microsoft/FLAML

11.7

Adjusted Score

11.7

Raw Score

100%

Time Factor

2026-08-09

Last Push

4.4K

Stars

Jupyter Notebook

Language

66.2K

Lines of Code

365

Files

701

Pattern Hits

2026-08-09

Scan Date

0.03

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 10MEDIUM 17LOW 674

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 701 distinct pattern matches across 18 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers211 hits · 226 pts

Severity	File	Line	Snippet	Context
LOW	test/conftest.py	22	def evaluate_cv_folds_with_underlying_model(X_train_all, y_train_all, kf, model: Any, task: str) -> List[float]:	CODE
LOW	test/test_autovw.py	377	def test_vw_oml_problem_and_vanilla_vw(self):	CODE
LOW	test/test_autovw.py	392	def test_supervised_vw_tune_namespace(self):	CODE
LOW	test/test_autovw.py	415	def test_supervised_vw_tune_namespace_learningrate(self):	CODE
LOW	test/test_autovw.py	441	def test_bandit_vw_tune_namespace(self):	CODE
LOW	test/test_autovw.py	444	def test_bandit_vw_tune_namespace_learningrate(self):	CODE
LOW	test/default/test_defaults.py	72	def test_suggest_classification():	CODE
LOW	test/automl/test_extra_models.py	180	def _test_sparse_matrix_classification(estimator):	CODE
LOW	test/automl/test_extra_models.py	219	def test_load_multi_dataset_aggregates_without_resample():	CODE
LOW	test/automl/test_split.py	55	def test_time_split_with_sample_weight():	CODE
LOW	test/automl/test_split.py	77	def test_groups_for_classification_task():	CODE
LOW	test/automl/test_split.py	115	def test_groups_for_regression_task():	CODE
LOW	test/automl/test_split.py	144	def test_groups_with_sample_weights():	CODE
LOW	test/automl/test_split.py	181	def test_stratified_groupkfold():	CODE
LOW	test/automl/test_sklearn_17_compat.py	19	def test_extra_trees_regressor_type():	CODE
LOW	test/automl/test_sklearn_17_compat.py	26	def test_extra_trees_classifier_type():	CODE
LOW	test/automl/test_sklearn_17_compat.py	37	def test_random_forest_regressor_type():	CODE
LOW	test/automl/test_sklearn_17_compat.py	44	def test_random_forest_classifier_type():	CODE
LOW⚡	test/automl/test_sklearn_17_compat.py	58	def test_lgbm_classifier_type():	CODE
LOW⚡	test/automl/test_sklearn_17_compat.py	65	def test_xgboost_regressor_type():	CODE
LOW⚡	test/automl/test_sklearn_17_compat.py	72	def test_xgboost_classifier_type():	CODE
LOW	test/automl/test_forecast.py	196	def test_multivariate_forecast_num(budget=5, estimators_when_no_prophet=["arima", "sarimax", "holt-winters"]):	CODE
LOW	test/automl/test_forecast.py	326	def test_multivariate_forecast_cat(budget=5, estimators_when_no_prophet=["arima", "sarimax", "holt-winters"]):	CODE
LOW	test/automl/test_forecast.py	404	def test_forecast_classification(budget=5):	CODE
LOW	test/automl/test_forecast.py	682	def test_log_training_metric_ts_models():	CODE
LOW	test/automl/test_constraints.py	95	def test_metric_constraints_custom():	CODE
LOW	test/automl/test_preprocess_api.py	14	def test_automl_preprocess_before_fit(self):	CODE
LOW	test/automl/test_preprocess_api.py	24	def test_automl_preprocess_classification(self):	CODE
LOW	test/automl/test_preprocess_api.py	49	def test_automl_preprocess_regression(self):	CODE
LOW	test/automl/test_preprocess_api.py	74	def test_automl_preprocess_with_dataframe(self):	CODE
LOW	test/automl/test_preprocess_api.py	113	def test_estimator_preprocess(self):	CODE
LOW	test/automl/test_preprocess_api.py	176	def test_preprocess_with_mixed_types(self):	CODE
LOW	test/automl/test_preprocess_api.py	215	def test_estimator_preprocess_without_automl(self):	CODE
LOW	test/automl/test_preprocess_api.py	254	def test_codes_stable_when_predict_uses_only_a_subset(self):	CODE
LOW	test/automl/test_preprocess_api.py	269	def test_unseen_categories_emit_warning_and_map_to_sentinel(self):	CODE
LOW	test/automl/test_multiclass.py	184	def test_ensemble_final_estimator_params_not_tuned(self):	CODE
LOW	test/automl/test_multiclass.py	281	def test_invalid_custom_metric(self):	CODE
LOW	test/automl/test_multiclass.py	403	def test_roc_auc_ovr_weighted(self):	CODE
LOW	test/automl/test_multiclass.py	417	def test_roc_auc_ovo_weighted(self):	CODE
LOW	test/automl/test_multiclass.py	431	def test_sparse_matrix_classification(self):	CODE
LOW	test/automl/test_multiclass.py	496	def test_fit_w_starting_point(self, as_frame=True, n_concurrent_trials=1):	CODE
LOW	test/automl/test_multiclass.py	551	def test_fit_w_starting_points_list(self, as_frame=True, n_concurrent_trials=1):	CODE
LOW	test/automl/test_multiclass.py	609	def test_starting_points_should_improve_performance(self):	CODE
LOW	test/automl/test_notebook.py	30	def test_automl_classification(save=False):	CODE
LOW	test/automl/test_mlflow.py	15	def test_autologged_model_round_trip():	CODE
LOW	test/automl/test_mlflow.py	35	def test_update_and_install_requirements(self):	CODE
LOW	test/automl/test_mlflow.py	47	def test_should_start_new_run_by_default(self, automl_settings):	CODE
LOW	test/automl/test_mlflow.py	60	def test_should_not_start_new_run_when_mlflow_logging_set_to_false_in_init(self, automl_settings):	CODE
LOW	test/automl/test_mlflow.py	73	def test_should_not_start_new_run_when_mlflow_logging_set_to_false_in_fit(self, automl_settings):	CODE
LOW	test/automl/test_mlflow.py	86	def test_should_start_new_run_when_mlflow_logging_set_to_true_in_fit(self, automl_settings):	CODE
LOW	test/automl/test_warmstart.py	11	def test_fit_w_freezinghp_starting_point(self, as_frame=True):	CODE
LOW	test/automl/test_ts_data.py	7	def test_prettify_prediction_generates_timestamps_without_test_data():	CODE
LOW	test/automl/test_ts_data.py	28	def test_prettify_prediction_generates_monthly_timestamps_without_test_data():	CODE
LOW	test/automl/test_ts_data.py	47	def test_create_forward_frame_uses_next_frequency_offset():	CODE
LOW	test/automl/test_no_overlap.py	9	def test_allow_label_overlap_true():	CODE
LOW	test/automl/test_no_overlap.py	60	def test_allow_label_overlap_false():	CODE
LOW	test/automl/test_no_overlap.py	112	def test_uniform_split_with_overlap_control():	CODE
LOW	test/automl/test_no_overlap.py	226	def test_single_instance_class():	CODE
LOW	test/automl/test_classification.py	273	def test_sparse_matrix_xgboost(self):	CODE
LOW	test/automl/test_classification.py	371	def test_parallel_xgboost_others(self):	CODE
151 more matches not shown…

Unused Imports215 hits · 207 pts

Severity	File	Line	Context
LOW	test/conftest.py	1	CODE
LOW	test/conftest.py	1	CODE
LOW	test/conftest.py	4	CODE
LOW	test/test_autovw.py	4	CODE
LOW	test/automl/test_extra_models.py	24	CODE
LOW	test/automl/test_sklearn_17_compat.py	8	CODE
LOW	test/automl/test_forecast.py	476	CODE
LOW	test/automl/test_forecast.py	36	CODE
LOW	test/automl/test_forecast.py	220	CODE
LOW	test/automl/test_forecast.py	345	CODE
LOW	test/automl/test_forecast.py	670	CODE
LOW	test/automl/test_custom_hp.py	8	CODE
LOW	test/automl/test_score.py	36	CODE
LOW	test/automl/test_warmstart.py	174	CODE
LOW	test/automl/test_no_overlap.py	3	CODE
LOW	test/pipeline_tuning_example/train/train.py	5	CODE
LOW	test/tune/test_searcher.py	324	CODE
LOW	test/tune/example_scheduler.py	1	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_sample.py	2	CODE
LOW	test/tune/test_lexiflow.py	3	CODE
LOW	test/tune/test_flaml_raytune_consistency.py	6	CODE
LOW	test/tune/test_tune.py	6	CODE
LOW	test/tune/test_tune.py	9	CODE
LOW	test/tune/test_tune.py	117	CODE
LOW	test/tune/test_search_thread.py	3	CODE
LOW	test/nlp/test_autohf_cv.py	9	CODE
LOW	test/nlp/test_default.py	11	CODE
LOW	test/nlp/test_autohf_classificationhead.py	12	CODE
LOW	test/nlp/test_autohf_classificationhead.py	12	CODE
LOW	test/nlp/test_autohf_classificationhead.py	12	CODE
LOW	test/nlp/test_autohf_classificationhead.py	8	CODE
LOW	test/nlp/test_autohf_multichoice_classification.py	9	CODE
LOW	test/nni/mnist.py	13	CODE
LOW	test/autogen/test_code.py	238	CODE
LOW	test/autogen/test_notebook.py	7	CODE
LOW	test/autogen/agentchat/test_async.py	51	CODE
LOW	test/autogen/agentchat/test_math_user_proxy_agent.py	20	CODE
LOW	test/autogen/agentchat/test_assistant_agent.py	20	CODE
LOW	test/autogen/agentchat/test_assistant_agent.py	64	CODE
LOW	test/autogen/agentchat/test_assistant_agent.py	118	CODE
LOW	test/autogen/agentchat/test_assistant_agent.py	161	CODE
LOW	test/autogen/agentchat/extensions/tsp.py	5	CODE
LOW	test/autogen/agentchat/extensions/tsp.py	6	CODE
LOW	test/autogen/agentchat/extensions/tsp.py	8	CODE
LOW	test/autogen/agentchat/extensions/tsp.py	9	CODE
LOW	test/autogen/oai/test_completion.py	122	CODE
LOW	test/autogen/oai/test_completion.py	211	CODE
LOW	test/autogen/oai/test_completion.py	330	CODE
LOW	test/spark/test_utils.py	17	CODE
LOW	test/spark/test_overtime.py	11	CODE
LOW	test/spark/test_overtime.py	13	CODE
LOW	test/spark/test_multiclass.py	23	CODE
LOW	test/spark/test_mlflow.py	3	CODE
LOW	test/spark/test_mlflow.py	11	CODE
155 more matches not shown…

Deep Nesting114 hits · 109 pts

Severity	File	Line	Context
LOW	test/test_autovw.py	45	CODE
LOW	test/automl/test_training_log.py	12	CODE
LOW	test/automl/test_forecast.py	276	CODE
LOW	test/automl/test_forecast.py	282	CODE
LOW	test/tune/test_pytorch_cifar10.py	189	CODE
LOW	test/tune/test_scheduler.py	56	CODE
LOW	test/tune/test_tune.py	115	CODE
LOW	test/nlp/test_autohf.py	14	CODE
LOW	test/nlp/test_autohf_tokenclassification.py	18	CODE
LOW	test/nlp/test_autohf_tokenclassification.py	71	CODE
LOW	test/autogen/test_notebook.py	17	CODE
LOW	flaml/default/suggest.py	23	CODE
LOW	flaml/automl/model.py	391	CODE
LOW	flaml/automl/model.py	1475	CODE
LOW	flaml/automl/model.py	1569	CODE
LOW	flaml/automl/model.py	2123	CODE
LOW	flaml/automl/model.py	2258	CODE
LOW	flaml/automl/ml.py	99	CODE
LOW	flaml/automl/ml.py	197	CODE
LOW	flaml/automl/automl.py	953	CODE
LOW	flaml/automl/automl.py	1370	CODE
LOW	flaml/automl/automl.py	1623	CODE
LOW	flaml/automl/automl.py	1791	CODE
LOW	flaml/automl/automl.py	2678	CODE
LOW	flaml/automl/automl.py	2874	CODE
LOW	flaml/automl/automl.py	3168	CODE
LOW	flaml/automl/automl.py	3437	CODE
LOW	flaml/automl/automl.py	1399	CODE
LOW	flaml/automl/automl.py	1439	CODE
LOW	flaml/automl/data.py	151	CODE
LOW	flaml/automl/data.py	607	CODE
LOW	flaml/automl/data.py	725	CODE
LOW	flaml/automl/data.py	269	CODE
LOW	flaml/automl/data.py	410	CODE
LOW	flaml/automl/state.py	57	CODE
LOW	flaml/automl/task/time_series_task.py	96	CODE
LOW	flaml/automl/task/generic_task.py	103	CODE
LOW	flaml/automl/task/generic_task.py	309	CODE
LOW	flaml/automl/task/generic_task.py	369	CODE
LOW	flaml/automl/task/generic_task.py	501	CODE
LOW	flaml/automl/task/generic_task.py	828	CODE
LOW	flaml/automl/task/generic_task.py	1073	CODE
LOW	flaml/automl/task/generic_task.py	1109	CODE
LOW	flaml/automl/task/generic_task.py	1138	CODE
LOW	flaml/automl/task/generic_task.py	1271	CODE
LOW	flaml/automl/task/generic_task.py	1351	CODE
LOW	flaml/automl/nlp/utils.py	14	CODE
LOW	flaml/automl/nlp/utils.py	38	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	26	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	79	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	312	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	375	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	388	CODE
LOW	flaml/automl/time_series/ts_data.py	229	CODE
LOW	flaml/automl/time_series/ts_data.py	385	CODE
LOW	flaml/automl/spark/metrics.py	50	CODE
LOW	flaml/automl/spark/utils.py	26	CODE
LOW	flaml/automl/spark/utils.py	179	CODE
LOW	flaml/tune/trial.py	24	CODE
LOW	flaml/tune/trial.py	95	CODE
54 more matches not shown…

Excessive Try-Catch Wrapping38 hits · 39 pts

Severity	File	Line	Snippet	Context
LOW	test/automl/test_regression.py	298	except Exception:	CODE
LOW	test/nni/mnist.py	210	except Exception as exception:	CODE
LOW	flaml/automl/ml.py	137	except Exception:	CODE
LOW	flaml/automl/automl.py	475	except Exception:	CODE
LOW	flaml/automl/automl.py	1418	except Exception:	CODE
LOW	flaml/automl/automl.py	1433	except Exception:	CODE
LOW	flaml/automl/automl.py	1451	except Exception:	CODE
LOW	flaml/automl/automl.py	1562	except Exception as e:	CODE
LOW	flaml/automl/automl.py	1582	except Exception:	CODE
LOW	flaml/automl/automl.py	1619	except Exception:	CODE
LOW	flaml/automl/automl.py	1651	except Exception:	CODE
LOW	flaml/automl/automl.py	1684	except Exception as e:	CODE
LOW	flaml/automl/automl.py	1702	except Exception as e:	CODE
LOW	flaml/automl/automl.py	3413	except Exception as e:	CODE
LOW	flaml/automl/automl.py	3420	except Exception as e:	CODE
LOW	flaml/automl/data.py	804	except Exception:	CODE
LOW	flaml/automl/data.py	834	except Exception:	CODE
LOW	flaml/automl/task/time_series_task.py	155	except Exception:	CODE
LOW	flaml/automl/time_series/ts_model.py	381	except Exception as e:	CODE
LOW	flaml/automl/spark/__init__.py	59	except Exception:	CODE
LOW	flaml/automl/spark/__init__.py	75	except Exception:	CODE
LOW	flaml/automl/spark/__init__.py	95	except Exception:	CODE
LOW	flaml/automl/spark/utils.py	65	except Exception:	CODE
LOW	flaml/tune/searcher/suggestion.py	97	except Exception: # pragma: no cover	CODE
LOW	flaml/tune/searcher/suggestion.py	824	except Exception as exc:	CODE
LOW	flaml/tune/searcher/blendsearch.py	231	except Exception:	CODE
LOW	flaml/fabric/mlflow.py	257	except Exception:	CODE
LOW	flaml/fabric/mlflow.py	290	except Exception as e:	CODE
LOW	flaml/fabric/mlflow.py	372	except Exception:	CODE
LOW	flaml/fabric/mlflow.py	572	except Exception as e:	CODE
MEDIUM	flaml/fabric/mlflow.py	135	def get_mlflow_log_latency(model_history=False, delete_run=True):	CODE
LOW	flaml/autogen/math_utils.py	42	except Exception:	CODE
LOW	flaml/autogen/math_utils.py	99	except Exception:	CODE
LOW	flaml/autogen/math_utils.py	136	except Exception:	CODE
LOW	flaml/autogen/math_utils.py	279	except Exception:	CODE
LOW	flaml/autogen/agentchat/conversable_agent.py	975	except Exception as e:	CODE
LOW	…aml/autogen/agentchat/contrib/math_user_proxy_agent.py	417	except Exception:	CODE
LOW	…aml/autogen/agentchat/contrib/math_user_proxy_agent.py	446	except Exception:	CODE

Over-Commented Block39 hits · 39 pts

Severity	File	Line	Snippet	Context
LOW	test/tune/test_space.py	21	# Sample a float uniformly between 0.0001 and 0.1, while	COMMENT
LOW	test/tune/test_restore.py	81		COMMENT
LOW	test/autogen/test_code.py	21	# def test_find_code():	COMMENT
LOW	test/autogen/test_code.py	41	# # "gpt-3.5-turbo-16k-0613",	COMMENT
LOW	test/autogen/test_code.py	61	# print('Hello, World! printed to hello.txt')	COMMENT
LOW	test/autogen/test_code.py	81	# },	COMMENT
LOW	test/autogen/test_code.py	101	# Please execute the above Python code to save a pandas df with 3 rows and 3 columns to disk.	COMMENT
LOW	test/autogen/test_code.py	121	# "role": "user",	COMMENT
LOW	test/autogen/agentchat/test_conversable_agent.py	181	# test_context()	COMMENT
LOW	test/autogen/agentchat/test_assistant_agent.py	201	test_gpt35()	COMMENT
LOW	test/spark/test_utils.py	441	# test ndcg	COMMENT
LOW	test/spark/test_mlflow.py	341	# test_tune_autolog_parentrun_nonparallel()	COMMENT
LOW	test/spark/test_0sparkml.py	421	# cProfile.run("_test_spark_large_df()", "_test_spark_large_df.profile")	COMMENT
LOW	website/docusaurus.config.js	61	{	COMMENT
LOW	website/docs/Use-Cases/Tune-User-Defined-Function.md	161	# mean=10 and sd=2	COMMENT
LOW	website/src/components/HomepageFeatures.js	21	description: (	COMMENT
LOW	flaml/default/portfolio.py	141	# for i, task in enumerate(neighbors):	COMMENT
LOW	flaml/automl/model.py	741	# ) and n_iter > 1:	COMMENT
LOW	flaml/automl/model.py	761	# if (	COMMENT
LOW	flaml/automl/task/generic_task.py	1321	estimator_list += ["catboost"]	COMMENT
LOW	flaml/automl/time_series/sklearn.py	161	# TODO: do we want auto-clipping?	COMMENT
LOW	flaml/automl/time_series/sklearn.py	181	# **{col: X[col] != "" for col in X.filter(like="_holiday_").columns}	COMMENT
LOW	flaml/tune/trial.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/analysis.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/result.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/sample.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/space.py	141	# for key, domain in space.items():	COMMENT
LOW	flaml/tune/searcher/variant_generator.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/searcher/suggestion.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/tune/searcher/online_searcher.py	61		COMMENT
LOW	flaml/tune/scheduler/trial_scheduler.py	1	# Copyright 2020 The Ray Authors.	COMMENT
LOW	flaml/onlineml/trial_runner.py	21	# The max number of Trial.RUNNING trials is running_budget.	COMMENT
LOW	flaml/onlineml/trial_runner.py	41	Args:	COMMENT
LOW	flaml/onlineml/trial_runner.py	61	# It adds candidate trials to the scheduler. It is called inside of the add_trial	COMMENT
LOW	flaml/autogen/code_utils.py	61	# "content": """In the following conversation, an assistant suggests code and a user is expected to run it.	COMMENT
LOW	flaml/autogen/code_utils.py	81		COMMENT
LOW	flaml/autogen/code_utils.py	321	while container.status != "exited" and time.time() - start_time < timeout:	COMMENT
LOW	flaml/autogen/code_utils.py	541	# for i, config in enumerate(configs):	COMMENT
LOW	…autogen/agentchat/contrib/retrieve_user_proxy_agent.py	281	else:	COMMENT

Modern Structural Boilerplate34 hits · 34 pts

Severity	File	Line	Snippet	Context
LOW	test/test_autovw.py	42	logger = logging.getLogger(__name__)	CODE
LOW	test/pipeline_tuning_example/tuner/tuner_func.py	9	logger = logging.getLogger(__name__)	CODE
LOW	test/pipeline_tuning_example/data_prep/data_prep.py	8	logger = logging.getLogger(__name__)	CODE
LOW	test/tune/test_pytorch_cifar10.py	9	logger = logging.getLogger(__name__)	CODE
LOW	test/tune/test_tune.py	23	logger = logging.getLogger(__name__)	CODE
LOW	flaml/__init__.py	15	logger = logging.getLogger(__name__)	CODE
LOW	flaml/default/suggest.py	19	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/logger.py	29	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/ml.py	38	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/task/time_series_task.py	26	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/task/generic_task.py	40	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/spark/__init__.py	50	logger = logging.getLogger(__name__)	CODE
LOW	flaml/automl/spark/utils.py	19	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/analysis.py	25	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/trial_runner.py	15	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/logger.py	29	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/sample.py	37	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/space.py	19	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/variant_generator.py	37	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/suggestion.py	108	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/blendsearch.py	35	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/online_searcher.py	11	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/flow2.py	35	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/searcher/search_thread.py	25	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/scheduler/online_scheduler.py	10	logger = logging.getLogger(__name__)	CODE
LOW	flaml/tune/spark/__init__.py	8	__all__ = ["check_spark", "get_n_cpus", "with_parameters", "broadcast_code"]	CODE
LOW	flaml/tune/spark/utils.py	8	logger = logging.getLogger(__name__)	CODE
LOW	flaml/onlineml/trial.py	17	logger = logging.getLogger(__name__)	CODE
LOW	flaml/onlineml/trial_runner.py	9	logger = logging.getLogger(__name__)	CODE
LOW	flaml/onlineml/autovw.py	16	logger = logging.getLogger(__name__)	CODE
LOW	flaml/autogen/retrieve_utils.py	13	logger = logging.getLogger(__name__)	CODE
LOW	flaml/autogen/agentchat/__init__.py	7	__all__ = [	CODE
LOW	flaml/autogen/oai/completion.py	34	logger = logging.getLogger(__name__)	CODE
LOW	flaml/autogen/oai/__init__.py	10	__all__ = [	CODE

Self-Referential Comments10 hits · 30 pts

Severity	File	Line	Snippet	Context
MEDIUM	test/automl/test_custom_hp.py	79	# Create a simple regression dataset	COMMENT
MEDIUM	test/automl/test_preprocess_api.py	76	# Create a simple dataset	COMMENT
MEDIUM	test/automl/test_preprocess_api.py	219	# Create a simple estimator	COMMENT
MEDIUM	test/automl/test_multiclass.py	195	# Create a LogisticRegression with specific non-default parameters	COMMENT
MEDIUM	test/automl/test_no_overlap.py	156	# Create a simple dataset	COMMENT
MEDIUM	test/nni/mnist.py	1	# This file is copied from NNI project	COMMENT
MEDIUM	test/spark/test_0sparkml.py	347	# Create a test DataFrame with various types	COMMENT
MEDIUM	test/spark/test_0sparkml.py	375	# Create a test DataFrame with various types	COMMENT
MEDIUM	flaml/automl/time_series/tcn.py	1	# This file is adapted from	COMMENT
MEDIUM	flaml/automl/spark/metrics.py	35	# Create a new column 'prediction' based on the maximum probability value	COMMENT

Cross-Language Confusion4 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH⚡	test/spark/test_utils.py	267	assert d1.equals(d2)	STRING
HIGH⚡	test/spark/test_utils.py	270	assert d1.equals(d2)	STRING
HIGH⚡	flaml/automl/state.py	32	(1) If the type of the starting point does not match the required type in search space, return false	STRING
HIGH⚡	flaml/automl/state.py	33	(2) If the starting point is not in the required search space, return false	STRING

Docstring Block Structure3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	flaml/automl/automl.py	862	Preprocess data using task-level preprocessing. This method applies task-level preprocessing transformations to	STRING
HIGH	flaml/automl/task/task.py	216	Choose an appropriate data split type for this data and task. If split_type is 'auto' then this is determined b	STRING
HIGH	flaml/automl/task/task.py	331	Determine the estimator class corresponding to the provided name. Args: estimator_name: Name of the	STRING

Cross-File Repetition3 hits · 15 pts

Severity	File	Snippet	Context
HIGH	test/automl/test_regression.py	xgboostestimator with the logregobj function as the objective function	STRING
HIGH	website/docs/Use-Cases/Task-Oriented-AutoML.md	xgboostestimator with the logregobj function as the objective function	STRING
HIGH	website/docs/Examples/AutoML-for-XGBoost.md	xgboostestimator with the logregobj function as the objective function	STRING

AI Structural Patterns14 hits · 13 pts

Severity	File	Line	Context
LOW	test/automl/test_forecast.py	301	CODE
LOW	test/spark/test_tune.py	33	CODE
LOW	flaml/automl/automl.py	953	CODE
LOW	flaml/automl/automl.py	1791	CODE
LOW	flaml/automl/nlp/huggingface/utils.py	283	CODE
LOW	flaml/tune/tune.py	235	CODE
LOW	flaml/tune/searcher/blendsearch.py	44	CODE
LOW	flaml/tune/searcher/flow2.py	44	CODE
LOW	flaml/onlineml/autovw.py	26	CODE
LOW	flaml/fabric/mlflow.py	77	CODE
LOW	flaml/fabric/mlflow.py	273	CODE
LOW	flaml/autogen/retrieve_utils.py	184	CODE
LOW	flaml/autogen/agentchat/conversable_agent.py	46	CODE
LOW	flaml/autogen/agentchat/user_proxy_agent.py	19	CODE

Modern AI Meta-Vocabulary4 hits · 11 pts

Severity	File	Line	Snippet	Context
MEDIUM	test/default/test_defaults.py	278	# make sure that zero-shot config out of the search space does not degnerate to low cost init config	COMMENT
MEDIUM	test/default/test_defaults.py	280	# make sure that the zero-shot config {} is not modified	COMMENT
MEDIUM	website/docs/Use-Cases/Task-Oriented-AutoML.md	669	`starting_points` is a dictionary or a str to specify the starting hyperparameter config. (1) When it is a dictionary, t	CODE
MEDIUM	website/docs/Use-Cases/Zero-Shot-AutoML.md	90	### Combine zero shot AutoML and hyperparameter tuning	COMMENT

Redundant / Tautological Comments7 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW	test/automl/test_training_log.py	35	# Check if the training log file is populated.	COMMENT
LOW	test/automl/test_python_log.py	107	# Check if the log buffer is populated.	COMMENT
LOW	flaml/automl/model.py	1213	# Check if processing_class parameter is supported (transformers >= 4.44.0)	COMMENT
LOW	flaml/automl/data.py	670	# Check if timestamp	COMMENT
LOW	flaml/automl/data.py	696	# Check if timestamp	COMMENT
LOW	flaml/tune/spark/utils.py	165	# Check if Spark is available	COMMENT
LOW	…aml/autogen/agentchat/contrib/math_user_proxy_agent.py	233	# Check if there is any print statement	COMMENT

AI Slop Vocabulary1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	test/autogen/oai/test_completion.py	279	# a more comprehensive tuning example	COMMENT

Decorative Section Separators1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	flaml/automl/time_series/sklearn.py	171	# ----------	COMMENT

TODO Padding1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	test/nlp/test_default.py	167	# TODO: implement _test_zero_shot_model	COMMENT

Structural Annotation Overuse1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	flaml/onlineml/trial_runner.py	115	# NOTE: This function consists of the following several parts:	COMMENT

Slop Phrases1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	flaml/autogen/code_utils.py	65	# When the user needs to run multiple blocks in sequence, make sure to output all the blocks to run in a right order.	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings