Future-House/paper-qa

5.1

Adjusted Score

5.1

Raw Score

100%

Time Factor

2026-06-29

Last Push

8.9K

Stars

Python

Language

79.5K

Lines of Code

146

Files

368

Pattern Hits

2026-07-14

Scan Date

0.05

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 7MEDIUM 11LOW 350

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 368 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.

Hyper-Verbose Identifiers175 hits · 164 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_configs.py	27	def test_prompt_settings_validation() -> None:	CODE
LOW	tests/test_configs.py	40	def test_get_formatted_variables() -> None:	CODE
LOW	tests/test_configs.py	53	def test_get_settings_with_valid_config(value: MaybeSettings) -> None:	CODE
LOW	tests/test_configs.py	58	def test_get_settings_missing_file() -> None:	CODE
LOW	tests/test_configs.py	69	def test_settings_default_instantiation(tmpdir, subtests: SubTests) -> None:	CODE
LOW	tests/test_configs.py	106	def test_router_kwargs_present_in_models() -> None:	CODE
LOW⚡	tests/test_configs.py	204	def test_matches_filter_criteria(doc_class, doc_data, filter_criteria, expected_result):	CODE
LOW⚡	tests/test_configs.py	209	def test_citation_prompt_current_year():	CODE
LOW⚡	tests/test_configs.py	218	def test_validity_of_bundled_configs(subtests: SubTests) -> None:	CODE
LOW	tests/test_configs.py	230	def test_readme_settings_cheatsheet_accuracy(subtests: SubTests) -> None:	CODE
LOW	tests/test_utils.py	4	def test_citation_to_docname_acronym_title() -> None:	CODE
LOW	tests/test_utils.py	9	def test_citation_to_docname_non_text_fallback_is_deterministic() -> None:	CODE
LOW	tests/conftest.py	56	def _defeat_litellm_callbacks() -> None:	CODE
LOW	tests/conftest.py	61	def _patch_litellm_logging_worker_for_race_condition() -> Iterator[None]:	CODE
LOW	tests/conftest.py	92	def ensure_initialized_and_enqueue(self, async_coroutine: Coroutine) -> None:	CODE
LOW	tests/conftest.py	184	def stub_data_dir_w_near_dupes(stub_data_dir: Path, tmp_path: Path) -> Iterator[Path]:	CODE
LOW	tests/conftest.py	219	async def _vcr_handle_async_request(	CODE
LOW	tests/conftest.py	245	def _build_response_with_raw_headers(vcr_request, vcr_response, history):	CODE
LOW⚡	tests/test_paperqa.py	146	def test_citations_with_pages() -> None:	CODE
LOW⚡	tests/test_paperqa.py	151	def test_citations_without_space() -> None:	CODE
LOW⚡	tests/test_paperqa.py	156	def test_citations_with_commas() -> None:	CODE
LOW⚡	tests/test_paperqa.py	3197	def test_basic_json_extraction(self, input_text: str) -> None:	CODE
LOW⚡	tests/test_paperqa.py	3260	def test_relevance_score_parsing(self, input_text: str) -> None:	CODE
LOW⚡	tests/test_paperqa.py	3338	def test_json_broken_formatting(self, input_text: str) -> None:	CODE
LOW⚡	tests/test_paperqa.py	3366	def test_llm_parse_json_with_escaped_characters(self, input_text, expected_output):	CODE
LOW	tests/test_paperqa.py	181	def test_citations_with_special_characters() -> None:	CODE
LOW	tests/test_paperqa.py	186	def test_citations_with_nonstandard_chars() -> None:	CODE
LOW	tests/test_paperqa.py	816	async def acompletion_that_breaks_first_context(args, *kwargs):	CODE
LOW	tests/test_paperqa.py	844	async def test_nonduplicate_contexts() -> None:	CODE
LOW	tests/test_paperqa.py	899	async def acompletion_that_breaks_first_context(args, *kwargs):	CODE
LOW	tests/test_paperqa.py	1018	async def test_custom_context_str_fn(docs_fixture) -> None:	CODE
LOW	tests/test_paperqa.py	1043	async def test_aquery_groups_contexts_by_question(docs_fixture) -> None:	CODE
LOW	tests/test_paperqa.py	1118	async def test_query_with_iteration(docs_fixture) -> None:	CODE
LOW	tests/test_paperqa.py	1253	async def test_docs_with_custom_embedding(	CODE
LOW	tests/test_paperqa.py	1386	async def test_custom_llm_custom_media(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	1565	async def test_pdf_reader_w_no_match_doc_details(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	1584	async def test_pdf_reader_w_no_chunks(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	1605	async def test_partly_embedded_texts(defer_embeddings: bool) -> None:	CODE
LOW	tests/test_paperqa.py	1651	async def test_pdf_reader_match_doc_details(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	1793	async def test_chunk_metadata_reader(	CODE
LOW	tests/test_paperqa.py	1916	def test_parsed_media_data_or_url() -> None:	CODE
LOW	tests/test_paperqa.py	1942	def test_parsed_media_url_only_hash_eq() -> None:	CODE
LOW	tests/test_paperqa.py	2000	async def test_read_doc_images_metadata(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	2052	async def test_read_doc_images_concurrency(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	2114	def test_should_parse_and_enrich_media(	CODE
LOW	tests/test_paperqa.py	2136	async def test_image_enrichment_normal_use(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	2266	async def test_image_enrichment_invalid_image(caplog) -> None:	CODE
LOW	tests/test_paperqa.py	2287	async def test_image_enrichment_with_oversized_image(caplog) -> None:	CODE
LOW	tests/test_paperqa.py	2425	async def test_duplicate_media_context_creation(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	2563	def test_missing_page_doesnt_crash_us() -> None:	CODE
LOW	tests/test_paperqa.py	2676	async def test_context_inner_outer_prompt(stub_data_dir: Path) -> None:	CODE
LOW	tests/test_paperqa.py	2717	def test_get_index_name_uniqueness(	CODE
LOW	tests/test_paperqa.py	2731	def test_case_insensitive_matching():	CODE
LOW	tests/test_paperqa.py	2752	def test_dois_resolve_to_correct_journals(doi_journals):	CODE
LOW	tests/test_paperqa.py	2765	def test_docdetails_merge_with_non_list_fields() -> None:	CODE
LOW	tests/test_paperqa.py	2799	def test_docdetails_merge_with_list_fields() -> None:	CODE
LOW	tests/test_paperqa.py	2833	def test_docdetails_deserialization(tmp_path) -> None:	CODE
LOW	tests/test_paperqa.py	2892	def test_docdetails_doc_id_roundtrip() -> None:	CODE
LOW	tests/test_paperqa.py	3048	async def test_partitioning_fn_docs(use_partition: bool) -> None:	CODE
LOW	tests/test_paperqa.py	3378	def test_llm_subquotes_and_newlines(self, input_text: str) -> None:	CODE
115 more matches not shown…

Unused Imports66 hits · 64 pts

Severity	File	Line	Context
LOW	tests/conftest.py	1	CODE
LOW	tests/test_paperqa.py	12	CODE
LOW	tests/test_clients.py	1	CODE
LOW	tests/test_clients.py	7	CODE
LOW	tests/test_clients.py	7	CODE
LOW	tests/test_clients.py	24	CODE
LOW	tests/test_clients.py	24	CODE
LOW	tests/test_agents.py	1	CODE
LOW	…kages/paper-qa-docling/src/paperqa_docling/__init__.py	3	CODE
LOW	packages/paper-qa-docling/src/paperqa_docling/reader.py	30	CODE
LOW	…kages/paper-qa-pymupdf/src/paperqa_pymupdf/__init__.py	1	CODE
LOW	…kages/paper-qa-pymupdf/src/paperqa_pymupdf/__init__.py	1	CODE
LOW	…kages/paper-qa-pymupdf/src/paperqa_pymupdf/__init__.py	1	CODE
LOW	packages/paper-qa-pypdf/src/paperqa_pypdf/__init__.py	1	CODE
LOW	packages/paper-qa-pypdf/src/paperqa_pypdf/reader.py	27	CODE
LOW	…ges/paper-qa-nemotron/src/paperqa_nemotron/__init__.py	3	CODE
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	59	CODE
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	60	CODE
LOW	src/paperqa/readers.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	1	CODE
LOW	src/paperqa/__init__.py	13	CODE
LOW	src/paperqa/__init__.py	14	CODE
LOW	src/paperqa/__init__.py	15	CODE
LOW	src/paperqa/__init__.py	15	CODE
LOW	src/paperqa/__init__.py	16	CODE
LOW	src/paperqa/__init__.py	16	CODE
LOW	src/paperqa/__init__.py	16	CODE
LOW	src/paperqa/__init__.py	21	CODE
LOW	src/paperqa/__init__.py	21	CODE
LOW	src/paperqa/__init__.py	22	CODE
LOW	src/paperqa/__init__.py	22	CODE
LOW	src/paperqa/__init__.py	22	CODE
LOW	src/paperqa/__init__.py	22	CODE
LOW	src/paperqa/__init__.py	23	CODE
LOW	src/paperqa/docs.py	1	CODE
LOW	src/paperqa/types.py	1	CODE
LOW	src/paperqa/_ldp_shims.py	33	CODE
LOW	src/paperqa/_ldp_shims.py	33	CODE
LOW	src/paperqa/settings.py	49	CODE
LOW	src/paperqa/llms.py	7	CODE
LOW	src/paperqa/clients/unpaywall.py	1	CODE
LOW	src/paperqa/clients/journal_quality.py	1	CODE
LOW	src/paperqa/clients/retractions.py	1	CODE
LOW	src/paperqa/clients/__init__.py	1	CODE
LOW	src/paperqa/clients/__init__.py	5	CODE
LOW	src/paperqa/clients/client_models.py	1	CODE
LOW	src/paperqa/clients/semantic_scholar.py	1	CODE
LOW	src/paperqa/clients/openalex.py	1	CODE
LOW	src/paperqa/clients/crossref.py	1	CODE
LOW	src/paperqa/agents/models.py	1	CODE
LOW	src/paperqa/agents/__init__.py	1	CODE
LOW	src/paperqa/agents/search.py	1	CODE
6 more matches not shown…

Fake / Example Data38 hits · 40 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_paperqa.py	3168	'{\n"summary": "Lorem Ipsum",\n"relevance_score": 8\n}'	CODE
LOW⚡	tests/test_paperqa.py	3174	'```json\n{\n"summary": "Lorem Ipsum",\n"relevance_score": 8\n}\n```'	CODE
LOW⚡	tests/test_paperqa.py	3180	'```json { "summary": "Lorem Ipsum", "relevance_ score": 8 } ```',	CODE
LOW⚡	tests/test_paperqa.py	3185	'{ "summary": "Lorem Ipsum", "relevance_score": 8 }'	CODE
LOW⚡	tests/test_paperqa.py	3191	'{\n "summary": "Lorem Ipsum",\n "relevance_score": "8" \n}'	CODE
LOW⚡	tests/test_paperqa.py	3198	output = {"summary": "Lorem Ipsum", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3206	' Ipsum\n\ndolor sit amet",\n"relevance_score": 8\n}\nHope this helps!',	CODE
LOW⚡	tests/test_paperqa.py	3212	output = {"summary": "Lorem Ipsum\n\ndolor sit amet", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3212	output = {"summary": "Lorem Ipsum\n\ndolor sit amet", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3221	'```json { "summary": "Lorem Ipsum", "relevance_score": 7.6 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3228	'```json { "summary": "Lorem Ipsum", "relevance_score": "8" } ```'	CODE
LOW⚡	tests/test_paperqa.py	3234	' "Lorem Ipsum", "relevance_score": "8/10" } ```Hope this helps!',	CODE
LOW⚡	tests/test_paperqa.py	3240	'```json { "summary": "Lorem Ipsum", "relevance_score": "4/5" } ```'	CODE
LOW⚡	tests/test_paperqa.py	3247	'```json { "summary": "Lorem Ipsum", "relevance_score": 8/10 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3254	'```json { "summary": "Lorem Ipsum", "relevance_score": 4/5 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3261	output = {"summary": "Lorem Ipsum", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3270	'```json { "summary": "Lorem Ipsum", "relevance-score": 8 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3277	'```json { "summary": "Lorem Ipsum", "relevance_ score": 8 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3284	'```json { "summary": "Lorem Ipsum", "score": 8 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3291	'```json { "summary": "Lorem Ipsum", "relevance score": 8 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3298	'```json { "summary": "Lorem Ipsum", "relevance": 8 } ```'	CODE
LOW⚡	tests/test_paperqa.py	3305	output = {"summary": "Lorem Ipsum", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3314	'{ "summary": "Lorem Ipsum", "relevance_score": 8, }'	CODE
LOW⚡	tests/test_paperqa.py	3321	'{ "summary": "Lorem Ipsum", , "relevance_score": 8 }'	CODE
LOW⚡	tests/test_paperqa.py	3328	'{ , "summary": "Lorem Ipsum", "relevance_score": 8 }'	CODE
LOW⚡	tests/test_paperqa.py	3333	'{ "summary": "Lorem Ipsum" "relevance_score": 8 }',	CODE
LOW⚡	tests/test_paperqa.py	3339	output = {"summary": "Lorem Ipsum", "relevance_score": 8}	CODE
LOW⚡	tests/test_paperqa.py	3346	"<think> Thinking </think>Lorem Ipsum. Hope this helps!",	CODE
LOW⚡	tests/test_paperqa.py	3350	"Lorem Ipsum. Hope this helps!",	CODE
LOW⚡	tests/test_paperqa.py	3356	output = {"summary": "Lorem Ipsum. Hope this helps!"}	CODE
LOW	tests/test_paperqa.py	3894	author_name="John Doe",	CODE
LOW	tests/test_paperqa.py	3902	author_name="John Doe",	CODE
LOW	tests/test_paperqa.py	3940	author_name="John Doe",	CODE
LOW	tests/test_paperqa.py	3957	author_name="John Doe", # Reversed order from context_with_extras	CODE
LOW	tests/test_clients.py	380	assert not await client.query(doi="placeholder")	CODE
LOW⚡	tests/test_clients.py	759	("Doe, John", "John Doe"),	CODE
LOW⚡	tests/test_clients.py	762	("Doe, Jane", "Jane Doe"),	CODE
LOW⚡	tests/test_clients.py	767	("Jane Doe", "Jane Doe"),	CODE

Modern Structural Boilerplate32 hits · 32 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	43	def _setup_default_logs() -> None:	CODE
LOW	…kages/paper-qa-docling/src/paperqa_docling/__init__.py	5	__all__ = ["parse_pdf_to_pages"]	CODE
LOW	…kages/paper-qa-pymupdf/src/paperqa_pymupdf/__init__.py	3	__all__ = [	CODE
LOW	packages/paper-qa-pypdf/src/paperqa_pypdf/__init__.py	3	__all__ = [	CODE
LOW	…ges/paper-qa-nemotron/src/paperqa_nemotron/__init__.py	5	__all__ = ["parse_pdf_to_pages"]	CODE
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	62	logger = logging.getLogger(__name__)	CODE
LOW	…kages/paper-qa-nemotron/src/paperqa_nemotron/reader.py	36	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/__init__.py	25	__all__ = [	CODE
LOW	src/paperqa/docs.py	42	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/core.py	16	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/types.py	56	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/_ldp_shims.py	3	__all__ = [	CODE
LOW	src/paperqa/utils.py	33	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/settings.py	86	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/llms.py	47	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/journal_quality.py	28	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/retractions.py	15	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/__init__.py	23	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/client_models.py	24	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/semantic_scholar.py	30	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/openalex.py	31	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/clients/crossref.py	38	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/env.py	42	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/models.py	18	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/tools.py	24	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/__init__.py	22	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/search.py	56	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/main.py	48	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/agents/helpers.py	17	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/contrib/openreview_paper_helper.py	21	logger = logging.getLogger(__name__)	CODE
LOW	src/paperqa/contrib/__init__.py	3	__all__ = ["ZoteroDB"]	CODE
LOW	src/paperqa/sources/clinical_trials.py	23	logger = logging.getLogger(__name__)	CODE

Cross-File Repetition4 hits · 20 pts

Severity	File	Snippet	Context
HIGH	packages/paper-qa-docling/tests/test_paperqa_docling.py	<html> <head><title>404 not found</title></head> <body> <center><h1>404 not found</h1></center> <hr><center>nginx</cente	STRING
HIGH	packages/paper-qa-pymupdf/tests/test_paperqa_pymupdf.py	<html> <head><title>404 not found</title></head> <body> <center><h1>404 not found</h1></center> <hr><center>nginx</cente	STRING
HIGH	packages/paper-qa-pypdf/tests/test_paperqa_pypdf.py	<html> <head><title>404 not found</title></head> <body> <center><h1>404 not found</h1></center> <hr><center>nginx</cente	STRING
HIGH	…kages/paper-qa-nemotron/tests/test_paperqa_nemotron.py	<html> <head><title>404 not found</title></head> <body> <center><h1>404 not found</h1></center> <hr><center>nginx</cente	STRING

Deep Nesting18 hits · 18 pts

Severity	File	Line	Context
LOW	tests/test_agents.py	68	CODE
LOW	packages/paper-qa-docling/src/paperqa_docling/reader.py	38	CODE
LOW	packages/paper-qa-pymupdf/src/paperqa_pymupdf/reader.py	127	CODE
LOW	packages/paper-qa-pypdf/src/paperqa_pypdf/reader.py	56	CODE
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	464	CODE
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	603	CODE
LOW	src/paperqa/readers.py	203	CODE
LOW	src/paperqa/readers.py	426	CODE
LOW	src/paperqa/core.py	178	CODE
LOW	src/paperqa/types.py	474	CODE
LOW	src/paperqa/types.py	983	CODE
LOW	src/paperqa/types.py	1267	CODE
LOW	src/paperqa/utils.py	314	CODE
LOW	src/paperqa/utils.py	589	CODE
LOW	src/paperqa/clients/crossref.py	167	CODE
LOW	src/paperqa/agents/env.py	47	CODE
LOW	src/paperqa/agents/search.py	186	CODE
LOW	src/paperqa/contrib/zotero.py	147	CODE

Modern AI Meta-Vocabulary6 hits · 16 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	36	- [Agentic Adding/Querying Documents](#agentic-addingquerying-documents)	CODE
MEDIUM	tests/test_paperqa.py	1590	settings.summary_llm = "gpt-4o-mini" # context window needs to fit our one chunk	CODE
MEDIUM	tests/test_agents.py	463	# https://docs.anthropic.com/en/docs/build-with-claude/tool-use#chain-of-thought	COMMENT
MEDIUM	docs/tutorials/where_do_I_get_papers.md	20	# 1Mil context window helps to suggest papers. These settings are not required, but useful for an initial setup.	COMMENT
MEDIUM	src/paperqa/llms.py	551	# Recursively create each component embedding model	COMMENT
MEDIUM	src/paperqa/sources/clinical_trials.py	294	# for embedding model context windows, we truncate at TRIAL_CHAR_TRUNCATION_SIZE	COMMENT

Docstring Block Structure3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH	packages/paper-qa-pymupdf/src/paperqa_pymupdf/reader.py	49	Load a PDF page and extract its text. Args: file: An open (assumed) PyMuPDF document. page_num: Zer	STRING
HIGH	src/paperqa/clients/openalex.py	74	Get paper details from OpenAlex given a DOI or paper title. Args: client: Async HTTP client for any request	STRING
HIGH	src/paperqa/agents/tools.py	474	Search for clinical trials, with support for repeated calls and concurrent execution. Will add new clinical tri	STRING

Excessive Try-Catch Wrapping11 hits · 13 pts

Severity	File	Line	Snippet	Context
LOW	src/paperqa/readers.py	77	except Exception as exc:	CODE
LOW	src/paperqa/types.py	1128	except Exception:	CODE
LOW	src/paperqa/utils.py	328	except Exception:	CODE
MEDIUM	src/paperqa/utils.py	227	def get_loop() -> asyncio.AbstractEventLoop:	CODE
LOW	src/paperqa/llms.py	297	except Exception as e:	CODE
LOW	src/paperqa/agents/search.py	252	except Exception:	CODE
LOW	src/paperqa/agents/search.py	477	except Exception:	CODE
LOW	src/paperqa/agents/search.py	531	except Exception as e:	CODE
MEDIUM	src/paperqa/agents/search.py	367	def save_index(self) -> None:	CODE
LOW	src/paperqa/agents/main.py	164	except Exception:	CODE
LOW	src/paperqa/sources/clinical_trials.py	275	except Exception as e:	CODE

Self-Referential Comments3 hits · 9 pts

Severity	File	Line	Snippet	Context
MEDIUM	src/paperqa/readers.py	228	# Create a ParsedMedia object	COMMENT
MEDIUM	src/paperqa/settings.py	1248	# Create a section with a question heading	COMMENT
MEDIUM	src/paperqa/llms.py	346	# Create a new event loop in a new thread to avoid nested loop issues	COMMENT

AI Structural Patterns5 hits · 5 pts

Severity	File	Line	Context
LOW	packages/paper-qa-pymupdf/src/paperqa_pymupdf/reader.py	127	CODE
LOW	…kages/paper-qa-nemotron/src/paperqa_nemotron/reader.py	136	CODE
LOW	src/paperqa/docs.py	93	CODE
LOW	src/paperqa/docs.py	156	CODE
LOW	src/paperqa/contrib/zotero.py	147	CODE

AI Slop Vocabulary2 hits · 3 pts

Severity	File	Line	Snippet	Context
LOW	packages/paper-qa-nemotron/src/paperqa_nemotron/api.py	635	# We just use aiobotocore directly here	COMMENT
LOW	src/paperqa/clients/__init__.py	253	# if we can't get metadata, just return the doc, but don't overwrite any fields	COMMENT

Redundant / Tautological Comments2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	pyproject.toml	324	# Set true to activate the evaluation score.	COMMENT
LOW	src/paperqa/utils.py	89	# Check if the entropy is within a reasonable range for text	STRING

Over-Commented Block2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	pyproject.toml	181	mypy_path = "$MYPY_CONFIG_FILE_DIR/src,$MYPY_CONFIG_FILE_DIR/packages/paper-qa-pypdf/src,$MYPY_CONFIG_FILE_DIR/packages/	COMMENT
LOW	src/paperqa/settings.py	1141	media.info["is_irrelevant"],	COMMENT

Verbosity Indicators1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_paperqa.py	1304	# For QdrantVectorStore, we need to check if collection exists and has points	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings