roboflow/supervision

29.5

Adjusted Score

29.5

Raw Score

100%

Time Factor

2026-07-13

Last Push

48.0K

Stars

Python

Language

98.2K

Lines of Code

327

Files

1.7K

Pattern Hits

2026-07-14

Scan Date

0.76

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

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

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 247MEDIUM 127LOW 1374

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 1748 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 Identifiers1084 hits · 974 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_public_api.py	12	def test_all_symbols_are_importable(symbol_name: str) -> None:	CODE
LOW	tests/test_public_api.py	31	def test_shipped_imports_are_listed_in_all(symbol_name: str) -> None:	CODE
LOW	tests/test_validate_deprecations.py	99	def test_validate_public_shims_warn(call: Callable[[], object], version: str) -> None:	CODE
LOW	tests/test_validate_deprecations.py	104	def test_private_validation_paths_do_not_warn() -> None:	CODE
LOW	tests/test_validate_deprecations.py	124	def test_import_supervision_stays_silent_about_bytetrack() -> None:	CODE
LOW	tests/helpers.py	597	def create_predictions_with_class_iou_tests(	CODE
LOW⚡	tests/classification/test_core.py	95	def test_from_clip_empty_output_dtypes() -> None:	CODE
LOW⚡	tests/classification/test_core.py	104	def test_from_timm_empty_output_dtypes() -> None:	CODE
LOW⚡	tests/classification/test_core.py	113	def test_from_timm_softmaxes_logits() -> None:	CODE
LOW	tests/classification/test_core.py	126	def test_classifications_compare_numpy_fields_by_value() -> None:	CODE
LOW	tests/metrics/test_size_bucket_regressions.py	47	def test_size_bucket_match_is_not_stolen(	CODE
LOW	tests/metrics/test_size_bucket_regressions.py	76	def test_small_bucket_mar_returns_zero_without_bucket_targets() -> None:	CODE
LOW	tests/metrics/test_size_bucket_regressions.py	101	def test_medium_bucket_mar_counts_global_rank_budget() -> None:	CODE
LOW	tests/metrics/test_size_bucket_regressions.py	145	def test_mask_target_requires_masks(metric_cls, missing_side) -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	148	def complex_scenario_predictions():	CODE
LOW	tests/metrics/test_mean_average_recall.py	287	def two_class_two_image_detections():	CODE
LOW	tests/metrics/test_mean_average_recall.py	327	def three_class_single_image_detections():	CODE
LOW	tests/metrics/test_mean_average_recall.py	367	def test_compute_value_error_for_missing_required_fields_after_update(	CODE
LOW	tests/metrics/test_mean_average_recall.py	403	def test_mask_content_preserves_compact_mask() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	419	def test_compute_with_compact_mask_matches_dense() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	440	def test_single_perfect_detection() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	456	def test_recall_per_class_keeps_each_max_detection_cutoff() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	483	def test_empty_inputs_keep_max_detection_axis() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	505	def test_medium_bucket_scores_target_matched_small_prediction() -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	536	def test_compute_value_error_for_missing_required_fields(missing_attribute) -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	570	def test_complex_integration_scenario(	CODE
LOW	tests/metrics/test_mean_average_recall.py	598	def test_mar_at_k_limits_per_image_not_per_class(	CODE
LOW	tests/metrics/test_mean_average_recall.py	655	def test_three_class_single_image_scenario(three_class_single_image_detections) -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	702	def test_dataset_split_integration(yolo_dataset_two_classes) -> None:	CODE
LOW	tests/metrics/test_mean_average_recall.py	784	def test_greedy_matching_two_valid_pairs():	CODE
LOW	tests/metrics/test_f1_score.py	13	def predictions_multiple_classes(self):	CODE
LOW⚡	tests/metrics/test_f1_score.py	40	def test_initialization_default(self):	CODE
LOW⚡	tests/metrics/test_f1_score.py	48	def test_initialization_custom(self):	CODE
LOW⚡	tests/metrics/test_f1_score.py	57	def test_mask_content_preserves_compact_mask(self) -> None:	CODE
LOW	tests/metrics/test_f1_score.py	72	def test_compute_with_compact_mask_matches_dense(self) -> None:	CODE
LOW	tests/metrics/test_f1_score.py	163	def test_medium_bucket_scores_target_matched_small_prediction(self) -> None:	CODE
LOW	tests/metrics/test_f1_score.py	180	def test_false_positives_on_background_image_counted(self):	CODE
LOW	tests/metrics/test_f1_score.py	223	def test_false_positives_of_absent_class_counted(self, method, expected):	CODE
LOW	tests/metrics/test_f1_score.py	246	def test_false_positives_on_background_image_weighted_returns_zero(self):	CODE
LOW	tests/metrics/test_f1_score.py	260	def test_single_class_mixed_results(	CODE
LOW	tests/metrics/test_f1_score.py	275	def test_precision_recall_imbalance(	CODE
LOW	tests/metrics/test_f1_score.py	308	def test_different_iou_thresholds(self, predictions_iou_064, targets_iou_064):	CODE
LOW	tests/metrics/test_f1_score.py	344	def test_mismatched_list_lengths(self, detections_50_50, targets_50_50):	CODE
LOW	tests/metrics/test_f1_score.py	356	def test_compute_value_error_for_missing_required_fields(	CODE
LOW	tests/metrics/test_f1_score.py	443	def test_greedy_matching_two_valid_pairs(self):	CODE
LOW	tests/metrics/test_lazy_imports.py	50	def test_metrics_package_import_keeps_pyplot_lazy() -> None:	CODE
LOW	tests/metrics/test_lazy_imports.py	60	def test_precision_plot_imports_pyplot_on_demand(monkeypatch) -> None:	CODE
LOW	tests/metrics/conftest.py	65	def predictions_multiple_classes():	CODE
LOW	tests/metrics/conftest.py	112	def predictions_confidence_ranking():	CODE
LOW	tests/metrics/test_mean_average_precision.py	38	def test_single_perfect_detection(self, detections_50_50, targets_50_50):	CODE
LOW	tests/metrics/test_mean_average_precision.py	47	def test_multiple_perfect_detections(self):	CODE
LOW	tests/metrics/test_mean_average_precision.py	66	def test_perfect_non_square_oriented_boxes_get_full_map(self):	CODE
LOW	tests/metrics/test_mean_average_precision.py	92	def test_batch_updates_perfect_detections(self, detections_50_50, targets_50_50):	CODE
LOW	tests/metrics/test_mean_average_precision.py	312	def test_mixed_classes_with_missing_detections(	CODE
LOW	tests/metrics/test_mean_average_precision.py	342	def test_empty_predictions_and_targets(self):	CODE
LOW	tests/metrics/test_mean_average_precision.py	393	def test_mask_pixel_count_drives_size_buckets(self) -> None:	CODE
LOW	tests/metrics/test_mean_average_precision.py	416	def test_boxes_target_ignores_masks(self) -> None:	CODE
LOW	tests/metrics/test_mean_average_precision.py	462	def test_missing_oriented_boxes_raise(self) -> None:	CODE
LOW	tests/metrics/test_mean_average_precision.py	478	def test_cross_matched_obb_orients_iou_correctly(self) -> None:	CODE
LOW	tests/metrics/test_mean_average_precision.py	510	def test_crowd_gt_ignores_contained_detection(self) -> None:	CODE
1024 more matches not shown…

Docstring Block Structure191 hits · 955 pts

Severity	File	Line	Snippet	Context
HIGH	tests/helpers.py	46	Create a Detections object from list-based inputs. This is a helper function primarily used for testing purpos	STRING
HIGH	tests/helpers.py	106	Create a KeyPoints object from list-based inputs. This is a helper function primarily used for testing purpose	STRING
HIGH	tests/helpers.py	170	Generate random bounding boxes within given image dimensions and size constraints. Creates `count` bounding bo	STRING
HIGH	tests/helpers.py	387	Create a synthetic YOLO-format dataset on disk. Generates dummy images with YOLO-format annotations, `data.yam	STRING
HIGH	tests/geometry/test_utils.py	9	Generate a semicircle with a given number of points. Parameters: n (int): amount of points in polyg	STRING
HIGH	src/supervision/metrics/detection.py	68	Convert Supervision Detections to a numpy tensor for metric computation. Args: detections: Detections/	STRING
HIGH	src/supervision/metrics/detection.py	443	Render detections onto a copy of ``scene`` with a title overlay. Args: scene: Source image panel (not mutat	STRING
HIGH	src/supervision/metrics/detection.py	689	Calculate confusion matrix based on predicted and ground-truth detections. Args: targets:	STRING
HIGH	src/supervision/metrics/detection.py	773	Calculate confusion matrix based on predicted and ground-truth detections. Args: predictio	STRING
HIGH	src/supervision/metrics/detection.py	1283	Calculate mean average precision based on predicted and ground-truth detections. Args: tar	STRING
HIGH	src/supervision/metrics/detection.py	1383	Calculate Mean Average Precision based on predicted and ground-truth detections at different thresh	STRING
HIGH	src/supervision/key_points/core.py	386	Create a `sv.KeyPoints` object from the [Roboflow](https://roboflow.com/) API inference result or the [	STRING
HIGH	src/supervision/key_points/core.py	470	Creates a `sv.KeyPoints` instance from a [MediaPipe](https://github.com/google-ai-edge/mediapipe)	STRING
HIGH	src/supervision/key_points/core.py	600	Creates a `sv.KeyPoints` instance from a [YOLOv8](https://github.com/ultralytics/ultralytics) pose infe	STRING
HIGH	src/supervision/key_points/core.py	637	Create a `sv.KeyPoints` instance from a [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLON	STRING
HIGH	src/supervision/key_points/core.py	695	Create a `sv.KeyPoints` object from the [Detectron2](https://github.com/facebookresearch/detectron2) in	STRING
HIGH	src/supervision/key_points/core.py	746	Create a `sv.KeyPoints` object from the [Transformers](https://github.com/huggingface/transformers) inf	STRING
HIGH	src/supervision/key_points/core.py	830	Filter keypoints using a 2D boolean mask of shape `(n, m)`. This method selects the **same set of keypoints fro	STRING
HIGH	src/supervision/key_points/core.py	1063	Get a subset of the KeyPoints object or access an item from its data field. Supports detection-level (	STRING
HIGH	src/supervision/key_points/core.py	1179	Merge a list of KeyPoints objects into a single KeyPoints object. This method takes a list of KeyPoint	STRING
HIGH	src/supervision/key_points/core.py	1300	Performs non-max suppression on the keypoint detections. Bounding boxes are derived from valid keypoint	STRING
HIGH	src/supervision/key_points/core.py	1385	Convert a KeyPoints object to a Detections object. This approximates the bounding box of the detected o	STRING
HIGH	src/supervision/key_points/annotators.py	62	Annotates the given scene with skeleton vertices based on the provided key points. It draws circles at	STRING
HIGH	src/supervision/key_points/annotators.py	154	Annotates the given scene by drawing lines between specified key points to form edges. Edges where eith	STRING
HIGH	src/supervision/key_points/annotators.py	420	Draws filled semi-transparent covariance ellipses around each keypoint. Args: scene: The i	STRING
HIGH	src/supervision/key_points/annotators.py	520	Draws stroke-only covariance ellipse outlines around each keypoint. Args: scene: The image	STRING
HIGH	src/supervision/key_points/annotators.py	624	Draws radially-fading covariance ellipses around each keypoint. Args: scene: The image to	STRING
HIGH	src/supervision/key_points/annotators.py	766	Draws labels at skeleton vertex positions on the image. Vertices marked not visible via ``key_points.vi	STRING
HIGH	src/supervision/dataset/core.py	211	Splits the dataset into two parts (training and testing) using the provided split_ratio. The input	STRING
HIGH	src/supervision/dataset/core.py	279	Merge a list of `DetectionDataset` objects into a single `DetectionDataset` object. This m	STRING
HIGH	src/supervision/dataset/core.py	459	Creates a Dataset instance from PASCAL VOC formatted data. Args: images_directory_path: Pa	STRING
HIGH	src/supervision/dataset/core.py	519	Creates a Dataset instance from YOLO formatted data. Args: images_directory_path: The path	STRING
HIGH	src/supervision/dataset/core.py	681	Creates a Dataset instance from LabelMe formatted data. LabelMe stores one JSON file per image, each c	STRING
HIGH	src/supervision/dataset/core.py	784	Creates a Dataset instance from CreateML formatted data. CreateML stores object-detection annotations	STRING
HIGH	src/supervision/dataset/core.py	838	Exports the dataset to CreateML format. This method saves the images and their corresponding annotation	STRING
HIGH	src/supervision/dataset/core.py	885	Creates a Dataset instance from COCO formatted data. Args: images_directory_path: The path	STRING
HIGH	src/supervision/dataset/core.py	1142	Splits the dataset into two parts (training and testing) using the provided split_ratio. A	STRING
HIGH	src/supervision/dataset/core.py	1245	Load data from a multiclass folder structure into a ClassificationDataset. Args: root_dire	STRING
HIGH	src/supervision/dataset/utils.py	148	Raise if two image paths would be written to the same output file. Dataset image paths may share a basename when th	STRING
HIGH	src/supervision/dataset/utils.py	238	Splits the data into two parts using the provided train_ratio. Args: data: The data to split.	STRING
HIGH	src/supervision/dataset/formats/coco.py	53	Convert a list of class names to COCO ``categories`` entries. Category ids are emitted 1-indexed to comply with the	STRING
HIGH	src/supervision/dataset/formats/coco.py	245	Convert `Detections` to COCO ``annotations`` entries. The internal 0-indexed ``Detections.class_id`` is serialized	STRING
HIGH	src/supervision/dataset/formats/coco.py	387	Generates a mapping from sequential class indices to original COCO class ids. This function is essential when	STRING
HIGH	src/supervision/dataset/formats/coco.py	461	Load COCO annotations and convert them to `Detections`. If `force_masks` is `False`, masks are still loaded fo	STRING
HIGH	src/supervision/dataset/formats/coco.py	590	Save a DetectionDataset to a COCO-format ``annotations.json`` file. Args: dataset: The DetectionDataset to	STRING
HIGH	src/supervision/dataset/formats/labelme.py	67	Convert a single image's LabelMe shapes into ``Detections``. Only ``rectangle`` and ``polygon`` shapes are imported	STRING
HIGH	src/supervision/dataset/formats/labelme.py	172	Load LabelMe annotations and convert them to ``Detections``. LabelMe stores one JSON file per image, each containin	STRING
HIGH	src/supervision/dataset/formats/labelme.py	304	Convert ``Detections`` into a list of LabelMe shape dicts. Masked detections are exported as ``polygon`` shapes (on	STRING
HIGH	src/supervision/dataset/formats/labelme.py	360	Export a ``DetectionDataset`` to per-image LabelMe ``.json`` files. Args: dataset: The ``DetectionDataset``	STRING
HIGH	src/supervision/dataset/formats/yolo.py	78	Return class names from a YOLO data.yaml file ordered by class index. Supports list and dict forms of the ``names``	STRING
HIGH	src/supervision/dataset/formats/yolo.py	316	Convert detections to YOLO annotation lines. Args: detections: The detections to serialize. Each detection	STRING
HIGH	src/supervision/dataset/formats/pascal_voc.py	30	Build a Pascal VOC ``<object>`` XML element for one detection. Coordinates are converted to 1-indexed Pascal VOC co	STRING
HIGH	src/supervision/dataset/formats/pascal_voc.py	390	Write Pascal VOC XML annotation files for every image in dataset. Args: dataset: Dataset whose annotation	STRING
HIGH	src/supervision/dataset/formats/createml.py	60	Convert a single image's CreateML annotations into ``Detections``. CreateML stores each box as a pixel-space centre	STRING
HIGH	src/supervision/dataset/formats/createml.py	135	Load CreateML object-detection annotations and convert them to ``Detections``. CreateML uses a single JSON file con	STRING
HIGH	src/supervision/dataset/formats/createml.py	225	Convert ``Detections`` into a list of CreateML annotation dicts. Each bounding box is stored as a pixel-space centr	STRING
HIGH	src/supervision/dataset/formats/createml.py	286	Export a ``DetectionDataset`` to a CreateML object-detection JSON file. Only the filename component of each image p	STRING
HIGH	src/supervision/annotators/core.py	228	Annotates the given scene with bounding boxes based on the provided detections. Args: scen	STRING
HIGH	src/supervision/annotators/core.py	531	Annotates the given scene with masks based on the provided detections. Args: scene: The im	STRING
HIGH	src/supervision/annotators/core.py	640	Annotates the given scene with polygons based on the provided detections. Args: scene: The	STRING
131 more matches not shown…

