export_claim_matrix_grouped_v1_2

Export grouped claim matrices from academic literature, organizing top claims by confidence and sign for structured analysis.

Instructions

导出分组 claim 矩阵，每组返回 top-k 代表 claims (按 confidence 排序，sign 分层)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`comm_id`	No
`pack_id`	No
`top_k_per_group`	No
`include_subgroups`	No

Implementation Reference

src/paperlib_mcp/tools/graph_v12.py:424-516 (handler)

The primary handler function implementing the logic for the 'export_claim_matrix_grouped_v1_2' tool. It queries claim groups, filters by comm_id or pack_id, retrieves top-k claims per group sorted by sign and confidence, and returns structured results.

@mcp.tool()
def export_claim_matrix_grouped_v1_2(
    comm_id: int | None = None,
    pack_id: int | None = None,
    top_k_per_group: int = 10,
    include_subgroups: bool = True,
) -> dict[str, Any]:
    """导出分组 claim 矩阵，每组返回 top-k 代表 claims (按 confidence 排序，sign 分层)"""
    try:
        # 构建过滤条件
        where_clauses = []
        params = []
        
        if comm_id:
            where_clauses.append("""
                EXISTS (
                    SELECT 1 FROM claim_group_members cgm
                    JOIN claims c ON c.claim_id = cgm.claim_id
                    JOIN mentions m ON m.doc_id = c.doc_id
                    JOIN community_members cm ON cm.entity_id = m.entity_id
                    WHERE cm.comm_id = %s AND cgm.group_id = g.group_id
                )
            """)
            params.append(comm_id)
        elif pack_id:
            where_clauses.append("""
                EXISTS (
                    SELECT 1 FROM claim_group_members cgm
                    JOIN claims c ON c.claim_id = cgm.claim_id
                    JOIN evidence_pack_items epi ON epi.chunk_id = c.chunk_id
                    WHERE epi.pack_id = %s AND cgm.group_id = g.group_id
                )
            """)
            params.append(pack_id)
        
        # 是否包含子组
        if not include_subgroups:
            where_clauses.append("g.parent_group_id IS NULL")
        
        where_sql = " WHERE " + " AND ".join(where_clauses) if where_clauses else ""
        
        # 获取分组
        groups = query_all(f"""
            SELECT 
                g.group_id, g.group_key, g.parent_group_id, g.subgroup_key,
                g.sign, g.id_family, g.setting,
                e.canonical_name as topic_name,
                (SELECT COUNT(*) FROM claim_group_members cgm WHERE cgm.group_id = g.group_id) as member_count
            FROM claim_groups g
            LEFT JOIN entities e ON e.entity_id = g.topic_entity_id
            {where_sql}
            ORDER BY member_count DESC
        """, tuple(params))
        
        # 为每个 group 获取 top-k claims（按 sign 分层 + confidence 排序）
        result_groups = []
        for g in groups:
            # 获取该组的 claims，按 sign 和 confidence 排序
            claims = query_all("""
                SELECT c.claim_id, c.doc_id, c.claim_text, c.sign, c.confidence,
                       cf.outcome_family, cf.treatment_family
                FROM claim_group_members cgm
                JOIN claims c ON c.claim_id = cgm.claim_id
                LEFT JOIN claim_features cf ON cf.claim_id = c.claim_id
                WHERE cgm.group_id = %s
                ORDER BY 
                    CASE c.sign 
                        WHEN 'positive' THEN 1 
                        WHEN 'negative' THEN 2 
                        WHEN 'mixed' THEN 3 
                        ELSE 4 
                    END,
                    c.confidence DESC
                LIMIT %s
            """, (g["group_id"], top_k_per_group))
            
            result_groups.append({
                "group_id": g["group_id"],
                "group_key": g["group_key"],
                "parent_group_id": g["parent_group_id"],
                "subgroup_key": g["subgroup_key"],
                "topic_name": g["topic_name"],
                "sign": g["sign"],
                "member_count": g["member_count"],
                "top_claims": claims,
            })
        
        return {
            "total_groups": len(result_groups),
            "groups": result_groups
        }
    except Exception as e:
        return {"error": str(e)}

src/paperlib_mcp/server.py:52-52 (registration)
The call to register_graph_v12_tools(mcp) in the main server file, which defines and registers the tool among other v1.2 GraphRAG tools.
```
register_graph_v12_tools(mcp)
```

src/paperlib_mcp/tools/graph_v12.py:17-26 (helper)

Configuration constants for v1.2 tools, defining grouping fields used in claim grouping which this export tool relies on.

V1_2_PARAMS = {
    "version": "1.2",
    "normalization": {
        "text_norm": "lower+punct+ws",
        "json_dumps": "sort_keys=True,separators=(',',':')",
        "sep": "\\u001f"
    },
    "grouping_fields": ["primary_topic_key", "outcome_family", "treatment_family", "sign", "id_family", "setting_bin"],
}

Paperlib MCP