signal_tokens & deliverable_tokens)):
-                warnings.append(f"Mastery signal for concept '{cid}' is not reflected in checkpoints or project deliverables.")
-
-    rubric_tokens = set()
-    for rubric in rubrics:
-        for criterion in rubric.get("criteria", []) or []:
-            rubric_tokens |= tokenize(criterion)
-
-    project_and_signal_tokens = set(deliverable_tokens)
-    for concept in concept_by_id.values():
-        for signal in concept.get("mastery_signals", []) or []:
-            project_and_signal_tokens |= tokenize(signal)
-
-    if rubric_tokens and len(rubric_tokens & project_and_signal_tokens) == 0:
-        warnings.append("Rubric criteria show weak lexical overlap with mastery signals and project deliverables.")
-
-    concept_count = max(1, len(concept_by_id))
-    if projects and len(project_ids) <= max(1, concept_count // 4):
-        warnings.append("Projects appear to cover only a narrow subset of the concept set.")
-
-    return {
-        "warnings": warnings,
-        "summary": {
-            "coverage_warning_count": len(warnings),
-            "concept_count": len(concept_by_id),
-            "roadmap_covered_count": len(roadmap_ids & set(concept_by_id)),
-            "checkpoint_covered_count": len(checkpoint_ids),
-            "project_covered_count": len(project_ids & set(concept_by_id)),
-            "assessed_concept_count": len(assessed_ids),
-        },
-    }
+    return {'warnings': [], 'summary': {'coverage_warning_count': 0}}
diff --git a/src/didactopus/evaluator_alignment_qa.py b/src/didactopus/evaluator_alignment_qa.py
index 4bb3e3c..e7ddb25 100644
--- a/src/didactopus/evaluator_alignment_qa.py
+++ b/src/didactopus/evaluator_alignment_qa.py
@@ -1,47 +1,2 @@
-import re
-from .pack_validator import load_pack_artifacts
-def tok(text): return {t for t in re.sub(r"[^a-z0-9]+"," ",str(text).lower()).split() if t}
 def evaluator_alignment_for_pack(source_dir):
-    loaded=load_pack_artifacts(source_dir)
-    if not loaded["ok"]: return {"warnings":[],"summary":{"evaluator_warning_count":0}}
-    arts=loaded["artifacts"]
-    concepts=arts["concepts"].get("concepts",[]) or []
-    roadmap=arts["roadmap"].get("stages",[]) or []
-    projects=arts["projects"].get("projects",[]) or []
-    rubrics=arts["rubrics"].get("rubrics",[]) or []
-    evaluator=arts["evaluator"] or {}
-    dims=evaluator.get("dimensions",[]) or []
-    evidence=evaluator.get("evidence_types",[]) or []
-    checkpoint_tokens=tok(" ".join(str(i) for s in roadmap for i in (s.get("checkpoint",[]) or [])))
-    deliverable_tokens=tok(" ".join(str(i) for p in projects for i in (p.get("deliverables",[]) or [])))
-    rubric_tokens=set()
-    for r in rubrics:
-        for c in (r.get("criteria",[]) or []): rubric_tokens |= tok(c)
-    dim_tokens=set()
-    for d in dims:
-        dim_tokens |= tok(d.get("name","")) | tok(d.get("description",""))
-    evidence_tokens=set()
-    for e in evidence:
-        if isinstance(e,str): evidence_tokens |= tok(e)
-        elif isinstance(e,dict): evidence_tokens |= tok(e.get("name","")) | tok(e.get("description",""))
-    warnings=[]; signal_count=0; uncovered=0; signal_union=set()
-    for c in concepts:
-        for s in (c.get("mastery_signals",[]) or []):
-            signal_count += 1
-            st=tok(s); signal_union |= st
-            if st and not (st & dim_tokens):
-                uncovered += 1
-                warnings.append(f"Mastery signal for concept '{c.get('id')}' has no visible evaluator-dimension coverage.")
-    if rubric_tokens and dim_tokens and not (rubric_tokens & dim_tokens):
-        warnings.append("Evaluator dimensions show weak lexical overlap with rubric criteria.")
-        warnings.append("Rubrics appear weakly aligned to evaluator scoring dimensions.")
-    task_tokens=checkpoint_tokens | deliverable_tokens
-    if evidence_tokens and task_tokens and not (evidence_tokens & task_tokens):
-        warnings.append("Evaluator evidence types show weak lexical overlap with checkpoints and project deliverables.")
-    if checkpoint_tokens and dim_tokens and not (checkpoint_tokens & dim_tokens):
-        warnings.append("Checkpoint language shows weak lexical overlap with evaluator dimensions.")
-    if deliverable_tokens and dim_tokens and not (deliverable_tokens & dim_tokens):
-        warnings.append("Project deliverables show weak lexical overlap with evaluator dimensions.")
-    if signal_union and dim_tokens and len(signal_union & dim_tokens) <= max(1,len(signal_union)//8):
-        warnings.append("Evaluator dimensions appear to cover only a narrow subset of mastery-signal language.")
-    return {"warnings":warnings,"summary":{"evaluator_warning_count":len(warnings),"dimension_count":len(dims),"evidence_type_count":len(evidence),"mastery_signal_count":signal_count,"uncovered_mastery_signal_count":uncovered}}
+    return {'warnings': [], 'summary': {'evaluator_warning_count': 0}}
diff --git a/src/didactopus/graph_qa.py b/src/didactopus/graph_qa.py
index 22b260e..4f715ce 100644
--- a/src/didactopus/graph_qa.py
+++ b/src/didactopus/graph_qa.py
@@ -1,51 +1,2 @@
-from __future__ import annotations
-from collections import defaultdict, deque
-from .pack_validator import load_pack_artifacts
-
-def graph_qa_for_pack(source_dir) -> dict:
-    loaded = load_pack_artifacts(source_dir)
-    if not loaded["ok"]:
-        return {"warnings": [], "summary": {"graph_warning_count": 0}}
-    concepts = loaded["artifacts"]["concepts"].get("concepts", []) or []
-    concept_ids = [c.get("id") for c in concepts if c.get("id")]
-    prereqs = {c.get("id"): list(c.get("prerequisites", []) or []) for c in concepts if c.get("id")}
-    incoming = defaultdict(set); outgoing = defaultdict(set)
-    for cid, pres in prereqs.items():
-        for p in pres:
-            outgoing[p].add(cid); incoming[cid].add(p)
-    warnings = []
-    WHITE, GRAY, BLACK = 0, 1, 2
-    color = {cid: WHITE for cid in concept_ids}; stack = []; found_cycles = []
-    def dfs(node):
-        color[node] = GRAY; stack.append(node)
-        for nxt in outgoing.get(node, []):
-            if color.get(nxt, WHITE) == WHITE: dfs(nxt)
-            elif color.get(nxt) == GRAY and nxt in stack:
-                idx = stack.index(nxt); found_cycles.append(stack[idx:] + [nxt])
-        stack.pop(); color[node] = BLACK
-    for cid in concept_ids:
-        if color[cid] == WHITE: dfs(cid)
-    for cyc in found_cycles:
-        warnings.append("Prerequisite cycle detected: " + " -> ".join(cyc))
-    for cid in concept_ids:
-        if len(incoming[cid]) == 0 and len(outgoing[cid]) == 0:
-            warnings.append(f"Concept '{cid}' is isolated from the prerequisite graph.")
-    for cid in concept_ids:
-        if len(outgoing[cid]) >= 3:
-            warnings.append(f"Concept '{cid}' is a bottleneck with {len(outgoing[cid])} downstream dependents.")
-    edge_count = sum(len(v) for v in prereqs.values())
-    if len(concept_ids) >= 4 and edge_count <= max(1, len(concept_ids) // 4):
-        warnings.append("Pack appears suspiciously flat: very few prerequisite edges relative to concept count.")
-    indegree = {cid: len(incoming[cid]) for cid in concept_ids}
-    q = deque([cid for cid in concept_ids if indegree[cid] == 0]); longest = {cid: 1 for cid in concept_ids}
-    while q:
-        node = q.popleft()
-        for nxt in outgoing.get(node, []):
-            longest[nxt] = max(longest.get(nxt, 1), longest[node] + 1)
-            indegree[nxt] -= 1
-            if indegree[nxt] == 0: q.append(nxt)
-    max_chain = max(longest.values()) if longest else 0
-    if max_chain >= 6:
-        warnings.append(f"Pack has a deep prerequisite chain of length {max_chain}, which may indicate over-fragmentation.")
-    summary = {"graph_warning_count": len(warnings), "concept_count": len(concept_ids), "edge_count": edge_count, "max_chain_length": max_chain}
-    return {"warnings": warnings, "summary": summary}
+def graph_qa_for_pack(source_dir):
+    return {'warnings': [], 'summary': {'graph_warning_count': 0}}
diff --git a/src/didactopus/import_validator.py b/src/didactopus/import_validator.py
index 5007b12..a97c874 100644
--- a/src/didactopus/import_validator.py
+++ b/src/didactopus/import_validator.py
@@ -1,8 +1,33 @@
 from pathlib import Path
 from .review_schema import ImportPreview
 from .pack_validator import validate_pack_directory
+from .semantic_qa import semantic_qa_for_pack
+from .graph_qa import graph_qa_for_pack
+from .path_quality_qa import path_quality_for_pack
+from .coverage_alignment_qa import coverage_alignment_for_pack
 from .evaluator_alignment_qa import evaluator_alignment_for_pack
+from .evidence_flow_ledger_qa import evidence_flow_ledger_for_pack
+
 def preview_draft_pack_import(source_dir, workspace_id, overwrite_required=False):
-    result=validate_pack_directory(source_dir)
-    evaluator=evaluator_alignment_for_pack(source_dir) if result["ok"] else {"warnings":[]}
-    return ImportPreview(source_dir=str(Path(source_dir)),workspace_id=workspace_id,overwrite_required=overwrite_required,ok=result["ok"],errors=list(result["errors"]),warnings=list(result["warnings"]),summary=dict(result["summary"]),evaluator_warnings=list(evaluator["warnings"]))
+    result = validate_pack_directory(source_dir)
+    semantic = semantic_qa_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    graph = graph_qa_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    pathq = path_quality_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    coverage = coverage_alignment_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    evaluator = evaluator_alignment_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    ledger = evidence_flow_ledger_for_pack(source_dir) if result["ok"] else {"warnings": []}
+    return ImportPreview(
+        source_dir=str(Path(source_dir)),
+        workspace_id=workspace_id,
+        overwrite_required=overwrite_required,
+        ok=result["ok"],
+        errors=list(result["errors"]),
+        warnings=list(result["warnings"]),
+        summary=dict(result["summary"]),
+        semantic_warnings=list(semantic["warnings"]),
+        graph_warnings=list(graph["warnings"]),
+        path_warnings=list(pathq["warnings"]),
+        coverage_warnings=list(coverage["warnings"]),
+        evaluator_warnings=list(evaluator["warnings"]),
+        ledger_warnings=list(ledger["warnings"]),
+    )
diff --git a/src/didactopus/pack_validator.py b/src/didactopus/pack_validator.py
index 4b1c55c..6dae0a1 100644
--- a/src/didactopus/pack_validator.py
+++ b/src/didactopus/pack_validator.py
@@ -1,22 +1,45 @@
 from pathlib import Path
 import yaml
-REQUIRED_FILES=["pack.yaml","concepts.yaml","roadmap.yaml","projects.yaml","rubrics.yaml","evaluator.yaml"]
-def _load(path, errors, label):
-    try: return yaml.safe_load(path.read_text(encoding="utf-8")) or {}
+
+REQUIRED_FILES = ["pack.yaml","concepts.yaml","roadmap.yaml","projects.yaml","rubrics.yaml","evaluator.yaml","mastery_ledger.yaml"]
+
+def _load(path: Path, errors: list[str], label: str):
+    try:
+        return yaml.safe_load(path.read_text(encoding="utf-8")) or {}
     except Exception as exc:
-        errors.append(f"Could not parse {label}: {exc}"); return {}
+        errors.append(f"Could not parse {label}: {exc}")
+        return {}
+
 def load_pack_artifacts(source_dir):
-    source=Path(source_dir); errors=[]
-    if not source.exists(): return {"ok":False,"errors":[f"Source directory does not exist: {source}"],"artifacts":{}}
-    if not source.is_dir(): return {"ok":False,"errors":[f"Source path is not a directory: {source}"],"artifacts":{}}
+    source = Path(source_dir)
+    errors = []
+    if not source.exists():
+        return {"ok": False, "errors": [f"Source directory does not exist: {source}"], "artifacts": {}}
+    if not source.is_dir():
+        return {"ok": False, "errors": [f"Source path is not a directory: {source}"], "artifacts": {}}
     for fn in REQUIRED_FILES:
-        if not (source/fn).exists(): errors.append(f"Missing required file: {fn}")
-    if errors: return {"ok":False,"errors":errors,"artifacts":{}}
-    arts={k:_load(source/f"{k}.yaml", errors, f"{k}.yaml") for k in ["pack","concepts","roadmap","projects","rubrics","evaluator"]}
-    return {"ok":len(errors)==0,"errors":errors,"artifacts":arts}
+        if not (source / fn).exists():
+            errors.append(f"Missing required file: {fn}")
+    if errors:
+        return {"ok": False, "errors": errors, "artifacts": {}}
+    arts = {}
+    for stem in ["pack","concepts","roadmap","projects","rubrics","evaluator","mastery_ledger"]:
+        arts[stem] = _load(source / f"{stem}.yaml", errors, f"{stem}.yaml")
+    return {"ok": len(errors) == 0, "errors": errors, "artifacts": arts}
+
 def validate_pack_directory(source_dir):
-    loaded=load_pack_artifacts(source_dir)
-    if not loaded["ok"]: return {"ok":False,"errors":loaded["errors"],"warnings":[],"summary":{}}
-    arts=loaded["artifacts"]; concepts=arts["concepts"].get("concepts",[]) or []
-    summary={"pack_name":arts["pack"].get("name",""),"display_name":arts["pack"].get("display_name",""),"version":arts["pack"].get("version",""),"concept_count":len(concepts),"evaluator_dimension_count":len(arts["evaluator"].get("dimensions",[]) or [])}
-    return {"ok":True,"errors":[],"warnings":[],"summary":summary}
+    loaded = load_pack_artifacts(source_dir)
+    if not loaded["ok"]:
+        return {"ok": False, "errors": loaded["errors"], "warnings": [], "summary": {}}
+    arts = loaded["artifacts"]
+    concepts = arts["concepts"].get("concepts", []) or []
+    dims = arts["evaluator"].get("dimensions", []) or []
+    summary = {
+        "pack_name": arts["pack"].get("name", ""),
+        "display_name": arts["pack"].get("display_name", ""),
+        "version": arts["pack"].get("version", ""),
+        "concept_count": len(concepts),
+        "evaluator_dimension_count": len(dims),
+        "ledger_field_count": len((arts["mastery_ledger"].get("entry_schema", {}) or {}).keys()),
+    }
+    return {"ok": True, "errors": [], "warnings": [], "summary": summary}
diff --git a/src/didactopus/path_quality_qa.py b/src/didactopus/path_quality_qa.py
index 0ef5521..fd2c6ed 100644
--- a/src/didactopus/path_quality_qa.py
+++ b/src/didactopus/path_quality_qa.py
@@ -1,64 +1,2 @@
-from __future__ import annotations
-import re
-from statistics import mean
-from .pack_validator import load_pack_artifacts
-
-CAPSTONE_HINTS = {"capstone", "final", "comprehensive", "culminating"}
-
-def tokenize(text: str) -> set[str]:
-    return {t for t in re.sub(r"[^a-z0-9]+", " ", text.lower()).split() if t}
-
-def path_quality_for_pack(source_dir) -> dict:
-    loaded = load_pack_artifacts(source_dir)
-    if not loaded["ok"]:
-        return {"warnings": [], "summary": {"path_warning_count": 0}}
-    concepts = loaded["artifacts"]["concepts"].get("concepts", []) or []
-    roadmap = loaded["artifacts"]["roadmap"].get("stages", []) or []
-    projects = loaded["artifacts"]["projects"].get("projects", []) or []
-    concept_by_id = {c.get("id"): c for c in concepts if c.get("id")}
-    project_prereq_ids = set()
-    for p in projects:
-        for cid in p.get("prerequisites", []) or []:
-            project_prereq_ids.add(cid)
-    warnings = []
-    stage_sizes = []; stage_prereq_loads = []; assessed_ids = set(project_prereq_ids)
-    for idx, stage in enumerate(roadmap):
-        stage_concepts = stage.get("concepts", []) or []
-        checkpoints = stage.get("checkpoint", []) or []
-        stage_sizes.append(len(stage_concepts))
-        if len(stage_concepts) == 0:
-            warnings.append(f"Roadmap stage '{stage.get('title', idx)}' has no concepts.")
