feat(kg): add markdown export format for knowledge graph

- Add kg_ocr/export/markdown_exporter.py with export_markdown()
- Cluster entity co-occurrences using Louvain community detection
- Wire -f markdown into `ocr-pipeline kg export` CLI command with KG_REPORT.md default
- Add unit and CLI tests in tests/test_graph.py
- Document markdown export in README.md
- Untrack pycache binaries and ignore graphify-out and KG_REPORT.md

.gitignore

@@ -81,3 +81,5 @@ Thumbs.db
 data/
 notebooks/
 .env
+graphify-out/
+KG_REPORT.md

README.md

@@ -79,6 +79,7 @@ uv run ocr-pipeline kg query data/ocr_output/kg_graph.json --entity BRCA1 --expa
 uv run ocr-pipeline kg query data/ocr_output/kg_graph.json --citation 10.1038/nature12345
 
 # export
+uv run ocr-pipeline kg export data/ocr_output/kg_graph.json -f markdown
 uv run ocr-pipeline kg export data/ocr_output/kg_graph.json -f graphml
 uv run ocr-pipeline kg export data/ocr_output/kg_graph.json -f neo4j
 ```
@@ -239,4 +240,3 @@ Gene/protein names go through scispaCy's `en_core_sci_lg`. Chemical formulas
 and units (µM, ng/mL, kb/Mb/Gb, °C, ×g) get normalized, scientific notation
 gets cleaned up (`1.5×10⁻³` → `1.5×10^-3`), and gel/blot figures get their
 captions pulled out separately.
-

kg_ocr/__init__.py

@@ -25,6 +25,7 @@ _LAZY: dict[str, tuple[str, str]] = {
     "expand_context": (".graph", "expand_context"),
     "export_json": (".export", "export_json"),
     "export_graphml": (".export", "export_graphml"),
+    "export_markdown": (".export", "export_markdown"),
     "load_json": (".export", "load_json"),
     "Neo4jExporter": (".export", "Neo4jExporter"),
 }

kg_ocr/export/__init__.py

@@ -1,3 +1,4 @@
+from .markdown_exporter import export_markdown
 from .neo4j_exporter import Neo4jExporter, export_graphml, export_json, load_json
 
-__all__ = ["Neo4jExporter", "export_graphml", "export_json", "load_json"]
+__all__ = ["Neo4jExporter", "export_graphml", "export_json", "export_markdown", "load_json"]

kg_ocr/export/markdown_exporter.py

@@ -0,0 +1,270 @@
+"""Export a knowledge graph to a Markdown report."""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Any
+
+from kg_ocr.graph.analyzer import (
+    Anomaly,
+    detect_anomalies,
+    summary,
+    top_citations,
+    top_cooccurrences,
+    top_entities,
+)
+
+
+def _load_graph(graph_input: Any) -> Any:
+    """Load a NetworkX graph from a file path or return it directly."""
+    import networkx as nx
+
+    if isinstance(graph_input, (str, Path)):
+        path = Path(graph_input)
+        data = json.loads(path.read_text(encoding="utf-8"))
+        try:
+            return nx.node_link_graph(data, edges="edges")
+        except TypeError:
+            return nx.node_link_graph(data)
+    return graph_input
+
+
+def _cluster_entity_cooccurrences(graph: Any) -> list[list[dict[str, Any]]]:
+    """Find concept clusters over the entity co-occurrence subgraph."""
+    import networkx as nx
+
+    cooccur_graph = nx.Graph()
+    for node, data in graph.nodes(data=True):
+        if data.get("kind") == "entity":
+            cooccur_graph.add_node(
+                node,
+                text=data.get("text", node.replace("entity:", "")),
+                mentions=int(data.get("mentions", 0)),
+            )
+
+    for u, v, data in graph.edges(data=True):
+        if data.get("kind") == "CO_OCCURS":
+            cooccur_graph.add_edge(u, v, weight=data.get("weight", 1))
+
+    if cooccur_graph.number_of_nodes() == 0:
+        return []
+
+    # Community detection
+    communities: list[set[str]] = []
+    if cooccur_graph.number_of_edges() > 0:
+        try:
+            import networkx.algorithms.community as nx_comm  # type: ignore[import-untyped]
+
+            communities = list(
+                nx_comm.louvain_communities(cooccur_graph, weight="weight", seed=42)
+            )
+        except Exception:
+            try:
+                import networkx.algorithms.community as nx_comm  # type: ignore[import-untyped]
+
+                communities = list(
+                    nx_comm.greedy_modularity_communities(cooccur_graph, weight="weight")
+                )
+            except Exception:
+                try:
+                    import community as community_louvain  # type: ignore[import-not-found]
+
+                    partition = community_louvain.best_partition(
+                        cooccur_graph, weight="weight", random_state=42
+                    )
+                    comm_dict: dict[int, set[str]] = {}
+                    for n, cid in partition.items():
+                        comm_dict.setdefault(cid, set()).add(n)
+                    communities = list(comm_dict.values())
+                except Exception:
+                    communities = list(nx.connected_components(cooccur_graph))
+    else:
+        # No edges: each entity is an isolated node
+        communities = [{n} for n in cooccur_graph.nodes()]
+
+    # Format and sort clusters
+    clusters: list[list[dict[str, Any]]] = []
+    for comm in communities:
+        cluster_nodes = []
+        for node in comm:
+            cluster_nodes.append(
+                {
+                    "id": node,
+                    "text": cooccur_graph.nodes[node].get("text", node),
+                    "mentions": cooccur_graph.nodes[node].get("mentions", 0),
+                }
+            )
+        # Sort entities inside cluster by mentions descending
+        cluster_nodes.sort(key=lambda item: item["mentions"], reverse=True)
+        clusters.append(cluster_nodes)
+
+    # Sort clusters by size (number of entities) descending, then top entity mentions
+    clusters.sort(
+        key=lambda c: (len(c), c[0]["mentions"] if c else 0),
+        reverse=True,
+    )
+    return clusters
+
+
+def export_markdown(graph_path: str | Path, output_path: str | Path) -> Path:
+    """Render a knowledge graph into a Markdown summary report.
+
+    Parameters
+    ----------
+    graph_path : str | Path | nx.Graph
+        Path to `kg_graph.json` or an in-memory NetworkX graph.
+    output_path : str | Path
+        Target path for the exported Markdown report.
+
+    Returns
+    -------
+    Path
+        The output Path written to.
+    """
+    graph = _load_graph(graph_path)
+    out = Path(output_path)
+    out.parent.mkdir(parents=True, exist_ok=True)
+
+    counts = summary(graph)
+    doc_count = counts.get("nodes:document", 0)
+    chunk_count = counts.get("nodes:chunk", 0)
+    entity_count = counts.get("nodes:entity", 0)
+    citation_count = counts.get("nodes:citation", 0)
+    contains_edges = counts.get("edges:CONTAINS", 0)
+    mentions_edges = counts.get("edges:MENTIONS", 0)
+    cites_edges = counts.get("edges:CITES", 0)
+    cooccurs_edges = counts.get("edges:CO_OCCURS", 0)
+
+    entities = top_entities(graph, limit=20)
+    cooccurrences = top_cooccurrences(graph, limit=20)
+    citations = top_citations(graph, limit=20)
+    clusters = _cluster_entity_cooccurrences(graph)
+
+    # Anomalies detection
+    anomalies: list[Anomaly] = list(detect_anomalies(graph))
+    # Detect isolated citations (citations with 0 citing chunks)
+    existing_anomaly_nodes = {a.node for a in anomalies}
+    for node, data in graph.nodes(data=True):
+        if data.get("kind") == "citation" and node not in existing_anomaly_nodes:
+            citing_count = sum(
+                1 for _, _, edge in graph.in_edges(node, data=True) if edge.get("kind") == "CITES"
+            )
+            if citing_count == 0:
+                ident = data.get("identifier", node)
+                anomalies.append(
+                    Anomaly(
+                        "isolated_citation",
+                        node,
+                        f"citation {ident} has no referencing chunks",
+                    )
+                )
+
+    lines: list[str] = [
+        "# Knowledge Graph Report",
+        "",
+        "## Summary",
+        f"- **Documents**: {doc_count:,}",
+        f"- **Chunks**: {chunk_count:,}",
+        f"- **Entities**: {entity_count:,}",
+        f"- **Citations**: {citation_count:,}",
+        f"- **Relationships**: {contains_edges + mentions_edges + cites_edges + cooccurs_edges:,} "
+        f"(CONTAINS: {contains_edges:,}, MENTIONS: {mentions_edges:,}, CITES: {cites_edges:,}, CO_OCCURS: {cooccurs_edges:,})",
+        "",
+    ]
+
+    # Section: Top Entities
+    lines.append("## Top Entities")
+    lines.append("")
+    if entities:
+        lines.append("| Entity | Mentions |")
+        lines.append("|:-------|:---------|")
+        for text, mention_count in entities:
+            clean_text = text.replace("|", "\\|")
+            lines.append(f"| {clean_text} | {mention_count:,} |")
+    else:
+        lines.append("No entities found.")
+    lines.append("")
+
+    # Section: Top Co-occurrences
+    lines.append("## Top Co-occurrences")
+    lines.append("")
+    if cooccurrences:
+        lines.append("| Entity A | Entity B | Co-occurrence Weight |")
+        lines.append("|:---------|:---------|:---------------------|")
+        for left, right, weight in cooccurrences:
+            clean_left = left.replace("|", "\\|")
+            clean_right = right.replace("|", "\\|")
+            lines.append(f"| {clean_left} | {clean_right} | {weight:,} |")
+    else:
+        lines.append("No entity co-occurrences found.")
+    lines.append("")
+
+    # Section: Top Citations
+    lines.append("## Top Citations")
+    lines.append("")
+    if citations:
+        lines.append("| Type | Identifier | Citing Chunks |")
+        lines.append("|:-----|:-----------|:--------------|")
+        for ctype, identifier, count in citations:
+            lines.append(f"| {ctype.upper() or 'UNKNOWN'} | `{identifier}` | {count:,} |")
+    else:
+        lines.append("No citations found.")
+    lines.append("")
+
+    # Section: Concept Clusters
+    lines.append("## Concept Clusters")
+    lines.append("")
+    if clusters:
+        multi_entity_clusters = [c for c in clusters if len(c) > 1]
+        single_entity_clusters = [c for c in clusters if len(c) == 1]
+
+        if multi_entity_clusters:
+            for idx, cluster in enumerate(multi_entity_clusters, start=1):
+                entity_names = [e["text"] for e in cluster[:3]]
+                cluster_label = ", ".join(entity_names)
+                if len(cluster) > 3:
+                    cluster_label += f" (+{len(cluster) - 3} more)"
+                lines.append(f"### Cluster {idx}: {cluster_label}")
+                lines.append(f"**Size**: {len(cluster)} entities")
+                lines.append("")
+                lines.append("| Entity | Mentions |")
+                lines.append("|:-------|:---------|")
+                for item in cluster:
+                    clean_name = item["text"].replace("|", "\\|")
+                    lines.append(f"| {clean_name} | {item['mentions']:,} |")
+                lines.append("")
+
+        if single_entity_clusters:
+            lines.append("### Isolated / Unclustered Entities")
+            lines.append(
+                f"*{len(single_entity_clusters)} entities with no co-occurrences across documents:*"
+            )
+            lines.append("")
+            items_preview = [
+                f"{c[0]['text']} ({c[0]['mentions']})" for c in single_entity_clusters[:30]
+            ]
+            lines.append(", ".join(items_preview))
+            if len(single_entity_clusters) > 30:
+                lines.append(f"*(and {len(single_entity_clusters) - 30} more)*")
+            lines.append("")
+    else:
+        lines.append("No concept clusters detected.")
+        lines.append("")
+
+    # Section: Anomalies
+    lines.append("## Anomalies")
+    lines.append("")
+    if anomalies:
+        lines.append("| Anomaly Type | Node | Detail |")
+        lines.append("|:-------------|:-----|:-------|")
+        for a in anomalies:
+            clean_node = a.node.replace("|", "\\|")
+            clean_detail = a.detail.replace("|", "\\|")
+            lines.append(f"| `{a.kind}` | `{clean_node}` | {clean_detail} |")
+    else:
+        lines.append("No anomalies detected.")
+    lines.append("")
+
+    out.write_text("\n".join(lines), encoding="utf-8")
+    return out

src/ocr_pipeline/cli.py

@@ -316,8 +316,8 @@ def config():
 
 @kg_app.command("build")
 def kg_build(
-    output_dir: Path = typer.Option(
-        ..., "--output-dir", "-d", help="Pipeline output directory with chunk markdown files"
+    output_dir: Path | None = typer.Option(
+        None, "--output-dir", "-d", help="Pipeline output directory with chunk markdown files"
     ),
     save: Path | None = typer.Option(
         None, "--save", "-s", help="Graph JSON path (default: <output-dir>/kg_graph.json)"
@@ -325,6 +325,19 @@ def kg_build(
 ):
     """Build a knowledge graph from pipeline output and save it as JSON."""