Decorative Section Separators118 hits · 429 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/dataset/test_core.py	709	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/dataset/test_core.py	711	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_core.py	634	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_core.py	636	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/dataset/test_progress.py	169	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/dataset/test_progress.py	171	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_progress.py	110	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_progress.py	112	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_progress.py	133	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/dataset/test_progress.py	135	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	148	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	150	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	181	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	183	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	213	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	215	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	245	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	247	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	275	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/draw/test_utils.py	277	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	201	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	203	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	313	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	315	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	373	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	375	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	434	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	436	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	480	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	482	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	537	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	539	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	602	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	604	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	709	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	711	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	755	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/test_from_adapters.py	757	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask_iou.py	23	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask_iou.py	25	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask_iou.py	383	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask_iou.py	385	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask.py	1092	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/test_compact_mask.py	1094	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	21	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	23	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	26	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	28	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	148	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	150	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	202	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	204	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	310	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	312	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	356	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/detection/tools/test_transformers.py	358	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/tools/test_transformers.py	65	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/tools/test_transformers.py	67	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/tools/test_transformers.py	109	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/detection/tools/test_transformers.py	111	# ---------------------------------------------------------------------------	COMMENT
58 more matches not shown…

Cross-File Repetition48 hits · 240 pts

Severity	File	Snippet	Context
HIGH	tests/metrics/test_mean_average_recall.py	test compute raises valueerror when required fields are missing.	STRING
HIGH	tests/metrics/test_f1_score.py	test compute raises valueerror when required fields are missing.	STRING
HIGH	tests/metrics/test_precision.py	test compute raises valueerror when required fields are missing.	STRING
HIGH	tests/metrics/test_recall.py	test compute raises valueerror when required fields are missing.	STRING
HIGH	tests/metrics/test_f1_score.py	test that mismatched prediction/target list lengths raise error	STRING
HIGH	tests/metrics/test_precision.py	test that mismatched prediction/target list lengths raise error	STRING
HIGH	tests/metrics/test_recall.py	test that mismatched prediction/target list lengths raise error	STRING
HIGH	tests/metrics/test_f1_score.py	greedy matching finds both tps; np.unique style missed the second pair. iou matrix: [[1.0, 0.667], [0.333, 0.538]]. at i	STRING
HIGH	tests/metrics/test_precision.py	greedy matching finds both tps; np.unique style missed the second pair. iou matrix: [[1.0, 0.667], [0.333, 0.538]]. at i	STRING
HIGH	tests/metrics/test_recall.py	greedy matching finds both tps; np.unique style missed the second pair. iou matrix: [[1.0, 0.667], [0.333, 0.538]]. at i	STRING
HIGH	examples/time_in_zone/rfdetr_file_example.py	calculating detections dwell time in zones, using rtsp stream. args: rtsp_url: complete rtsp url for the video stream zo	STRING
HIGH	examples/time_in_zone/rfdetr_stream_example.py	calculating detections dwell time in zones, using rtsp stream. args: rtsp_url: complete rtsp url for the video stream zo	STRING
HIGH	examples/time_in_zone/rfdetr_naive_stream_example.py	calculating detections dwell time in zones, using rtsp stream. args: rtsp_url: complete rtsp url for the video stream zo	STRING
HIGH	examples/time_in_zone/utils/general.py	load polygon zone configurations from a json file. this function reads a json file which contains polygon coordinates, a	STRING
HIGH	examples/count_people_in_zone/ultralytics_example.py	load polygon zone configurations from a json file. this function reads a json file which contains polygon coordinates, a	STRING
HIGH	examples/count_people_in_zone/inference_example.py	load polygon zone configurations from a json file. this function reads a json file which contains polygon coordinates, a	STRING
HIGH	src/supervision/metrics/recall.py	reset the metric to its initial state, clearing all stored data.	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	reset the metric to its initial state, clearing all stored data.	STRING
HIGH	src/supervision/metrics/f1_score.py	reset the metric to its initial state, clearing all stored data.	STRING
HIGH	src/supervision/metrics/precision.py	reset the metric to its initial state, clearing all stored data.	STRING
HIGH	src/supervision/metrics/mean_average_precision.py	reset the metric to its initial state, clearing all stored data.	STRING
HIGH	src/supervision/metrics/recall.py	add new predictions and targets to the metric, but do not compute the result. args: predictions: the predicted detection	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	add new predictions and targets to the metric, but do not compute the result. args: predictions: the predicted detection	STRING
HIGH	src/supervision/metrics/f1_score.py	add new predictions and targets to the metric, but do not compute the result. args: predictions: the predicted detection	STRING
HIGH	src/supervision/metrics/precision.py	add new predictions and targets to the metric, but do not compute the result. args: predictions: the predicted detection	STRING
HIGH	src/supervision/metrics/mean_average_precision.py	add new predictions and targets to the metric, but do not compute the result. args: predictions: the predicted detection	STRING
HIGH	src/supervision/metrics/recall.py	compute the confusion matrix for each class and iou threshold. assumes the matches and prediction_class_ids are sorted b	STRING
HIGH	src/supervision/metrics/f1_score.py	compute the confusion matrix for each class and iou threshold. assumes the matches and prediction_class_ids are sorted b	STRING
HIGH	src/supervision/metrics/precision.py	compute the confusion matrix for each class and iou threshold. assumes the matches and prediction_class_ids are sorted b	STRING
HIGH	src/supervision/metrics/recall.py	broadcastable function, computing the precision from the confusion matrix. args: confusion_matrix: shape (n, ..., 3), wh	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	broadcastable function, computing the precision from the confusion matrix. args: confusion_matrix: shape (n, ..., 3), wh	STRING
HIGH	src/supervision/metrics/f1_score.py	broadcastable function, computing the precision from the confusion matrix. args: confusion_matrix: shape (n, ..., 3), wh	STRING
HIGH	src/supervision/metrics/precision.py	broadcastable function, computing the precision from the confusion matrix. args: confusion_matrix: shape (n, ..., 3), wh	STRING
HIGH	src/supervision/metrics/recall.py	return boxes, masks or oriented bounding boxes from detections. for the mask target this may return a :class:`~supervisi	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	return boxes, masks or oriented bounding boxes from detections. for the mask target this may return a :class:`~supervisi	STRING
HIGH	src/supervision/metrics/f1_score.py	return boxes, masks or oriented bounding boxes from detections. for the mask target this may return a :class:`~supervisi	STRING
HIGH	src/supervision/metrics/recall.py	return a copy of detections with contents filtered by object size.	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	return a copy of detections with contents filtered by object size.	STRING
HIGH	src/supervision/metrics/f1_score.py	return a copy of detections with contents filtered by object size.	STRING
HIGH	src/supervision/metrics/precision.py	return a copy of detections with contents filtered by object size.	STRING
HIGH	src/supervision/metrics/recall.py	filter predictions and targets by object size category.	STRING
HIGH	src/supervision/metrics/f1_score.py	filter predictions and targets by object size category.	STRING
HIGH	src/supervision/metrics/precision.py	filter predictions and targets by object size category.	STRING
HIGH	src/supervision/metrics/recall.py	convert the result to a pandas dataframe. returns: the result as a dataframe.	STRING
HIGH	src/supervision/metrics/mean_average_recall.py	convert the result to a pandas dataframe. returns: the result as a dataframe.	STRING
HIGH	src/supervision/metrics/f1_score.py	convert the result to a pandas dataframe. returns: the result as a dataframe.	STRING
HIGH	src/supervision/metrics/precision.py	convert the result to a pandas dataframe. returns: the result as a dataframe.	STRING
HIGH	src/supervision/metrics/mean_average_precision.py	convert the result to a pandas dataframe. returns: the result as a dataframe.	STRING

Unused Imports202 hits · 143 pts

Severity	File	Line	Context
LOW	tests/helpers.py	9	CODE
LOW	tests/classification/test_core.py	1	CODE
LOW	tests/metrics/test_lazy_imports.py	3	CODE
LOW	tests/metrics/test_core.py	3	CODE
LOW	tests/metrics/utils/test_utils.py	3	CODE
LOW	tests/metrics/utils/test_object_size.py	3	CODE
LOW	tests/metrics/utils/test_matching.py	3	CODE
LOW	tests/detection/tools/test_transformers.py	3	CODE
LOW	tests/detection/utils/test_iou_and_nms.py	1	CODE
LOW	examples/time_in_zone/rfdetr_file_example.py	1	CODE
LOW	examples/time_in_zone/rfdetr_stream_example.py	1	CODE
LOW	examples/time_in_zone/rfdetr_naive_stream_example.py	1	CODE
LOW	examples/compact_mask/bench_inference_api.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	10	CODE
LOW	src/supervision/__init__.py	35	CODE
LOW	src/supervision/__init__.py	35	CODE
LOW	src/supervision/__init__.py	35	CODE
LOW	src/supervision/__init__.py	35	CODE
LOW	src/supervision/__init__.py	41	CODE
LOW	src/supervision/__init__.py	42	CODE
LOW	src/supervision/__init__.py	42	CODE
LOW	src/supervision/__init__.py	42	CODE
LOW	src/supervision/__init__.py	47	CODE
LOW	src/supervision/__init__.py	48	CODE
LOW	src/supervision/__init__.py	49	CODE
LOW	src/supervision/__init__.py	50	CODE
LOW	src/supervision/__init__.py	50	CODE
LOW	src/supervision/__init__.py	50	CODE
LOW	src/supervision/__init__.py	55	CODE
LOW	src/supervision/__init__.py	56	CODE
LOW	src/supervision/__init__.py	56	CODE
LOW	src/supervision/__init__.py	60	CODE
LOW	src/supervision/__init__.py	61	CODE
LOW	src/supervision/__init__.py	61	CODE
LOW	src/supervision/__init__.py	62	CODE
LOW	src/supervision/__init__.py	63	CODE
LOW	src/supervision/__init__.py	63	CODE
LOW	src/supervision/__init__.py	63	CODE
142 more matches not shown…

Deep Nesting55 hits · 50 pts

Severity	File	Line	Context
LOW	tests/annotators/test_docs.py	38	CODE
LOW	examples/time_in_zone/scripts/draw_zones.py	128	CODE
LOW	examples/speed_estimation/ultralytics_example.py	39	CODE
LOW	examples/speed_estimation/yolo_nas_example.py	40	CODE
LOW	examples/speed_estimation/inference_example.py	40	CODE
LOW	src/supervision/metrics/detection.py	1041	CODE
LOW	src/supervision/metrics/detection.py	1148	CODE
LOW	src/supervision/metrics/recall.py	150	CODE
LOW	src/supervision/metrics/recall.py	316	CODE
LOW	src/supervision/metrics/mean_average_recall.py	386	CODE
LOW	src/supervision/metrics/f1_score.py	147	CODE
LOW	src/supervision/metrics/f1_score.py	353	CODE
LOW	src/supervision/metrics/precision.py	149	CODE
LOW	src/supervision/metrics/precision.py	349	CODE
LOW	src/supervision/metrics/mean_average_precision.py	506	CODE
LOW	src/supervision/metrics/mean_average_precision.py	822	CODE
LOW	src/supervision/metrics/mean_average_precision.py	947	CODE
LOW	src/supervision/metrics/mean_average_precision.py	1500	CODE
LOW	src/supervision/metrics/mean_average_precision.py	1579	CODE
LOW	src/supervision/key_points/core.py	467	CODE
LOW	src/supervision/key_points/core.py	945	CODE
LOW	src/supervision/key_points/annotators.py	153	CODE
LOW	src/supervision/key_points/annotators.py	343	CODE
LOW	src/supervision/key_points/annotators.py	760	CODE
LOW	src/supervision/dataset/formats/coco.py	158	CODE
LOW	src/supervision/dataset/formats/coco.py	237	CODE
LOW	src/supervision/dataset/formats/yolo.py	145	CODE
LOW	src/supervision/annotators/core.py	2188	CODE
LOW	src/supervision/annotators/core.py	2939	CODE
LOW	src/supervision/annotators/core.py	3136	CODE
LOW	src/supervision/annotators/utils.py	38	CODE
LOW	src/supervision/annotators/utils.py	78	CODE
LOW	src/supervision/utils/file.py	20	CODE
LOW	src/supervision/utils/video.py	248	CODE
LOW	src/supervision/utils/video.py	306	CODE
LOW	src/supervision/validators/__init__.py	191	CODE
LOW	src/supervision/detection/line_zone.py	807	CODE
LOW	src/supervision/detection/compact_mask.py	59	CODE
LOW	src/supervision/detection/compact_mask.py	254	CODE
LOW	src/supervision/detection/core.py	856	CODE
LOW	src/supervision/detection/core.py	2493	CODE
LOW	src/supervision/detection/vlm.py	692	CODE
LOW	src/supervision/detection/tools/inference_slicer.py	309	CODE
LOW	src/supervision/detection/tools/inference_slicer.py	474	CODE
LOW	src/supervision/detection/tools/inference_slicer.py	554	CODE
LOW	src/supervision/detection/utils/internal.py	166	CODE
LOW	src/supervision/detection/utils/internal.py	285	CODE
LOW	src/supervision/detection/utils/internal.py	532	CODE
LOW	src/supervision/detection/utils/internal.py	593	CODE
LOW	src/supervision/detection/utils/internal.py	647	CODE
LOW	src/supervision/detection/utils/iou_and_nms.py	449	CODE
LOW	src/supervision/detection/utils/iou_and_nms.py	1390	CODE
LOW	src/supervision/detection/utils/iou_and_nms.py	1514	CODE
LOW	src/supervision/detection/utils/masks.py	330	CODE
LOW	src/supervision/detection/utils/converters.py	290	CODE

Cross-Language Confusion4 hits · 30 pts

Severity	File	Line	Snippet	Context
HIGH	tests/detection/test_compact_mask_iou.py	193	# Ensure no all-false mask (diagonal would be undefined).	COMMENT
HIGH	src/supervision/metrics/recall.py	353	# undefined, so report 0 as the empty case did before.	COMMENT
HIGH	src/supervision/metrics/f1_score.py	403	# undefined, so report 0 as the empty case did before.	COMMENT
HIGH	src/supervision/metrics/precision.py	399	# undefined, so report 0 as the empty case did before.	COMMENT

Magic Placeholder Names4 hits · 20 pts

Severity	File	Line	Snippet	Context
HIGH	docs/how_to/benchmark_a_model.md	53	rf = Roboflow(api_key="<YOUR_API_KEY>")	CODE
HIGH	docs/how_to/benchmark_a_model.md	53	rf = Roboflow(api_key="<YOUR_API_KEY>")	CODE
HIGH	docs/how_to/benchmark_a_model.md	67	rf = Roboflow(api_key="<YOUR_API_KEY>")	CODE
HIGH	docs/how_to/benchmark_a_model.md	67	rf = Roboflow(api_key="<YOUR_API_KEY>")	CODE

Self-Referential Comments4 hits · 12 pts

Severity	File	Line	Snippet	Context
MEDIUM	src/supervision/metrics/mean_average_precision.py	516	# Create an empty EvaluationDataset object for the predictions	COMMENT
MEDIUM	src/supervision/metrics/mean_average_precision.py	1657	# Create a coco object with the targets	COMMENT
MEDIUM	src/supervision/metrics/mean_average_precision.py	1661	# Create a coco evaluator with the predictions	COMMENT
MEDIUM	src/supervision/metrics/mean_average_precision.py	1707	# Create the final MeanAveragePrecisionResult object	COMMENT

AI Structural Patterns12 hits · 10 pts

Severity	File	Line	Context
LOW	examples/heatmap_and_track/script.py	13	CODE
LOW	src/supervision/dataset/core.py	576	CODE
LOW	src/supervision/dataset/core.py	933	CODE
LOW	src/supervision/annotators/core.py	108	CODE
LOW	src/supervision/annotators/core.py	1318	CODE
LOW	src/supervision/annotators/core.py	1669	CODE
LOW	src/supervision/annotators/core.py	3285	CODE
LOW	src/supervision/utils/image.py	633	CODE
LOW	src/supervision/detection/line_zone.py	356	CODE
LOW	src/supervision/detection/line_zone.py	752	CODE
LOW	src/supervision/detection/tools/inference_slicer.py	262	CODE
LOW	src/supervision/detection/tools/polygon_zone.py	143	CODE

Modern Structural Boilerplate9 hits · 9 pts

Severity	File	Line	Snippet	Context
LOW	src/supervision/__init__.py	165	__all__ = [	CODE
LOW	src/supervision/metrics/__init__.py	23	__all__ = [	CODE
LOW	src/supervision/key_points/core.py	29	logger = logging.getLogger(__name__)	CODE
LOW	src/supervision/dataset/utils.py	3	__all__ = ["check_no_basename_collisions", "train_test_split"]	CODE
LOW	src/supervision/dataset/formats/labelme.py	31	__all__ = [	CODE
LOW	src/supervision/tracker/__init__.py	5	__all__ = ["ByteTrack"]	CODE
LOW	src/supervision/assets/__init__.py	4	__all__ = ["ImageAssets", "VideoAssets", "download_assets"]	CODE
LOW	src/supervision/detection/line_zone.py	325	def _update_class_id_to_name(self, detections: Detections) -> None:	CODE
LOW	src/supervision/detection/utils/internal.py	15	logger = logging.getLogger(__name__)	CODE

Modern AI Meta-Vocabulary3 hits · 8 pts

Severity	File	Line	Snippet	Context
MEDIUM	docs/llms.txt	112	- Zero-shot object detection with YOLO-World: https://supervision.roboflow.com/latest/cookbooks/#zero-shot-object-detect	CODE
MEDIUM	docs/llms.full.txt	121	- Zero-shot object detection with YOLO-World: https://supervision.roboflow.com/latest/cookbooks/#zero-shot-object-detect	CODE
MEDIUM⚡	examples/compact_mask/benchmark.py	622	# Scenario runner — orchestrates stages	COMMENT

Redundant / Tautological Comments5 hits · 7 pts

Severity	File	Line	Snippet	Context
LOW	examples/traffic_analysis/setup.sh	6	# Check if 'data' directory does not exist and then create it	COMMENT
LOW	examples/count_people_in_zone/setup.sh	6	# Check if 'data' directory does not exist and then create it	COMMENT
LOW	src/supervision/metrics/mean_average_precision.py	536	# Check if the predictions contain any unsupported keys	COMMENT
LOW	src/supervision/metrics/mean_average_precision.py	1085	# Set recall to either the final recall value or 0 (when there	COMMENT
LOW	src/supervision/detection/compact_mask.py	162	# Check if last run has same parity (True/False) as current chunk.	COMMENT

Excessive Try-Catch Wrapping5 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	src/supervision/utils/video.py	215	except Exception as exc:	CODE
LOW	src/supervision/utils/video.py	440	except Exception as exc:	CODE
LOW	src/supervision/assets/downloader.py	58	except Exception:	CODE
LOW	src/supervision/detection/vlm.py	302	except Exception:	CODE
LOW	src/supervision/detection/vlm.py	797	except Exception:	CODE

AI Slop Vocabulary1 hit · 3 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	145	# Enable linting rules for code style, imports, and best practices.	COMMENT

Dead Code1 hit · 2 pts

Severity	File	Line	Snippet	Context
MEDIUM	src/supervision/metrics/recall.py	513		CODE

Over-Commented Block1 hit · 1 pts

Severity	File	Line	Snippet	Context
LOW	src/supervision/config.py	1	CLASS_NAME_DATA_FIELD: str = "class_name"	COMMENT

Overly Generic Function Names1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	src/supervision/utils/internal.py	142	def my_method(cls):	STRING

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings