Search the INSPIRE-HEP literature database for high-energy physics papers.

Supports the full INSPIRE query syntax, e.g. 'title top squark and collaboration CMS', 'a Witten and tc p', 'arxiv 2301.08096'. Returns titles, authors, arXiv ids, journal references, citation counts, abstracts, and INSPIRE record ids (needed for HEPData).

Fetch the official BibTeX entry for a paper from INSPIRE-HEP.

Accepts an INSPIRE record id (e.g. 1748602) or arXiv id (e.g. 2301.08096). Always use this for bibliography entries — never write BibTeX by hand.

Fetch an arXiv paper.

section='abstract' returns title, authors, and abstract; section='fulltext' returns the plain-text body from arXiv's HTML rendering (availability varies by paper).

Fetch a HEPData record by INSPIRE record id (e.g. 1748602).

Lists its data tables and additional resources, flagging ones that look like published statistical models (pyhf likelihoods).

Download and extract a published pyhf likelihood archive from HEPData.

Pass the resource URL found via hepdata_get and a local output directory.

List the signal patches (model points) in a downloaded published-likelihood directory containing a patchset.json.

Compute observed and expected CLs for a pyhf workspace at a given signal strength.

Pass the directory containing the background-only workspace (and patchset.json), and optionally a patch_name selecting the signal point. CLs < 0.05 means excluded at 95% CL. Runs a real maximum-likelihood fit; large workspaces can take minutes.

Generate LaTeX \newcommand macros from a results.json file.

Enforces the analysis-bundle rule that notes never hand-type physics numbers: every value in results_json becomes a macro (m_z_peak -> \MZPeak) written to out_tex, which the note includes via \input.

Copy the HEP analysis-note LaTeX template (note.tex skeleton + hepnote.sty with \pt/\GeV/\stat-style macros) into dest_dir. Structure mirrors experiment publications: Introduction, Detector and data, Event selection, Method, Systematic uncertainties, Results, Summary.

Validate an analysis bundle: layout, reproducibility (rerun analysis.py in a clean copy and require identical results.json), macros in sync, no hand-typed result values in the note, citations resolve, and the note compiles.