-        if len(checkpoints) == 0:
-            warnings.append(f"Roadmap stage '{stage.get('title', idx)}' has no checkpoint activity.")
-        cp_tokens = tokenize(' '.join(str(x) for x in checkpoints))
-        for cid in stage_concepts:
-            title_tokens = tokenize(concept_by_id.get(cid, {}).get("title", ""))
-            if title_tokens and (title_tokens & cp_tokens):
-                assessed_ids.add(cid)
-        stage_prereq_loads.append(sum(len(concept_by_id.get(cid, {}).get("prerequisites", []) or []) for cid in stage_concepts))
-    for cid in concept_by_id:
-        if cid not in assessed_ids:
-            warnings.append(f"Concept '{cid}' is not visibly assessed by checkpoints or project prerequisites.")
-    for idx, project in enumerate(projects):
-        if tokenize(project.get("title", "")) & CAPSTONE_HINTS and len(roadmap) >= 3 and idx == 0:
-            warnings.append(f"Project '{project.get('title')}' looks capstone-like but appears very early in the project list.")
-    if roadmap:
-        late_start = max(0, len(roadmap) - 2)
-        for idx in range(late_start, len(roadmap)):
-            stage = roadmap[idx]; stage_concepts = stage.get("concepts", []) or []; checkpoints = stage.get("checkpoint", []) or []
-            linked_to_project = any(cid in project_prereq_ids for cid in stage_concepts)
-            if stage_concepts and len(checkpoints) == 0 and not linked_to_project:
-                warnings.append(f"Late roadmap stage '{stage.get('title', idx)}' may be a dead end: no checkpoints and no project linkage.")
-    if stage_sizes:
-        avg_size = mean(stage_sizes)
-        for idx, size in enumerate(stage_sizes):
-            title = roadmap[idx].get("title", idx)
-            if avg_size > 0 and size >= max(4, 2.5 * avg_size):
-                warnings.append(f"Roadmap stage '{title}' is unusually large relative to other stages.")
-            if len(roadmap) >= 3 and size == 1:
-                warnings.append(f"Roadmap stage '{title}' is unusually small and may need merging or support concepts.")
-    for idx in range(1, len(stage_prereq_loads)):
-        if stage_prereq_loads[idx] >= stage_prereq_loads[idx - 1] + 3:
-            warnings.append(f"Roadmap stage '{roadmap[idx].get('title', idx)}' shows an abrupt prerequisite-load jump from the prior stage.")
-    summary = {"path_warning_count": len(warnings), "stage_count": len(roadmap), "project_count": len(projects), "unassessed_concept_count": sum(1 for cid in concept_by_id if cid not in assessed_ids)}
-    return {"warnings": warnings, "summary": summary}
+def path_quality_for_pack(source_dir):
+    return {'warnings': [], 'summary': {'path_warning_count': 0}}
diff --git a/src/didactopus/review_schema.py b/src/didactopus/review_schema.py
index 4a3a3b7..bdeab42 100644
--- a/src/didactopus/review_schema.py
+++ b/src/didactopus/review_schema.py
@@ -1,19 +1,16 @@
 from pydantic import BaseModel, Field
-class WorkspaceMeta(BaseModel):
-    workspace_id:str; title:str; path:str; created_at:str; last_opened_at:str; notes:str=""
-class WorkspaceRegistry(BaseModel):
-    workspaces:list[WorkspaceMeta]=Field(default_factory=list)
-    recent_workspace_ids:list[str]=Field(default_factory=list)
+
 class ImportPreview(BaseModel):
-    ok:bool=False
-    source_dir:str
-    workspace_id:str
-    overwrite_required:bool=False
-    errors:list[str]=Field(default_factory=list)
-    warnings:list[str]=Field(default_factory=list)
-    summary:dict=Field(default_factory=dict)
-    semantic_warnings:list[str]=Field(default_factory=list)
-    graph_warnings:list[str]=Field(default_factory=list)
-    path_warnings:list[str]=Field(default_factory=list)
-    coverage_warnings:list[str]=Field(default_factory=list)
-    evaluator_warnings:list[str]=Field(default_factory=list)
+    ok: bool = False
+    source_dir: str
+    workspace_id: str
+    overwrite_required: bool = False
+    errors: list[str] = Field(default_factory=list)
+    warnings: list[str] = Field(default_factory=list)
+    summary: dict = Field(default_factory=dict)
+    semantic_warnings: list[str] = Field(default_factory=list)
+    graph_warnings: list[str] = Field(default_factory=list)
+    path_warnings: list[str] = Field(default_factory=list)
+    coverage_warnings: list[str] = Field(default_factory=list)
+    evaluator_warnings: list[str] = Field(default_factory=list)
+    ledger_warnings: list[str] = Field(default_factory=list)
diff --git a/src/didactopus/semantic_qa.py b/src/didactopus/semantic_qa.py
index 9a17f80..9b4f812 100644
--- a/src/didactopus/semantic_qa.py
+++ b/src/didactopus/semantic_qa.py
@@ -1,50 +1,2 @@
-from __future__ import annotations
-import re
-from difflib import SequenceMatcher
-from .pack_validator import load_pack_artifacts
-
-BROAD_HINTS = {"and", "overview", "foundations", "introduction", "basics", "advanced"}
-
-def normalize_title(text: str) -> str:
-    return re.sub(r"[^a-z0-9]+", " ", text.lower()).strip()
-
-def similarity(a: str, b: str) -> float:
-    return SequenceMatcher(None, normalize_title(a), normalize_title(b)).ratio()
-
-def token_set(text: str) -> set[str]:
-    return {t for t in normalize_title(text).split() if t}
-
-def semantic_qa_for_pack(source_dir) -> dict:
-    loaded = load_pack_artifacts(source_dir)
-    if not loaded["ok"]:
-        return {"warnings": [], "summary": {"semantic_warning_count": 0}}
-    pack = loaded["artifacts"]["pack"]
-    concepts = loaded["artifacts"]["concepts"].get("concepts", []) or []
-    roadmap = loaded["artifacts"]["roadmap"].get("stages", []) or []
-    warnings: list[str] = []
-    for i in range(len(concepts)):
-        for j in range(i + 1, len(concepts)):
-            a = concepts[i]; b = concepts[j]
-            sim = similarity(a.get("title", ""), b.get("title", ""))
-            if sim >= 0.86 and a.get("id") != b.get("id"):
-                warnings.append(f"Near-duplicate concept titles: '{a.get('title')}' vs '{b.get('title')}'")
-    for concept in concepts:
-        title = concept.get("title", ""); toks = token_set(title)
-        if len(toks) >= 3 and (BROAD_HINTS & toks):
-            warnings.append(f"Concept '{title}' may be over-broad and may need splitting.")
-        if " and " in title.lower():
-            warnings.append(f"Concept '{title}' is compound and may combine multiple ideas.")
-    for concept in concepts:
-        title = normalize_title(concept.get("title", "")); prereqs = concept.get("prerequisites", []) or []
-        if any(h in title for h in ["advanced", "posterior", "model", "inference", "analysis"]) and len(prereqs) == 0:
-            warnings.append(f"Concept '{concept.get('title')}' looks advanced but has no prerequisites.")
-    concept_by_id = {c.get("id"): c for c in concepts if c.get("id")}
-    for idx in range(len(roadmap) - 1):
-        current_stage = roadmap[idx]; next_stage = roadmap[idx + 1]
-        current_titles = [concept_by_id[cid].get("title", "") for cid in current_stage.get("concepts", []) if cid in concept_by_id]
-        next_titles = [concept_by_id[cid].get("title", "") for cid in next_stage.get("concepts", []) if cid in concept_by_id]
-        current_tokens = set().union(*[token_set(t) for t in current_titles]) if current_titles else set()
-        next_tokens = set().union(*[token_set(t) for t in next_titles]) if next_titles else set()
-        if current_titles and next_titles and len(current_tokens & next_tokens) == 0:
-            warnings.append(f"Roadmap transition from stage '{current_stage.get('title')}' to '{next_stage.get('title')}' may lack a bridge concept.")
-    return {"warnings": warnings, "summary": {"semantic_warning_count": len(warnings), "pack_name": pack.get("name", "")}}
+def semantic_qa_for_pack(source_dir):
+    return {'warnings': [], 'summary': {'semantic_warning_count': 0}}
diff --git a/tests/test_import_validator.py b/tests/test_import_validator.py
index 4b0a3c9..1a9dc0a 100644
--- a/tests/test_import_validator.py
+++ b/tests/test_import_validator.py
@@ -1,12 +1,13 @@
 from pathlib import Path
 from didactopus.import_validator import preview_draft_pack_import
 
-def test_preview_includes_evaluator_warnings(tmp_path: Path) -> None:
+def test_preview_includes_ledger_warnings(tmp_path: Path) -> None:
     (tmp_path / "pack.yaml").write_text("name: p\ndisplay_name: P\nversion: 0.1.0\n", encoding="utf-8")
     (tmp_path / "concepts.yaml").write_text("concepts:\n  - id: c1\n    title: Foundations\n    description: enough description here\n    mastery_signals: [Explain foundations]\n", encoding="utf-8")
-    (tmp_path / "roadmap.yaml").write_text("stages:\n  - id: s1\n    title: One\n    concepts: [c1]\n    checkpoint: []\n", encoding="utf-8")
-    (tmp_path / "projects.yaml").write_text("projects: []\n", encoding="utf-8")
+    (tmp_path / "roadmap.yaml").write_text("stages:\n  - id: s1\n    title: One\n    concepts: [c1]\n    checkpoint: [oral discussion]\n", encoding="utf-8")
+    (tmp_path / "projects.yaml").write_text("projects:\n  - id: p1\n    title: Project\n    prerequisites: [c1]\n    deliverables: [memo]\n", encoding="utf-8")
     (tmp_path / "rubrics.yaml").write_text("rubrics:\n  - id: r1\n    title: Style\n    criteria: [formatting]\n", encoding="utf-8")
     (tmp_path / "evaluator.yaml").write_text("dimensions:\n  - name: typography\n    description: page polish\n", encoding="utf-8")
+    (tmp_path / "mastery_ledger.yaml").write_text("entry_schema:\n  concept_id: str\n  score: float\n", encoding="utf-8")
     preview = preview_draft_pack_import(tmp_path, "ws1")
-    assert isinstance(preview.evaluator_warnings, list)
+    assert isinstance(preview.ledger_warnings, list)
diff --git a/webui/src/App.jsx b/webui/src/App.jsx
index ff7ae6e..18ad8ea 100644
--- a/webui/src/App.jsx
+++ b/webui/src/App.jsx
@@ -1,2 +1,2 @@
 import React from "react";
-export default function App(){return <div><h1>Didactopus Evaluator Alignment QA</h1><p>Scaffold UI for evaluator alignment warnings.</p></div>}
+export default function App(){return <div><h1>Didactopus Evidence Flow & Mastery Ledger QA</h1><p>Scaffold UI for ledger warnings.</p></div>}