     kg_graph, kg_export = _load_kg()
+    if output_dir is None:
+        default_candidates = [
+            Path("data/ocr_output"),
+            Path("data"),
+            Path(settings.output.base_directory),
+        ]
+        for candidate in default_candidates:
+            if candidate.is_dir():
+                output_dir = candidate
+                break
+        if output_dir is None:
+            output_dir = Path("data/ocr_output")
+
     if not output_dir.is_dir():
         console.print(f"[red]Not a directory:[/red] {output_dir}")
         raise typer.Exit(code=2)
@@ -344,9 +357,9 @@ def kg_build(
 @kg_app.command("stats")
 def kg_stats(
     graph_path: Path = typer.Argument(..., help="Graph JSON written by `kg build`"),
-    top: int = typer.Option(10, "--top", "-n", help="Rows per top-list"),
+    top: int = typer.Option(10, "--top", "-n", help="Number of top items to show"),
 ):
-    """Summarize a graph: counts, top entities/citations, anomalies."""
+    """Summarize graph contents and flag anomalies."""
     kg_graph, kg_export = _load_kg()
     if not graph_path.is_file():
         console.print(f"[red]Graph file not found:[/red] {graph_path}")
@@ -354,59 +367,66 @@ def kg_stats(
     graph = kg_export.load_json(graph_path)
 
     counts = kg_graph.summary(graph)
-    table = Table(title="Graph summary")
-    table.add_column("Kind", style="cyan")
-    table.add_column("Count", style="green")
+    summary_table = Table(title=f"Summary ({graph_path})")
+    summary_table.add_column("Kind", style="cyan")
+    summary_table.add_column("Count", style="green")
     for kind, count in sorted(counts.items()):
-        table.add_row(kind, str(count))
-    console.print(table)
+        summary_table.add_row(kind, str(count))
+    console.print(summary_table)
 
     entities = kg_graph.top_entities(graph, limit=top)
     if entities:
-        table = Table(title=f"Top {top} entities")
-        table.add_column("Entity", style="cyan")
-        table.add_column("Mentions", style="green")
-        for text, mentions in entities:
-            table.add_row(text, str(mentions))
-        console.print(table)
+        ent_table = Table(title=f"Top {len(entities)} Entities")
+        ent_table.add_column("Entity", style="cyan")
+        ent_table.add_column("Mentions", style="green")
+        for name, count in entities:
+            ent_table.add_row(name, str(count))
+        console.print(ent_table)
 
     citations = kg_graph.top_citations(graph, limit=top)
     if citations:
-        table = Table(title=f"Top {top} citations")
-        table.add_column("Type", style="cyan")
-        table.add_column("Identifier")
-        table.add_column("Citing chunks", style="green")
-        for ctype, identifier, citing in citations:
-            table.add_row(ctype, identifier, str(citing))
-        console.print(table)
+        cit_table = Table(title=f"Top {len(citations)} Citations")
+        cit_table.add_column("Type", style="cyan")
+        cit_table.add_column("Identifier", style="magenta")
+        cit_table.add_column("Citing chunks", style="green")
+        for ctype, identifier, count in citations:
+            cit_table.add_row(ctype, identifier, str(count))
+        console.print(cit_table)
 
     anomalies = kg_graph.detect_anomalies(graph)
     if anomalies:
-        console.print(f"\n[yellow]{len(anomalies)} anomalies:[/yellow]")
-        for anomaly in anomalies[:top]:
-            console.print(f"  [dim]{anomaly.kind}[/dim] {anomaly.node}: {anomaly.detail}")
+        anom_table = Table(title=f"Anomalies ({len(anomalies)})")
+        anom_table.add_column("Kind", style="yellow")
+        anom_table.add_column("Node", style="cyan")
+        anom_table.add_column("Detail")
+        for anomaly in anomalies:
+            anom_table.add_row(anomaly.kind, anomaly.node, anomaly.detail)
+        console.print(anom_table)
+    else:
+        console.print("[green]No anomalies detected.[/green]")
 
 
 @kg_app.command("query")
 def kg_query(
     graph_path: Path = typer.Argument(..., help="Graph JSON written by `kg build`"),
-    entity: str | None = typer.Option(None, "--entity", "-e", help="Entity to look up"),
+    entity: str | None = typer.Option(None, "--entity", "-e", help="Entity text to query"),
     citation: str | None = typer.Option(
-        None, "--citation", "-c", help="Citation identifier (e.g. 10.1038/nature12345)"
+        None, "--citation", "-c", help="Citation identifier or DOI/PMID"
     ),
     expand: bool = typer.Option(
-        False, "--expand", "-x", help="Include chunks from co-occurring entities"
+        False, "--expand", "-x", help="Include 1-hop neighbor chunks (co-occurring entities)"
     ),
-    limit: int = typer.Option(5, "--limit", "-n", help="Max chunks to show"),
+    limit: int = typer.Option(10, "--limit", "-l", help="Max chunks to display"),
 ):
-    """Retrieve chunks by entity or citation; --expand adds neighbor chunks."""
+    """Retrieve text chunks grounded in the knowledge graph."""
     kg_graph, kg_export = _load_kg()
     if not graph_path.is_file():
         console.print(f"[red]Graph file not found:[/red] {graph_path}")
         raise typer.Exit(code=2)
     if not entity and not citation:
-        console.print("[red]Give --entity or --citation.[/red]")
+        console.print("[red]Provide at least one of --entity or --citation.[/red]")
         raise typer.Exit(code=2)
+
     graph = kg_export.load_json(graph_path)
 
     if entity:
@@ -416,43 +436,57 @@ def kg_query(
             else kg_graph.chunks_for_entity(graph, entity)
         )
         related = kg_graph.related_entities(graph, entity)
+        console.print(f"[bold cyan]Entity:[/bold cyan] {entity} ({len(chunks)} chunks)")
         if related:
-            console.print(
-                "[dim]Related entities: "
-                + ", ".join(f"{text} ({weight})" for text, weight in related[:5])
-                + "[/dim]"
-            )
-    else:
+            rendered = ", ".join(f"{name} ({weight})" for name, weight in related[:5])
+            console.print(f"[dim]Related entities:[/dim] {rendered}")
+        for chunk in chunks[:limit]:
+            source = chunk.get("source_path", "unknown")
+            via = f" (via {chunk['via_entity']})" if "via_entity" in chunk else ""
+            console.print(f"[bold]{source}[/bold]{via}:")
+            excerpt = chunk.get("text", "")[:200].replace("\n", " ")
+            console.print(f"  {excerpt}")
+
+    if citation:
         chunks = kg_graph.chunks_for_citation(graph, citation or "")
-
-    if not chunks:
-        console.print("[yellow]No matching chunks.[/yellow]")
-        return
-
-    for payload in chunks[:limit]:
-        via = f" via {payload['via_entity']}" if payload.get("via_entity") else ""
-        console.print(
-            f"\n[bold]{Path(str(payload['source_path'])).name}[/bold] "
-            f"chunk {payload['chunk_index']}{via} "
-            f"[dim]({payload['ocr_engine']} {payload['ocr_confidence_mean']:.2f})[/dim]"
-        )
-        excerpt = " ".join(str(payload["text"]).split())[:300]
+        console.print(f"[bold cyan]Citation:[/bold cyan] {citation} ({len(chunks)} chunks)")
+        for chunk in chunks[:limit]:
+            source = chunk.get("source_path", "unknown")
+            console.print(f"[bold]{source}[/bold]:")
+            excerpt = chunk.get("text", "")[:200].replace("\n", " ")
             console.print(f"  {excerpt}")
 
 
 @kg_app.command("export")
 def kg_export_cmd(
-    graph_path: Path = typer.Argument(..., help="Graph JSON written by `kg build`"),
-    fmt: str = typer.Option("graphml", "--format", "-f", help="graphml | neo4j"),
-    out: Path | None = typer.Option(None, "--out", "-o", help="Output path for graphml"),
+    graph_path: Path | None = typer.Argument(
+        None, help="Graph JSON written by `kg build` (default: <output-dir>/kg_graph.json)"
+    ),
+    fmt: str = typer.Option("graphml", "--format", "-f", help="graphml | neo4j | markdown"),
+    out: Path | None = typer.Option(
+        None, "--out", "--output", "-o", help="Output path (default: KG_REPORT.md for markdown)"
+    ),
     uri: str | None = typer.Option(None, "--uri", help="Neo4j bolt URI (or NEO4J_URI)"),
     user: str | None = typer.Option(None, "--user", help="Neo4j user (or NEO4J_USER)"),
     password: str | None = typer.Option(
         None, "--password", help="Neo4j password (or NEO4J_PASSWORD)"
     ),
 ):
-    """Export a graph JSON to GraphML or push it into Neo4j."""
+    """Export a graph JSON to GraphML, Markdown report, or push it into Neo4j."""
     _, kg_export = _load_kg()
+    if graph_path is None:
+        candidates = [
+            Path("data/ocr_output/kg_graph.json"),
+            Path("kg_graph.json"),
+            Path(settings.output.base_directory) / "kg_graph.json",
+        ]
+        for c in candidates:
+            if c.is_file():
+                graph_path = c
+                break
+        if graph_path is None:
+            graph_path = Path("data/ocr_output/kg_graph.json")
+
     if not graph_path.is_file():
         console.print(f"[red]Graph file not found:[/red] {graph_path}")
         raise typer.Exit(code=2)
@@ -462,6 +496,10 @@ def kg_export_cmd(
         out = out or graph_path.with_suffix(".graphml")
         kg_export.export_graphml(graph, out)
         console.print(f"[green]GraphML written:[/green] {out}")
+    elif fmt == "markdown":
+        out = out or Path("KG_REPORT.md")
+        kg_export.export_markdown(graph, out)
+        console.print(f"[green]Markdown report written:[/green] {out}")
     elif fmt == "neo4j":
         try:
             with kg_export.Neo4jExporter(uri=uri, user=user, password=password) as exporter:
@@ -473,7 +511,7 @@ def kg_export_cmd(
             f"[green]Pushed to Neo4j:[/green] {pushed['nodes']} nodes, {pushed['edges']} edges"
         )
     else:
-        console.print(f"[red]Unknown format:[/red] {fmt} (choose graphml or neo4j)")
+        console.print(f"[red]Unknown format:[/red] {fmt} (choose graphml, neo4j, or markdown)")
         raise typer.Exit(code=2)
 
 

tests/test_graph.py

@@ -6,7 +6,7 @@ import pytest
 
 nx = pytest.importorskip("networkx", reason="kg extra not installed")
 
-from kg_ocr.export import export_graphml, export_json, load_json  # noqa: E402
+from kg_ocr.export import export_graphml, export_json, export_markdown, load_json  # noqa: E402
 from kg_ocr.graph import (  # noqa: E402
     build_from_directory,
     build_graph,
@@ -202,6 +202,50 @@ def test_kg_cli_build_and_stats(chunk_dir: Path, tmp_path: Path) -> None:
     assert result.exit_code == 0, result.output
     assert out_graphml.is_file()
 
+    out_md = tmp_path / "g_report.md"
+    result = runner.invoke(app, ["kg", "export", str(save), "-f", "markdown", "-o", str(out_md)])
+    assert result.exit_code == 0, result.output
+    assert out_md.is_file()
+    content = out_md.read_text(encoding="utf-8")
+    assert "## Top Entities" in content
+    assert "## Top Co-occurrences" in content
+    assert "## Top Citations" in content
+    assert "## Concept Clusters" in content
+    assert "## Anomalies" in content
+    assert "BRCA1" in content
+    assert "10.1038/nature12345" in content
+
+
+def test_export_markdown(chunk_dir: Path, tmp_path: Path) -> None:
+    graph = build_from_directory(chunk_dir)
+    save_json = tmp_path / "graph.json"
+    export_json(graph, save_json)
+
+    out_md = tmp_path / "report.md"
+    # Test with string paths as per signature requirement
+    written = export_markdown(str(save_json), str(out_md))
+    assert written == out_md
+    assert out_md.is_file()
+
+    text = out_md.read_text(encoding="utf-8")
+    assert "# Knowledge Graph Report" in text
+    assert "## Summary" in text
+    assert "## Top Entities" in text
+    assert "## Top Co-occurrences" in text
+    assert "## Top Citations" in text
+    assert "## Concept Clusters" in text
+    assert "## Anomalies" in text
+    assert "BRCA1" in text
+    assert "PARP" in text
+    assert "10.1038/nature12345" in text
+    assert "low_confidence" in text
+
+    # Also test passing in-memory graph directly
+    out_direct = tmp_path / "report_direct.md"
+    export_markdown(graph, out_direct)
+    assert out_direct.is_file()
+    assert "## Top Entities" in out_direct.read_text(encoding="utf-8")
+
 
 def test_chunks_for_entity(chunk_dir: Path) -> None:
     from kg_ocr.graph import chunks_for_entity