Files
kwcode/kaiwu/validation/v5_conclusion.json
Val-sss ef7b0b402c AST engine + V5 validation: tree-sitter call graph +50pp over LLM guessing
New module kaiwu/ast_engine/:
- parser.py: tree-sitter Python parser, extracts functions + calls
- call_graph.py: dict-based call graph with BFS expansion
- locator.py: ASTLocator using call graph for function-level location

V5 results (gemma3:4b, 10 cases):
- Group A (LLM): file 100%, function 50%, avg 2.5s/case
- Group B (AST): file 100%, function 100%, avg 0.05s/case
- Improvement: +50pp function accuracy, 50x faster

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-27 00:36:32 +08:00

142 lines
2.7 KiB
JSON

{
"group_a": {
"method": "LLM file tree guessing (LocatorExpert)",
"file_accuracy": 100.0,
"func_accuracy": 50.0,
"results": [
{
"case_id": 1,
"file_hit": true,
"func_hit": true,
"elapsed_s": 9.2
},
{
"case_id": 2,
"file_hit": true,
"func_hit": true,
"elapsed_s": 1.1
},
{
"case_id": 3,
"file_hit": true,
"func_hit": false,
"elapsed_s": 1.1
},
{
"case_id": 4,
"file_hit": true,
"func_hit": false,
"elapsed_s": 1.2
},
{
"case_id": 5,
"file_hit": true,
"func_hit": false,
"elapsed_s": 2.2
},
{
"case_id": 6,
"file_hit": true,
"func_hit": true,
"elapsed_s": 2.4
},
{
"case_id": 7,
"file_hit": true,
"func_hit": false,
"elapsed_s": 2.6
},
{
"case_id": 8,
"file_hit": true,
"func_hit": true,
"elapsed_s": 2.3
},
{
"case_id": 9,
"file_hit": true,
"func_hit": true,
"elapsed_s": 2.3
},
{
"case_id": 10,
"file_hit": true,
"func_hit": false,
"elapsed_s": 1.1
}
]
},
"group_b": {
"method": "tree-sitter call graph (ASTLocator)",
"file_accuracy": 100.0,
"func_accuracy": 100.0,
"results": [
{
"case_id": 1,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.053
},
{
"case_id": 2,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.077
},
{
"case_id": 3,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.046
},
{
"case_id": 4,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.043
},
{
"case_id": 5,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.048
},
{
"case_id": 6,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.049
},
{
"case_id": 7,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.056
},
{
"case_id": 8,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.043
},
{
"case_id": 9,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.04
},
{
"case_id": 10,
"file_hit": true,
"func_hit": true,
"elapsed_s": 0.047
}
]
},
"comparison": {
"file_improvement_pct": 0.0,
"func_improvement_pct": 50.0,
"flex4_triggered": false
},
"total_cases": 10
}