amazon-science
diff --git a/‎.gitignore
+3-3 b/‎.gitignore
+3-3
diff --git a/‎src/llm_agent_evaluation/__init__.py ‎llm_agent_evaluation/__init__.py b/‎src/llm_agent_evaluation/__init__.py ‎llm_agent_evaluation/__init__.py
diff --git a/‎src/llm_agent_evaluation/configure.py ‎llm_agent_evaluation/configure.py b/‎src/llm_agent_evaluation/configure.py ‎llm_agent_evaluation/configure.py
diff --git a/‎src/llm_agent_evaluation/data/__init__.py ‎llm_agent_evaluation/data/__init__.py b/‎src/llm_agent_evaluation/data/__init__.py ‎llm_agent_evaluation/data/__init__.py
diff --git a/‎src/llm_agent_evaluation/data/_base.py ‎llm_agent_evaluation/data/_base.py b/‎src/llm_agent_evaluation/data/_base.py ‎llm_agent_evaluation/data/_base.py
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/__init__.py ‎llm_agent_evaluation/data/bugsinpy/__init__.py b/‎src/llm_agent_evaluation/data/bugsinpy/__init__.py ‎llm_agent_evaluation/data/bugsinpy/__init__.py
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/build.py ‎llm_agent_evaluation/data/bugsinpy/build.py b/‎src/llm_agent_evaluation/data/bugsinpy/build.py ‎llm_agent_evaluation/data/bugsinpy/build.py
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/collect.py ‎llm_agent_evaluation/data/bugsinpy/collect.py b/‎src/llm_agent_evaluation/data/bugsinpy/collect.py ‎llm_agent_evaluation/data/bugsinpy/collect.py
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/error.py ‎llm_agent_evaluation/data/bugsinpy/error.py b/‎src/llm_agent_evaluation/data/bugsinpy/error.py ‎llm_agent_evaluation/data/bugsinpy/error.py
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/execute.py ‎llm_agent_evaluation/data/bugsinpy/execute.py
+2-1 b/‎src/llm_agent_evaluation/data/bugsinpy/execute.py ‎llm_agent_evaluation/data/bugsinpy/execute.py
+2-1
diff --git a/‎src/llm_agent_evaluation/data/bugsinpy/run_sandbox.sh ‎llm_agent_evaluation/data/bugsinpy/run_sandbox.sh b/‎src/llm_agent_evaluation/data/bugsinpy/run_sandbox.sh ‎llm_agent_evaluation/data/bugsinpy/run_sandbox.sh
diff --git a/‎src/llm_agent_evaluation/data/constants.py ‎llm_agent_evaluation/data/constants.py b/‎src/llm_agent_evaluation/data/constants.py ‎llm_agent_evaluation/data/constants.py
diff --git a/‎src/llm_agent_evaluation/data/patch_utils.py ‎llm_agent_evaluation/data/patch_utils.py b/‎src/llm_agent_evaluation/data/patch_utils.py ‎llm_agent_evaluation/data/patch_utils.py
diff --git a/‎src/llm_agent_evaluation/data/swe_bench/__init__.py ‎llm_agent_evaluation/data/swe_bench/__init__.py b/‎src/llm_agent_evaluation/data/swe_bench/__init__.py ‎llm_agent_evaluation/data/swe_bench/__init__.py
diff --git a/‎src/llm_agent_evaluation/data/swe_bench/build.py ‎llm_agent_evaluation/data/swe_bench/build.py b/‎src/llm_agent_evaluation/data/swe_bench/build.py ‎llm_agent_evaluation/data/swe_bench/build.py
diff --git a/‎src/llm_agent_evaluation/data/swe_bench/collect.py ‎llm_agent_evaluation/data/swe_bench/collect.py b/‎src/llm_agent_evaluation/data/swe_bench/collect.py ‎llm_agent_evaluation/data/swe_bench/collect.py
diff --git a/‎src/llm_agent_evaluation/experiments/__init__.py ‎llm_agent_evaluation/experiments/__init__.py b/‎src/llm_agent_evaluation/experiments/__init__.py ‎llm_agent_evaluation/experiments/__init__.py
diff --git a/‎src/llm_agent_evaluation/experiments/analysis/confidence.py ‎llm_agent_evaluation/experiments/analysis/confidence.py b/‎src/llm_agent_evaluation/experiments/analysis/confidence.py ‎llm_agent_evaluation/experiments/analysis/confidence.py
diff --git a/‎src/llm_agent_evaluation/experiments/analysis/metrics.py ‎llm_agent_evaluation/experiments/analysis/metrics.py b/‎src/llm_agent_evaluation/experiments/analysis/metrics.py ‎llm_agent_evaluation/experiments/analysis/metrics.py
diff --git a/‎src/llm_agent_evaluation/experiments/evaluate_execution.py ‎llm_agent_evaluation/experiments/evaluate_execution.py b/‎src/llm_agent_evaluation/experiments/evaluate_execution.py ‎llm_agent_evaluation/experiments/evaluate_execution.py
diff --git a/‎src/llm_agent_evaluation/experiments/evaluate_lexical.py ‎llm_agent_evaluation/experiments/evaluate_lexical.py b/‎src/llm_agent_evaluation/experiments/evaluate_lexical.py ‎llm_agent_evaluation/experiments/evaluate_lexical.py
diff --git a/‎src/llm_agent_evaluation/experiments/evaluate_ref_free.py ‎llm_agent_evaluation/experiments/evaluate_ref_free.py b/‎src/llm_agent_evaluation/experiments/evaluate_ref_free.py ‎llm_agent_evaluation/experiments/evaluate_ref_free.py
diff --git a/‎src/llm_agent_evaluation/experiments/evaluate_semantics.py ‎llm_agent_evaluation/experiments/evaluate_semantics.py b/‎src/llm_agent_evaluation/experiments/evaluate_semantics.py ‎llm_agent_evaluation/experiments/evaluate_semantics.py
diff --git a/‎src/llm_agent_evaluation/experiments/evaluate_test_centric.py ‎llm_agent_evaluation/experiments/evaluate_test_centric.py b/‎src/llm_agent_evaluation/experiments/evaluate_test_centric.py ‎llm_agent_evaluation/experiments/evaluate_test_centric.py
diff --git a/‎src/llm_agent_evaluation/experiments/run_all.sh ‎llm_agent_evaluation/experiments/run_all.sh b/‎src/llm_agent_evaluation/experiments/run_all.sh ‎llm_agent_evaluation/experiments/run_all.sh
diff --git a/‎src/llm_agent_evaluation/experiments/run_all2.sh ‎llm_agent_evaluation/experiments/run_all2.sh b/‎src/llm_agent_evaluation/experiments/run_all2.sh ‎llm_agent_evaluation/experiments/run_all2.sh
diff --git a/‎src/llm_agent_evaluation/experiments/utils.py ‎llm_agent_evaluation/experiments/utils.py b/‎src/llm_agent_evaluation/experiments/utils.py ‎llm_agent_evaluation/experiments/utils.py
diff --git a/‎src/llm_agent_evaluation/external/__init__.py ‎llm_agent_evaluation/external/__init__.py b/‎src/llm_agent_evaluation/external/__init__.py ‎llm_agent_evaluation/external/__init__.py
diff --git a/‎src/llm_agent_evaluation/external/ast/__init__.py ‎llm_agent_evaluation/external/ast/__init__.py b/‎src/llm_agent_evaluation/external/ast/__init__.py ‎llm_agent_evaluation/external/ast/__init__.py
diff --git a/‎src/llm_agent_evaluation/external/ast/explorer.py ‎llm_agent_evaluation/external/ast/explorer.py b/‎src/llm_agent_evaluation/external/ast/explorer.py ‎llm_agent_evaluation/external/ast/explorer.py
diff --git a/‎src/llm_agent_evaluation/py.typed ‎llm_agent_evaluation/py.typed b/‎src/llm_agent_evaluation/py.typed ‎llm_agent_evaluation/py.typed
diff --git a/‎src/llm_agent_evaluation/scorers/__init__.py ‎llm_agent_evaluation/scorers/__init__.py b/‎src/llm_agent_evaluation/scorers/__init__.py ‎llm_agent_evaluation/scorers/__init__.py
diff --git a/‎src/llm_agent_evaluation/scorers/_base.py ‎llm_agent_evaluation/scorers/_base.py b/‎src/llm_agent_evaluation/scorers/_base.py ‎llm_agent_evaluation/scorers/_base.py
diff --git a/‎src/llm_agent_evaluation/scorers/complexity.py ‎llm_agent_evaluation/scorers/complexity.py b/‎src/llm_agent_evaluation/scorers/complexity.py ‎llm_agent_evaluation/scorers/complexity.py
diff --git a/‎src/llm_agent_evaluation/scorers/lexical.py ‎llm_agent_evaluation/scorers/lexical.py b/‎src/llm_agent_evaluation/scorers/lexical.py ‎llm_agent_evaluation/scorers/lexical.py
diff --git a/‎src/llm_agent_evaluation/scorers/llm.py ‎llm_agent_evaluation/scorers/llm.py b/‎src/llm_agent_evaluation/scorers/llm.py ‎llm_agent_evaluation/scorers/llm.py
diff --git a/‎src/llm_agent_evaluation/scorers/llm_utils.py ‎llm_agent_evaluation/scorers/llm_utils.py b/‎src/llm_agent_evaluation/scorers/llm_utils.py ‎llm_agent_evaluation/scorers/llm_utils.py
diff --git a/‎src/llm_agent_evaluation/scorers/prompt_templates/execution_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/execution_prompts.yaml b/‎src/llm_agent_evaluation/scorers/prompt_templates/execution_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/execution_prompts.yaml
diff --git a/‎src/llm_agent_evaluation/scorers/prompt_templates/reference_free.yaml ‎llm_agent_evaluation/scorers/prompt_templates/reference_free.yaml b/‎src/llm_agent_evaluation/scorers/prompt_templates/reference_free.yaml ‎llm_agent_evaluation/scorers/prompt_templates/reference_free.yaml
diff --git a/‎src/llm_agent_evaluation/scorers/prompt_templates/semantic_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/semantic_prompts.yaml b/‎src/llm_agent_evaluation/scorers/prompt_templates/semantic_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/semantic_prompts.yaml
diff --git a/‎src/llm_agent_evaluation/scorers/prompt_templates/syntax_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/syntax_prompts.yaml b/‎src/llm_agent_evaluation/scorers/prompt_templates/syntax_prompts.yaml ‎llm_agent_evaluation/scorers/prompt_templates/syntax_prompts.yaml
diff --git a/‎src/llm_agent_evaluation/scorers/prompt_templates/system_prompt.yaml ‎llm_agent_evaluation/scorers/prompt_templates/system_prompt.yaml b/‎src/llm_agent_evaluation/scorers/prompt_templates/system_prompt.yaml ‎llm_agent_evaluation/scorers/prompt_templates/system_prompt.yaml
diff --git a/‎src/llm_agent_evaluation/scorers/syntax.py ‎llm_agent_evaluation/scorers/syntax.py b/‎src/llm_agent_evaluation/scorers/syntax.py ‎llm_agent_evaluation/scorers/syntax.py
diff --git a/‎src/llm_agent_evaluation/utils.py ‎llm_agent_evaluation/utils.py b/‎src/llm_agent_evaluation/utils.py ‎llm_agent_evaluation/utils.py
diff --git a/‎src/llm_agent_evaluation/workflows/agentic_patches.py ‎llm_agent_evaluation/workflows/agentic_patches.py b/‎src/llm_agent_evaluation/workflows/agentic_patches.py ‎llm_agent_evaluation/workflows/agentic_patches.py
diff --git a/‎src/llm_agent_evaluation/workflows/perturbation.py ‎llm_agent_evaluation/workflows/perturbation.py b/‎src/llm_agent_evaluation/workflows/perturbation.py ‎llm_agent_evaluation/workflows/perturbation.py
diff --git a/‎src/llm_agent_evaluation/workflows/run_all.sh ‎llm_agent_evaluation/workflows/run_all.sh b/‎src/llm_agent_evaluation/workflows/run_all.sh ‎llm_agent_evaluation/workflows/run_all.sh
@@ -8,10 +8,10 @@
 *.env
 
 # Do not track dataset resources.
-/src/llm_agent_evaluation/resources/
-/src/llm_agent_evaluation/resources-dev/
+llm_agent_evaluation/resources/
+llm_agent_evaluation/resources-dev/
 
-/src/llm_agent_evaluation/experiments/analysis/figures
+llm_agent_evaluation/experiments/analysis/figures
 
 __pycache__/
 *.py[cod]
 
@@ -140,7 +140,8 @@ def test(
 
 
 # if __name__ == '__main__':
-#     runner = TestRunner(pathlib.Path('/home/axyadav/workspace/llmevalws/src/LLMAgentEvaluation/src/llm_agent_evaluation/resources'))
+#     TODO: Add your local path bellow 
+#     runner = TestRunner(pathlib.Path('/my/local/path/llm_agent_evaluation/resources'))
 
 #     PROJECTS = [
 #         'PySnooper',