mindee/doctr

15.4

Adjusted Score

15.4

Raw Score

100%

Time Factor

2026-07-09

Last Push

6.2K

Stars

Python

Language

46.8K

Lines of Code

298

Files

500

Pattern Hits

2026-07-14

Scan Date

0.16

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 48MEDIUM 14LOW 438

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 500 distinct pattern matches across 15 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.

Cross-File Repetition46 hits · 230 pts

Severity	File	Snippet	Context
HIGH	references/classification/train_orientation.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/classification/train_character.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/layout/train.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/table/train.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/recognition/train.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/detection/train.py	gridsearch the optimal learning rate for the training. adapted from https://github.com/frgfm/holocron/blob/master/holocr	STRING
HIGH	references/classification/utils.py	display the results of the lr grid search. adapted from https://github.com/frgfm/holocron/blob/master/holocron/trainer/c	STRING
HIGH	references/layout/utils.py	display the results of the lr grid search. adapted from https://github.com/frgfm/holocron/blob/master/holocron/trainer/c	STRING
HIGH	references/detection/utils.py	display the results of the lr grid search. adapted from https://github.com/frgfm/holocron/blob/master/holocron/trainer/c	STRING
HIGH	references/recognition/utils.py	display the results of the lr grid search. adapted from https://github.com/frgfm/holocron/blob/master/holocron/trainer/c	STRING
HIGH	doctr/models/classification/mobilenet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/vip/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/starnet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/vit_det/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/resnet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/vit/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/textnet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/classification/vgg/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/layout/lw_detr/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/table_structure/tablecenternet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/crnn/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/vitstr/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/viptr/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/master/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/sar/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/parseq/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	…odels/detection/differentiable_binarization/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/detection/linknet/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/detection/fast/pytorch.py	load pretrained parameters onto the model args: path_or_url: the path or url to the model parameters (checkpoint) **kwar	STRING
HIGH	doctr/models/recognition/core.py	encode a list of gts sequences into a np array and gives the corresponding* sequence lengths. args: gts: list of ground-	STRING
HIGH	doctr/models/recognition/vitstr/base.py	encode a list of gts sequences into a np array and gives the corresponding* sequence lengths. args: gts: list of ground-	STRING
HIGH	doctr/models/recognition/master/base.py	encode a list of gts sequences into a np array and gives the corresponding* sequence lengths. args: gts: list of ground-	STRING
HIGH	doctr/models/recognition/parseq/base.py	encode a list of gts sequences into a np array and gives the corresponding* sequence lengths. args: gts: list of ground-	STRING
HIGH	doctr/models/recognition/core.py	abstract class to postprocess the raw output of the model args: vocab: string containing the ordered sequence of support	STRING
HIGH	doctr/models/recognition/vitstr/base.py	abstract class to postprocess the raw output of the model args: vocab: string containing the ordered sequence of support	STRING
HIGH	doctr/models/recognition/master/base.py	abstract class to postprocess the raw output of the model args: vocab: string containing the ordered sequence of support	STRING
HIGH	doctr/models/recognition/parseq/base.py	abstract class to postprocess the raw output of the model args: vocab: string containing the ordered sequence of support	STRING
HIGH	doctr/models/recognition/vitstr/pytorch.py	compute categorical cross-entropy loss for the model. sequences are masked after the eos character. args: gt: the encode	STRING
HIGH	doctr/models/recognition/sar/pytorch.py	compute categorical cross-entropy loss for the model. sequences are masked after the eos character. args: gt: the encode	STRING
HIGH	doctr/models/recognition/master/pytorch.py	compute categorical cross-entropy loss for the model. sequences are masked after the eos character. args: gt: the encode	STRING
HIGH	…r/models/detection/differentiable_binarization/base.py	expand a polygon (points) by a factor unclip_ratio, and returns a polygon args: points: the first parameter. returns: a	STRING
HIGH	doctr/models/detection/linknet/base.py	expand a polygon (points) by a factor unclip_ratio, and returns a polygon args: points: the first parameter. returns: a	STRING
HIGH	doctr/models/detection/fast/base.py	expand a polygon (points) by a factor unclip_ratio, and returns a polygon args: points: the first parameter. returns: a	STRING
HIGH	…r/models/detection/differentiable_binarization/base.py	compute boxes from a bitmap/pred_map: find connected components then filter boxes args: pred: pred map from differentiab	STRING
HIGH	doctr/models/detection/linknet/base.py	compute boxes from a bitmap/pred_map: find connected components then filter boxes args: pred: pred map from differentiab	STRING
HIGH	doctr/models/detection/fast/base.py	compute boxes from a bitmap/pred_map: find connected components then filter boxes args: pred: pred map from differentiab	STRING

Unused Imports128 hits · 126 pts

Severity	File	Line	Context
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	1	CODE
LOW	doctr/__init__.py	2	CODE
LOW	doctr/datasets/__init__.py	1	CODE
LOW	doctr/datasets/__init__.py	2	CODE
LOW	doctr/datasets/__init__.py	3	CODE
LOW	doctr/datasets/__init__.py	4	CODE
LOW	doctr/datasets/__init__.py	5	CODE
LOW	doctr/datasets/__init__.py	6	CODE
LOW	doctr/datasets/__init__.py	7	CODE
LOW	doctr/datasets/__init__.py	8	CODE
LOW	doctr/datasets/__init__.py	9	CODE
LOW	doctr/datasets/__init__.py	10	CODE
LOW	doctr/datasets/__init__.py	11	CODE
LOW	doctr/datasets/__init__.py	12	CODE
LOW	doctr/datasets/__init__.py	13	CODE
LOW	doctr/datasets/__init__.py	14	CODE
LOW	doctr/datasets/__init__.py	15	CODE
LOW	doctr/datasets/__init__.py	16	CODE
LOW	doctr/datasets/__init__.py	17	CODE
LOW	doctr/datasets/__init__.py	18	CODE
LOW	doctr/datasets/__init__.py	19	CODE
LOW	doctr/datasets/__init__.py	20	CODE
LOW	doctr/datasets/__init__.py	21	CODE
LOW	doctr/datasets/__init__.py	22	CODE
LOW	doctr/datasets/__init__.py	23	CODE
LOW	doctr/datasets/__init__.py	24	CODE
LOW	doctr/datasets/datasets/__init__.py	1	CODE
LOW	doctr/datasets/generator/__init__.py	1	CODE
LOW	doctr/io/__init__.py	1	CODE
LOW	doctr/io/__init__.py	2	CODE
LOW	doctr/io/__init__.py	3	CODE
LOW	doctr/io/__init__.py	4	CODE
LOW	doctr/io/__init__.py	5	CODE
LOW	doctr/io/image/__init__.py	1	CODE
LOW	doctr/io/image/__init__.py	2	CODE
LOW	doctr/utils/__init__.py	1	CODE
LOW	doctr/utils/__init__.py	2	CODE
LOW	doctr/utils/__init__.py	3	CODE
LOW	doctr/utils/__init__.py	4	CODE
LOW	doctr/models/__init__.py	1	CODE
LOW	doctr/models/__init__.py	2	CODE
LOW	doctr/models/__init__.py	3	CODE
LOW	doctr/models/__init__.py	4	CODE
LOW	doctr/models/__init__.py	5	CODE
LOW	doctr/models/__init__.py	6	CODE
LOW	doctr/models/__init__.py	7	CODE
LOW	doctr/models/classification/__init__.py	1	CODE
LOW	doctr/models/classification/__init__.py	2	CODE
LOW	doctr/models/classification/__init__.py	3	CODE
LOW	doctr/models/classification/__init__.py	4	CODE
LOW	doctr/models/classification/__init__.py	5	CODE
LOW	doctr/models/classification/__init__.py	6	CODE
LOW	doctr/models/classification/__init__.py	7	CODE
LOW	doctr/models/classification/__init__.py	8	CODE
LOW	doctr/models/classification/__init__.py	9	CODE
68 more matches not shown…

Hyper-Verbose Identifiers118 hits · 124 pts

Severity	File	Line	Snippet	Context
LOW	references/detection/train.py	39	def convert_to_multiclass_targets(targets: list) -> list[dict[str, np.ndarray]]:	CODE
LOW	tests/conftest.py	87	def mock_artefact_image_stream():	CODE
LOW	tests/common/test_utils_fonts.py	26	def test_get_font_respects_size():	CODE
LOW	tests/common/test_utils_fonts.py	33	def test_get_font_explicit_family():	CODE
LOW	tests/common/test_utils_fonts.py	46	def test_get_font_resolution_is_cached():	CODE
LOW	tests/common/test_models_builder.py	192	def test_documentbuilder_layout():	CODE
LOW	tests/common/test_models_builder.py	267	def test_documentbuilder_tables():	CODE
LOW	tests/common/test_models_builder.py	364	def test_kiedocumentbuilder_layout():	CODE
LOW	tests/common/test_models_builder.py	480	def test_documentbuilder_tables_straight_geometry():	CODE
LOW	tests/common/test_models_builder.py	527	def test_documentbuilder_argument_length_validation():	CODE
LOW	tests/common/test_models_builder.py	559	def test_sort_boxes_degenerate_heights():	CODE
LOW	tests/common/test_models_builder.py	567	def test_documentbuilder_tables_empty_cells():	CODE
LOW	tests/common/test_utils_geometry.py	81	def test_resolve_enclosing_bbox():	CODE
LOW	tests/common/test_utils_geometry.py	87	def test_resolve_enclosing_rbbox():	CODE
LOW	tests/common/test_utils_geometry.py	186	def test_remove_image_padding():	CODE
LOW	tests/common/test_utils_geometry.py	226	def test_convert_to_relative_coords(abs_geoms, img_size, rel_geoms):	CODE
LOW	tests/common/test_datasets_utils.py	24	def test_translate_unknown_vocab():	CODE
LOW	tests/common/test_datasets_utils.py	46	def test_encode_string_unknown_char():	CODE
LOW	tests/common/test_datasets_utils.py	51	def test_encode_string_duplicate_vocab_chars():	CODE
LOW	tests/common/test_datasets_utils.py	108	def test_convert_target_to_relative(target, mock_image_stream):	CODE
LOW	tests/common/test_datasets_utils.py	125	def test_crop_bboxes_from_image(geoms, mock_image_path):	CODE
LOW	tests/common/test_models_reading_order.py	34	def test_detect_text_direction(texts, language, expected):	CODE
LOW	tests/common/test_models_reading_order.py	38	def test_normalize_layout_label():	CODE
LOW	tests/common/test_models_reading_order.py	68	def test_sort_reading_order_basic():	CODE
LOW	tests/common/test_models_reading_order.py	80	def test_sort_reading_order_columns():	CODE
LOW	tests/common/test_models_reading_order.py	94	def test_sort_reading_order_input_formats():	CODE
LOW	tests/common/test_models_reading_order.py	107	def test_sort_reading_order_vertical():	CODE
LOW	tests/common/test_models_reading_order.py	117	def test_sort_reading_order_labels():	CODE
LOW	tests/common/test_models_reading_order.py	146	def test_sort_reading_order_degenerate_geometries():	CODE
LOW	tests/common/test_models_reading_order.py	153	def test_resolve_reading_segments():	CODE
LOW	tests/common/test_models_reading_order.py	170	def test_assign_layout_labels():	CODE
LOW	tests/common/test_models_reading_order.py	183	def test_reading_order_predictor():	CODE
LOW	tests/common/test_models_reading_order.py	200	def test_sort_reading_order_fragmented_columns():	CODE
LOW	tests/common/test_models_detection.py	65	def test_linknet_postprocessor():	CODE
LOW	tests/common/test_utils_data.py	21	def test_download_from_url_customizing_cache_dir(mkdir_mock, urlretrieve_mock):	CODE
LOW	tests/common/test_utils_data.py	29	def test_download_from_url_error_creating_directory(logging_mock, mkdir_mock):	CODE
LOW	tests/common/test_utils_data.py	41	def test_download_from_url_error_creating_directory_with_env_var(logging_mock, mkdir_mock):	CODE
LOW	tests/common/test_io.py	103	def test_read_img_as_numpy_exif_orientation(tmpdir_factory):	CODE
LOW	tests/common/test_models_layout.py	7	def test_lwdetr_postprocessor():	CODE
LOW	tests/common/test_models_table_structure.py	23	def test_tablecenternet_postprocessor(assume_straight_pages):	CODE
LOW	tests/common/test_models_table_structure.py	59	def test_tablecenternet_build_target(use_polygons):	CODE
LOW	tests/common/test_models_table_structure.py	128	def test_tablecenternet_build_target_box_polygon_equivalence():	CODE
LOW	tests/common/test_models_table_structure.py	146	def test_tablecenternet_build_target_rejects_invalid_cell_shape(cells):	CODE
LOW	tests/common/test_utils_metrics.py	109	def test_localization_confusion(gts, preds, iou_thresh, recall, precision, mean_iou):	CODE
LOW	tests/common/test_utils_metrics.py	150	def test_r_localization_confusion(gts, preds, iou_thresh, recall, precision, mean_iou):	CODE
LOW	tests/common/test_utils_metrics.py	161	def test_localization_confusion_empty_gt(use_polygons):	CODE
LOW	tests/common/test_utils_metrics.py	329	def test_detection_metric_empty_gt():	CODE
LOW	tests/common/test_utils_metrics.py	405	def test_object_detection_metric_basic(gt_boxes, gt_labels, pred_boxes, pred_labels, pred_scores, expected_keys):	CODE
LOW	tests/common/test_utils_metrics.py	434	def test_object_detection_metric_cases():	CODE
LOW	tests/common/test_models.py	31	def test_estimate_orientation(mock_image, mock_bitmap, mock_tilted_payslip):	CODE
LOW	tests/common/test_models_detection_utils.py	74	def test_remove_padding_does_not_mutate_input():	CODE
LOW	tests/common/test_models_recognition_predictor.py	105	def test_invalid_split_overlap_ratio(split_overlap_ratio):	CODE
LOW	tests/common/test_utils_reconstitution.py	42	def test_synthesize_page_colors():	CODE
LOW	tests/common/test_utils_reconstitution.py	56	def test_synthesize_page_font_size_bounds():	CODE
LOW	tests/common/test_utils_reconstitution.py	62	def test_synthesize_page_unicode():	CODE
LOW	tests/common/test_utils_reconstitution.py	86	def test_synthesize_kie_page_rotated_prediction(caplog):	CODE
LOW	tests/common/test_utils_reconstitution.py	106	def test_synthesize_page_words_do_not_overlap():	CODE
LOW	tests/common/test_utils_reconstitution.py	134	def test_synthesize_page_rotated_line():	CODE
LOW	tests/common/test_cli.py	23	def test_parse_args_boolean_optional_flags():	CODE
LOW	tests/common/test_cli.py	35	def test_parse_args_requires_input_path():	CODE
58 more matches not shown…

Modern Structural Boilerplate106 hits · 106 pts

Severity	File	Line	Snippet	Context
LOW	doctr/file_utils.py	9	__all__ = ["requires_package", "CLASS_NAME"]	CODE
LOW	doctr/datasets/recognition.py	13	__all__ = ["RecognitionDataset"]	CODE
LOW	doctr/datasets/synthtext.py	18	__all__ = ["SynthText"]	CODE
LOW	doctr/datasets/detection.py	17	__all__ = ["DetectionDataset"]	CODE
LOW	doctr/datasets/coco_text.py	17	__all__ = ["COCOTEXT"]	CODE
LOW	doctr/datasets/orientation.py	13	__all__ = ["OrientationDataset"]	CODE
LOW	doctr/datasets/table_structure.py	19	__all__ = ["TableStructureDataset"]	CODE
LOW	doctr/datasets/layout.py	15	__all__ = ["LayoutDataset"]	CODE
LOW	doctr/datasets/cord.py	17	__all__ = ["CORD"]	CODE
LOW	doctr/datasets/mjsynth.py	13	__all__ = ["MJSynth"]	CODE
LOW	doctr/datasets/wildreceipt.py	17	__all__ = ["WILDRECEIPT"]	CODE
LOW	doctr/datasets/doc_artefacts.py	14	__all__ = ["DocArtefacts"]	CODE
LOW	doctr/datasets/svhn.py	16	__all__ = ["SVHN"]	CODE
LOW	doctr/datasets/iiit5k.py	17	__all__ = ["IIIT5K"]	CODE
LOW	doctr/datasets/imgur5k.py	20	__all__ = ["IMGUR5K"]	CODE
LOW	doctr/datasets/ic13.py	17	__all__ = ["IC13"]	CODE
LOW	doctr/datasets/ocr.py	15	__all__ = ["OCRDataset"]	CODE
LOW	doctr/datasets/ic03.py	16	__all__ = ["IC03"]	CODE
LOW	doctr/datasets/utils.py	22	__all__ = [	CODE
LOW	doctr/datasets/vocabs.py	9	__all__ = ["VOCABS"]	CODE
LOW	doctr/datasets/funsd.py	17	__all__ = ["FUNSD"]	CODE
LOW	doctr/datasets/sroie.py	17	__all__ = ["SROIE"]	CODE
LOW	doctr/datasets/iiithws.py	14	__all__ = ["IIITHWS"]	CODE
LOW	doctr/datasets/svt.py	16	__all__ = ["SVT"]	CODE
LOW	doctr/datasets/datasets/pytorch.py	18	__all__ = ["AbstractDataset", "VisionDataset"]	CODE
LOW	doctr/datasets/datasets/base.py	15	__all__ = ["_AbstractDataset", "_VisionDataset"]	CODE
LOW	doctr/datasets/generator/pytorch.py	8	__all__ = ["CharacterGenerator", "WordGenerator"]	CODE
LOW	doctr/io/elements.py	25	__all__ = [	CODE
LOW	doctr/io/html.py	8	__all__ = ["read_html"]	CODE
LOW	doctr/io/pdf.py	13	__all__ = ["read_pdf"]	CODE
LOW	doctr/io/reader.py	18	__all__ = ["DocumentFile"]	CODE
LOW	doctr/io/image/pytorch.py	15	__all__ = ["tensor_from_pil", "read_img_as_tensor", "decode_img_as_tensor", "tensor_from_numpy", "get_img_shape"]	CODE
LOW	doctr/io/image/base.py	13	__all__ = ["read_img_as_numpy"]	CODE
LOW	doctr/utils/metrics.py	12	__all__ = [	CODE
LOW	doctr/utils/common_types.py	12	__all__ = ["Point2D", "BoundingBox", "Polygon4P", "Polygon", "Bbox", "Sample"]	CODE
LOW	doctr/utils/visualization.py	17	__all__ = ["visualize_page", "visualize_kie_page", "draw_boxes"]	CODE
LOW	doctr/utils/repr.py	9	__all__ = ["NestedObject"]	CODE
LOW	doctr/utils/geometry.py	13	__all__ = [	CODE
LOW	doctr/utils/reconstitution.py	16	__all__ = ["synthesize_page", "synthesize_kie_page"]	CODE
LOW	doctr/utils/fonts.py	12	__all__ = ["get_font"]	CODE
LOW	doctr/utils/data.py	18	__all__ = ["download_from_url"]	CODE
LOW	doctr/utils/multithreading.py	15	__all__ = ["multithread_exec"]	CODE
LOW	doctr/models/zoo.py	15	__all__ = ["ocr_predictor", "kie_predictor"]	CODE
LOW	doctr/models/core.py	11	__all__ = ["BaseModel"]	CODE
LOW	doctr/models/builder.py	29	__all__ = ["DocumentBuilder"]	CODE
LOW	doctr/models/_utils.py	17	__all__ = [	CODE
LOW	doctr/models/classification/zoo.py	14	__all__ = ["crop_orientation_predictor", "page_orientation_predictor"]	CODE
LOW	doctr/models/classification/magc_resnet/pytorch.py	19	__all__ = ["magc_resnet31"]	CODE
LOW	doctr/models/classification/mobilenet/pytorch.py	19	__all__ = [	CODE
LOW	doctr/models/classification/vip/pytorch.py	26	__all__ = ["VIPNet", "vip_tiny", "vip_base"]	CODE
LOW	doctr/models/classification/vip/layers/pytorch.py	13	__all__ = [	CODE
LOW	doctr/models/classification/starnet/pytorch.py	21	__all__ = ["StarNet", "starnet_s3"]	CODE
LOW	doctr/models/classification/vit_det/pytorch.py	20	__all__ = ["VisionDetectionTransformer", "vit_det_s", "vit_det_m"]	CODE
LOW	doctr/models/classification/vit_det/layers/pytorch.py	12	__all__ = ["PatchEmbed", "MLP", "AttentionWithCAE", "WindowedCAETransformerBlock"]	CODE
LOW	doctr/models/classification/resnet/pytorch.py	23	__all__ = ["ResNet", "resnet18", "resnet31", "resnet34", "resnet50", "resnet34_wide", "resnet_stage"]	CODE
LOW	doctr/models/classification/vit/pytorch.py	18	__all__ = ["VisionTransformer", "vit_s", "vit_b"]	CODE
LOW	doctr/models/classification/predictor/pytorch.py	14	__all__ = ["OrientationPredictor"]	CODE
LOW	doctr/models/classification/textnet/pytorch.py	17	__all__ = ["TextNet", "textnet_tiny", "textnet_small", "textnet_base"]	CODE
LOW	doctr/models/classification/vgg/pytorch.py	18	__all__ = ["VGG", "vgg16_bn_r"]	CODE
LOW	doctr/models/kie_predictor/pytorch.py	21	__all__ = ["KIEPredictor"]	CODE
46 more matches not shown…

Deep Nesting53 hits · 53 pts

Severity	File	Line	Context
LOW	demo/app.py	20	CODE
LOW	references/layout/utils.py	40	CODE
LOW	references/recognition/train.py	193	CODE
LOW	references/recognition/evaluate.py	27	CODE
LOW	references/detection/utils.py	12	CODE
LOW	references/detection/train.py	174	CODE
LOW	references/detection/train.py	213	CODE
LOW	tests/common/test_models_detection_utils.py	29	CODE
LOW	tests/common/test_headers.py	7	CODE
LOW	tests/common/test_io_elements.py	564	CODE
LOW	tests/common/test_io_elements.py	607	CODE
LOW	doctr/datasets/synthtext.py	51	CODE
LOW	doctr/datasets/coco_text.py	47	CODE
LOW	doctr/datasets/cord.py	52	CODE
LOW	doctr/datasets/wildreceipt.py	50	CODE
LOW	doctr/datasets/svhn.py	51	CODE
LOW	doctr/datasets/iiit5k.py	45	CODE
LOW	doctr/datasets/imgur5k.py	54	CODE
LOW	doctr/datasets/ic13.py	46	CODE
LOW	doctr/datasets/ic03.py	50	CODE
LOW	doctr/datasets/funsd.py	44	CODE
LOW	doctr/datasets/sroie.py	51	CODE
LOW	doctr/datasets/svt.py	42	CODE
LOW	doctr/utils/metrics.py	731	CODE
LOW	doctr/utils/visualization.py	155	CODE
LOW	doctr/utils/visualization.py	308	CODE
LOW	doctr/utils/repr.py	32	CODE
LOW	doctr/utils/data.py	26	CODE
LOW	doctr/models/builder.py	340	CODE
LOW	doctr/models/builder.py	649	CODE
LOW	doctr/models/_utils.py	42	CODE
LOW	doctr/models/classification/vit_det/pytorch.py	231	CODE
LOW	doctr/models/layout/lw_detr/pytorch.py	273	CODE
LOW	doctr/models/layout/lw_detr/base.py	89	CODE
LOW	doctr/models/layout/lw_detr/base.py	216	CODE
LOW	doctr/models/reading_order/base.py	79	CODE
LOW	doctr/models/reading_order/base.py	169	CODE
LOW	doctr/models/table_structure/tablecenternet/base.py	295	CODE
LOW	doctr/models/table_structure/tablecenternet/base.py	112	CODE
LOW	doctr/models/recognition/sar/pytorch.py	113	CODE
LOW	doctr/models/recognition/parseq/pytorch.py	125	CODE
LOW	doctr/models/recognition/parseq/pytorch.py	323	CODE
LOW	doctr/models/detection/_utils/base.py	12	CODE
LOW	…r/models/detection/differentiable_binarization/base.py	270	CODE
LOW	doctr/models/detection/linknet/base.py	159	CODE
LOW	doctr/models/detection/fast/base.py	156	CODE
LOW	doctr/models/factory/hub.py	190	CODE
LOW	doctr/contrib/artefacts.py	68	CODE
LOW	doctr/transforms/modules/pytorch.py	97	CODE
LOW	scripts/evaluate_kie.py	23	CODE
LOW	scripts/collect_env.py	167	CODE
LOW	scripts/evaluate.py	23	CODE
LOW	api/tests/routes/test_ocr.py	5	CODE

Self-Referential Comments12 hits · 28 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/pytorch/test_models_zoo_pt.py	26	# Create a dummy callback	COMMENT
MEDIUM	doctr/io/elements.py	553	# Create the XML root element	COMMENT
MEDIUM	doctr/io/elements.py	555	# Create the header / SubElements of the root element	COMMENT
MEDIUM	doctr/io/elements.py	569	# Create the body	COMMENT
MEDIUM	doctr/io/elements.py	741	# Create the XML root element	COMMENT
MEDIUM	doctr/io/elements.py	743	# Create the header / SubElements of the root element	COMMENT
MEDIUM	doctr/io/elements.py	757	# Create the body	COMMENT
MEDIUM	doctr/models/builder.py	136	# Define a mean y-center for the line	COMMENT
MEDIUM	doctr/models/layout/lw_detr/layers/pytorch.py	116	"""This module implements the self-attention mechanism used in LW-DETR.	STRING
MEDIUM	doctr/models/layout/lw_detr/layers/pytorch.py	196	"""This module implements MultiScaleDeformableAttention from Deformable DETR.	STRING
MEDIUM	doctr/models/layout/lw_detr/layers/pytorch.py	357	"""This module implements a single decoder layer of LW-DETR,	STRING
MEDIUM	doctr/models/layout/lw_detr/layers/pytorch.py	484	"""This module implements the decoder of LW-DETR,	STRING

AI Structural Patterns20 hits · 20 pts

Severity	File	Line	Context
LOW	doctr/models/zoo.py	18	CODE
LOW	doctr/models/zoo.py	100	CODE
LOW	doctr/models/zoo.py	184	CODE
LOW	doctr/models/zoo.py	250	CODE
LOW	doctr/models/classification/starnet/pytorch.py	95	CODE
LOW	doctr/models/classification/vit_det/pytorch.py	164	CODE
LOW	doctr/models/kie_predictor/pytorch.py	195	CODE
LOW	doctr/models/layout/lw_detr/pytorch.py	273	CODE
LOW	doctr/models/layout/lw_detr/layers/pytorch.py	371	CODE
LOW	doctr/models/layout/lw_detr/layers/pytorch.py	499	CODE
LOW	doctr/models/table_structure/tablecenternet/pytorch.py	157	CODE
LOW	doctr/models/recognition/master/pytorch.py	54	CODE
LOW	doctr/models/recognition/sar/pytorch.py	180	CODE
LOW	doctr/models/recognition/parseq/pytorch.py	125	CODE
LOW	doctr/models/predictor/pytorch.py	48	CODE
LOW	doctr/models/predictor/pytorch.py	194	CODE
LOW	…odels/detection/differentiable_binarization/pytorch.py	111	CODE
LOW	doctr/models/detection/linknet/pytorch.py	85	CODE
LOW	doctr/models/detection/fast/pytorch.py	117	CODE
LOW	doctr/transforms/functional/pytorch.py	41	CODE

Decorative Section Separators2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/pytorch/test_transforms_pt.py	666	# ----------------------------------------------------------------------------	COMMENT
MEDIUM	tests/pytorch/test_transforms_pt.py	668	# ----------------------------------------------------------------------------	COMMENT

Slop Phrases4 hits · 6 pts

Severity	File	Line	Snippet	Context
LOW	doctr/models/recognition/vitstr/pytorch.py	153	# Compute loss: don't forget to shift gt! Otherwise the model learns to output the gt[t-1]!	COMMENT
LOW	doctr/models/recognition/vitstr/pytorch.py	153	# Compute loss: don't forget to shift gt! Otherwise the model learns to output the gt[t-1]!	COMMENT
LOW	doctr/models/recognition/master/pytorch.py	144	# Compute loss: don't forget to shift gt! Otherwise the model learns to output the gt[t-1]!	COMMENT
LOW	doctr/models/recognition/master/pytorch.py	144	# Compute loss: don't forget to shift gt! Otherwise the model learns to output the gt[t-1]!	COMMENT

Cross-Language Confusion1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	docs/source/conf.py	133	function gtag(){{dataLayer.push(arguments);}}	CODE

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	doctr/utils/multithreading.py	19	Execute a given function in parallel for each element of a given sequence >>> from doctr.utils.multithreading impor	STRING

Excessive Try-Catch Wrapping4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	doctr/utils/reconstitution.py	107	except Exception: # pragma: no cover	CODE
LOW	doctr/models/table_structure/tablecenternet/base.py	270	except Exception:	CODE
LOW	doctr/cli/main.py	48	except Exception as e:	CODE
LOW	doctr/cli/main.py	64	except Exception as e:	CODE

Over-Commented Block3 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	321	# third = np.array([[51], [46], [112], [110], [103]], dtype=np.int16) # 3.png	COMMENT
LOW	tests/pytorch/test_models_layout.py	181		COMMENT
LOW	docs/source/conf.py	1	# Copyright (C) 2021-2026, Mindee.	COMMENT

Redundant / Tautological Comments1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	doctr/utils/geometry.py	561	# Add the crop to the list of crops	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	doctr/models/factory/hub.py	124	### Example usage:	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings