pathwaycom/llm-app

29.8

Adjusted Score

29.8

Raw Score

100%

Time Factor

2026-07-05

Last Push

59.0K

Stars

Jupyter Notebook

Language

6.0K

Lines of Code

Files

Pattern Hits

2026-07-14

Scan Date

0.00

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 0MEDIUM 43LOW 36

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 79 distinct pattern matches across 7 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.

Modern AI Meta-Vocabulary43 hits · 144 pts

Severity	File	Line	Snippet	Context
MEDIUM	templates/slides_ai_search/app.yaml	1	# This YAML configuration file is used to set up and configure the Slides Search RAG template.	COMMENT
MEDIUM	templates/slides_ai_search/app.yaml	8	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM	templates/slides_ai_search/README.md	219	#### With the Pathway Live Data Framework RAG Client	COMMENT
MEDIUM	templates/document_store_mcp_server/app.yaml	1	# This YAML configuration file is used to set up and configure the Document indexing RAG template.	COMMENT
MEDIUM	templates/document_store_mcp_server/app.yaml	7	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM	templates/document_store_mcp_server/app.yaml	65	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM⚡	templates/video_rag_twelvelabs/app.yaml	1	# This YAML configuration file sets up the TwelveLabs video RAG template.	COMMENT
MEDIUM⚡	templates/video_rag_twelvelabs/app.yaml	3	# embedding that text with the TwelveLabs Marengo model, and serving a RAG	COMMENT
MEDIUM⚡	templates/video_rag_twelvelabs/app.yaml	9	# $sources defines the data sources read and indexed in the RAG.	COMMENT
MEDIUM	templates/video_rag_twelvelabs/app.yaml	79	# The RAG question-answering component served over HTTP.	COMMENT
MEDIUM	templates/video_rag_twelvelabs/README.md	12	# Video RAG with Pathway Live Data Framework and TwelveLabs	COMMENT
MEDIUM	templates/document_indexing/app.yaml	1	# This YAML configuration file is used to set up and configure the Document indexing RAG template.	COMMENT
MEDIUM	templates/document_indexing/app.yaml	7	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM	templates/document_indexing/app.yaml	65	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM	templates/private_rag/app.yaml	1	# This YAML configuration file is used to set up and configure the Private RAG template.	COMMENT
MEDIUM	templates/private_rag/app.yaml	8	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM	templates/private_rag/app.yaml	87	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM	templates/private_rag/app.yaml	94	# Configures the question-answering component using the RAG approach.	COMMENT
MEDIUM	templates/private_rag/README.md	12	# Fully private RAG with Pathway Live Data Framework	COMMENT
MEDIUM	templates/multimodal_rag/app.yaml	1	# This YAML configuration file is used to set up and configure the Multimodal RAG template.	COMMENT
MEDIUM	templates/multimodal_rag/app.yaml	8	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM	templates/multimodal_rag/app.yaml	91	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM	templates/multimodal_rag/app.yaml	98	# Configures the question-answering component using the RAG approach.	COMMENT
MEDIUM	templates/multimodal_rag/README.md	12	# Multimodal RAG with Pathway Live Data Framework: Process your Financial Reports and Tables with GPT-4o	COMMENT
MEDIUM	templates/drive_alert/README.md	1	# Pathway Live Data Framework + LLM + Slack notification: RAG App with real-time alerting when answers change in documen	COMMENT
MEDIUM	templates/adaptive_rag/app.yaml	1	# This YAML configuration file is used to set up and configure the Adaptive RAG template.	COMMENT
MEDIUM	templates/adaptive_rag/app.yaml	8	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM⚡	templates/adaptive_rag/app.yaml	79	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM⚡	templates/adaptive_rag/app.yaml	86	# Configures the question-answering component using the RAG approach.	COMMENT
MEDIUM⚡	templates/adaptive_rag/app.yaml	87	# The component builds a RAG over an index.	COMMENT
MEDIUM⚡	templates/adaptive_rag/app.yaml	88	# You can interact with obtained RAG using a REST API.	COMMENT
MEDIUM	templates/adaptive_rag/README.md	13	# End to end Adaptive RAG with Pathway Live Data Framework	COMMENT
MEDIUM	templates/question_answering_rag/app.yaml	1	# This YAML configuration file is used to set up and configure the Question Answering RAG template.	COMMENT
MEDIUM	templates/question_answering_rag/app.yaml	8	# $sources defines the data sources used to read the data which will be indexed in the RAG.	COMMENT
MEDIUM⚡	templates/question_answering_rag/app.yaml	80	# Manages the storage and retrieval of documents for the RAG template.	COMMENT
MEDIUM⚡	templates/question_answering_rag/app.yaml	87	# Configures the question-answering component using the RAG approach.	COMMENT
MEDIUM⚡	templates/question_answering_rag/app.yaml	88	# The component builds a RAG over an index.	COMMENT
MEDIUM⚡	templates/question_answering_rag/app.yaml	89	# You can interact with obtained RAG using a REST API.	COMMENT
MEDIUM	templates/question_answering_rag/README.md	12	# Pathway Live Data Framework RAG app with always up-to-date knowledge	COMMENT
MEDIUM	templates/question_answering_rag/README.md	41	This example spawns a lightweight webserver using Pathway’s [`QASummaryRestServer`](https://pathway.com/developers/api-d	CODE
MEDIUM	templates/question_answering_rag/README.md	48	### LLM and RAG capabilities	COMMENT
MEDIUM	templates/question_answering_rag/README.md	94	### RAG	COMMENT
MEDIUM	templates/question_answering_rag/README.md	329	#### Asking questions to LLM (With and without RAG)	COMMENT

Over-Commented Block22 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	templates/slides_ai_search/app.yaml	21	# url: $SHAREPOINT_URL	COMMENT
LOW	templates/slides_ai_search/app.yaml	101	description: "Language of the slide. For example 'fr', 'en'"	COMMENT
LOW	templates/slides_ai_search/app.yaml	121	# Defaults to false, uncomment the following line if you want to set it to true	COMMENT
LOW	templates/document_store_mcp_server/app.yaml	1	# This YAML configuration file is used to set up and configure the Document indexing RAG template.	COMMENT
LOW	templates/document_store_mcp_server/app.yaml	21	# tenant: $SHAREPOINT_TENANT	COMMENT
LOW	templates/document_store_mcp_server/app.yaml	81	# By default, caching is enabled for UDFs with cache_strategy set.	COMMENT
LOW	templates/video_rag_twelvelabs/app.yaml	1	# This YAML configuration file sets up the TwelveLabs video RAG template.	COMMENT
LOW	templates/video_rag_twelvelabs/app.yaml	21	# - !pw.io.gdrive.read	COMMENT
LOW	templates/video_rag_twelvelabs/app.yaml	81	llm: $llm	COMMENT
LOW	templates/document_indexing/app.yaml	1	# This YAML configuration file is used to set up and configure the Document indexing RAG template.	COMMENT
LOW	templates/document_indexing/app.yaml	21	# tenant: $SHAREPOINT_TENANT	COMMENT
LOW	templates/document_indexing/app.yaml	81	# By default, when enabled, Cache is stored in .Cache directory.	COMMENT
LOW	templates/private_rag/app.yaml	21	# url: $SHAREPOINT_URL	COMMENT
LOW	templates/private_rag/app.yaml	101	strict_prompt: true	COMMENT
LOW	templates/multimodal_rag/app.yaml	21	# url: $SHAREPOINT_URL	COMMENT
LOW	templates/multimodal_rag/app.yaml	101	indexer: $document_store	COMMENT
LOW	templates/multimodal_rag/app.yaml	121	# path: ".Cache"	COMMENT
LOW	templates/adaptive_rag/app.yaml	21	# url: $SHAREPOINT_URL	COMMENT
LOW	templates/adaptive_rag/app.yaml	101		COMMENT
LOW	templates/question_answering_rag/app.yaml	21	# url: $SHAREPOINT_URL	COMMENT
LOW	templates/question_answering_rag/app.yaml	81	$document_store: !pw.xpacks.llm.document_store.DocumentStore	COMMENT
LOW	templates/question_answering_rag/app.yaml	101		COMMENT

Hyper-Verbose Identifiers4 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	templates/slides_ai_search/ui/ui.py	91	def parse_slide_id_components(slide_id: str) -> tuple[str, int, int]:	CODE
LOW	templates/drive_alert/app.py	73	def build_prompt_check_for_alert_request_and_extract_query(query: str) -> str:	CODE
LOW	templates/drive_alert/app.py	94	def build_prompt_compare_answers(new: str, old: str) -> str:	STRING
LOW	templates/drive_alert/app.py	111	def construct_notification_message(query: str, response: str) -> str:	STRING

Excessive Try-Catch Wrapping3 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	…/slides_ai_search/pathway_slides_ai_search/__init__.py	104	except Exception as e:	CODE
LOW	…/slides_ai_search/pathway_slides_ai_search/__init__.py	117	except Exception as e:	CODE
LOW	templates/unstructured_to_sql_on_the_fly/ui/server.py	75	except Exception as e:	CODE

AI Structural Patterns3 hits · 3 pts

Severity	File	Line	Context
LOW	templates/unstructured_to_sql_on_the_fly/app.py	208	CODE
LOW	templates/unstructured_to_sql_on_the_fly/app.py	273	CODE
LOW	templates/drive_alert/app.py	128	CODE

Modern Structural Boilerplate2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	templates/unstructured_to_sql_on_the_fly/__init__.py	3	__all__ = ["run"]	CODE
LOW	templates/drive_alert/__init__.py	3	__all__ = ["run"]	CODE

Unused Imports2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	templates/unstructured_to_sql_on_the_fly/__init__.py	1		CODE
LOW	templates/drive_alert/__init__.py	1		CODE

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings