scitex-scholar 1.3.0

Scientific paper search, enrichment, download, and management for the SciTeX ecosystem

SciTeX Scholar (scitex-scholar)

Scientific paper search, enrichment, PDF download, and library management for reproducible research.

Full Documentation · pip install scitex-scholar

---

Problem and Solution

#	Problem	Solution
1	Literature search is balkanized -- CrossRef / OpenAlex / Semantic Scholar / arXiv / PubMed each have different APIs, rate limits, auth	Unified search -- scitex scholar search "topic" federates across all, deduplicates by DOI, returns ranked results
2	BibTeX from the wild is missing abstracts / DOIs / impact factors -- manuscript prep wastes hours	scitex scholar bibtex enrichment -- one call resolves DOIs, fetches abstracts, adds impact factors, normalizes formatting
3	Paywalled PDFs require institutional login per journal -- manual login-download-rename is the bottleneck	Browser-automation + OAuth -- persistent Chrome profile with stealth; scitex scholar fetch 10.1038/... grabs the PDF end-to-end

Problem

Literature management spans many tools and APIs: searching databases, resolving DOIs, downloading PDFs through institutional access, enriching BibTeX metadata, and keeping a reproducible, deduplicated library. Each step speaks a different library, auth flow, and data format.

Solution

scitex-scholar provides a unified workflow:

• Search across CrossRef, Semantic Scholar, PubMed, arXiv, and OpenAlex
• Resolve DOIs from titles; enrich BibTeX with abstracts, citation counts, impact factors (JCR 2024), PMIDs, and arXiv IDs
• Download PDFs through institutional access (OpenAthens / SSO) with Playwright browser automation
• Organize papers in a MASTER-hash library with per-project symlinks at ~/.scitex/scholar/library/
• Highlight each sentence of a PDF by rhetorical role — claim, method, limitation, supportive citation, contradicting citation — via Claude
• Automate the same operations from the CLI, a Python API, or the SciTeX MCP server

Installation

pip install scitex-scholar                 # core
pip install "scitex-scholar[pdf]"          # PDF text extraction
pip install "scitex-scholar[mcp]"          # MCP server deps (fastmcp)
pip install "scitex-scholar[browser]"      # Playwright automation
pip install "scitex-scholar[all]"          # everything

4 Interfaces

Python API

from scitex_scholar import Scholar, Paper, Papers, apply_filters, to_bibtex

scholar = Scholar()
papers = scholar.search("deep learning EEG", year_min=2020)   # auto-enriched
papers.save("results.bib")

# Filter + export
top = apply_filters(papers, min_citations=50, min_impact_factor=5.0)
print(to_bibtex(top))

CLI

Entry point: scitex-scholar <subcommand> (Click-based).

# Discover everything
scitex-scholar --help
scitex-scholar --help-recursive          # full overview, every leaf
scitex-scholar --version                  # or -V

# Paper(s)
scitex-scholar paper fetch --doi 10.1038/nature12373 --project demo
scitex-scholar paper fetch-batch --dois 10.1038/xxx --dois 10.1126/yyy --project demo --num-workers 4

# BibTeX file
scitex-scholar bibtex import --bibtex refs.bib --project demo --output refs.enriched.bib

# PDF post-processing
scitex-scholar pdf highlight paper.pdf

# Library
scitex-scholar library link-project-tree .
scitex-scholar library db build --dry-run
scitex-scholar library db audit --json

# MCP server
scitex-scholar mcp start
scitex-scholar mcp list-tools --json

# Skills + Python API introspection
scitex-scholar skills list
scitex-scholar list-python-apis -v

Mutating verbs accept --dry-run and -y/--yes. Read verbs support --json. Common paper/bibtex flags: --browser-mode {stealth,interactive}, --chrome-profile NAME, --force.

Migration (1.3.0): the CLI moved to noun-verb groups. Old top-level commands (single, parallel, top-level bibtex --bibtex, highlight, link-project-tree, materialize, dematerialize, db) still work but emit a DeprecationWarning and will be removed in 1.4.0. See CHANGELOG.md for the full migration table.

MCP Server

The package ships MCP tool handlers consumed by the unified scitex serve server (tools prefixed scholar_*). A standalone server at scitex_scholar.mcp_server is still shipped but deprecated. See the Skills documentation for the full tool list.

Skills

Agent skill pages are published at scitex-scholar.readthedocs.io/en/latest/skills.html. The semantic-highlight skill documents the PDF-highlighting workflow.

Core API

Symbol	Purpose
Scholar	Main search / enrich / download / save interface
Paper, Papers	Single paper / collection with export methods
ScholarConfig	Paths, API keys, auto-enrich toggle, browser settings
apply_filters	Filter a Papers collection
to_bibtex, to_ris, to_endnote, to_text_citation	Export formats
generate_cite_key, make_citation_key	Deterministic BibTeX keys
CitationGraphBuilder, plot_citation_graph	Optional citation graph
pdf_highlight.highlight_pdf	Overlay semantic highlights on a PDF

Sources: core/, search_engines/, metadata_engines/, pdf_download/, pipelines/, browser/, auth/, storage/, pdf_highlight/, _mcp/.

Semantic PDF Highlighting

Overlay colour-coded highlights on a PDF that separate what the paper claims from its methods, self-admitted limitations, and stance toward related work. Highlights are standard PDF annotation objects placed on a copy of the source — the original bytes are unchanged and any viewer can show or strip them.

colour	category	meaning
green	focal_claim	what the paper clarifies, suggests, demonstrates
purple	focal_method	novel method, model, cohort, or analysis
red	focal_limitation	self-admitted caveat or threat to validity
blue	related_supportive	prior work whose finding supports the paper
orange	related_contradictive	prior work whose finding contradicts the paper

A compact colour legend + signature (model name, timestamp) is stamped in the lower-right corner of the last page. See docs for full details.

export ANTHROPIC_API_KEY=sk-ant-...
scitex-scholar pdf highlight paper.pdf        # sentence-level, Haiku, writes paper.highlighted.pdf
scitex-scholar pdf highlight paper.pdf --stub # offline keyword heuristic (no API calls)

from scitex_scholar.pdf_highlight import highlight_pdf
result = highlight_pdf("paper.pdf", output_path="paper.highlighted.pdf")
print(result.counts(), result.annotations_added)

Also exposed as the scholar_highlight_pdf MCP tool (unified scitex serve server) and as the semantic-highlight agent skill (see skills documentation).

Storage layout

~/.scitex/scholar/library/
├── MASTER/<HASH>/               # Canonical per-paper storage (metadata.json + PDF)
└── <project>/<human-label> -> ../MASTER/<HASH>

Cache and auth state live under ~/.scitex/scholar/cache/ (URL resolver, Chrome profiles, OpenAthens cookies). Override with SCITEX_DIR.

License

AGPL-3.0-only.

Part of SciTeX

scitex-scholar is part of SciTeX. Install via the umbrella with pip install scitex[scholar] to use as scitex.scholar (Python) or scitex scholar ... (CLI).

Four Freedoms for Research

0. The freedom to run your research anywhere — your machine, your terms.
1. The freedom to study how every step works — from raw data to final manuscript.
2. The freedom to redistribute your workflows, not just your papers.
3. The freedom to modify any module and share improvements with the community.

AGPL-3.0 — because we believe research infrastructure deserves the same freedoms as the software it runs on.

---