Return PaperGraph version and reproducible launch diagnostics.

Normalize arXiv ID and URL inputs and return the safe next action.

Validate a raw user arXiv request and return the safe next action.

Open or initialize a persistent multi-paper workspace.

Add or replace a local LaTeX project in the active workspace.

Add or replace an arXiv LaTeX project in the active workspace.

Add or replace a born-digital PDF paper in the active workspace.

Find exact DOI metadata and public body candidates; never download links.

Import a selected root DOI PDF only after explicit review/confirmation.

This is not permission to download newly discovered external references. Candidate provider identity is evidence, not a verification of PDF contents.

Load a user-requested root DOI when one public PDF candidate is eligible.

Multiple candidates require user selection. Do not use for newly discovered external references: those require an import plan and review first.

List all papers stored in the active workspace.

Return metadata and counts for one stored paper.

Search theorem titles and bodies across the active workspace.

Return dependencies of a globally identified stored theorem.

Explain how workspace dependencies were extracted for one theorem.

Return incoming or outgoing citation evidence for a stored paper.

List a stable result page (limit 1..100). Advance offset by returned count.

A full page may be truncated; continue until a page has fewer than limit results. This is not an unbounded complete list.

Return one stored evidence result with source spans.

Return proof evidence for one stored evidence result.

Return proof dependency evidence for one stored evidence result.

Return external result mentions from a result's proof evidence.

Return metadata and source spans for one evidence node or edge.

Export a paper-level evidence bundle for paper-reading consumers.

Export focused evidence context for reading one result's proof.

Return bounded source text around one span, result, or proof.

Read raw source blocks from a slice locator; follow next until null.

Blocks are source text, with no inferred proof ownership. Works for legacy imports without changing reading data. A changed extraction needs new locators.

Return deterministic local reading paths for one result.

List main-result candidates or read a user-selected target with evidence.

Statement references and proof-local dependencies remain separate. External references produce reviewable plans only; empty evidence is not independence.

Create a persistent reading session in the active workspace.

List persistent reading sessions in the active workspace.

Return one persistent reading session with checkpoints and notes.

Create or update a reading checkpoint in the active workspace.

Add a note or question to a reading session.

Export a deterministic recovery summary for a reading session.

Create a persistent reading queue for one stored result.

List persistent reading queues in the active workspace.

Return one persistent reading queue with ordered items.

Apply reading queue items as checkpoints in a reading session.

Plan external arXiv imports for one result's reading path.

Plan external arXiv imports referenced by one reading queue.

Plan external arXiv imports visible in one stored paper.

Resolve a blocked external reference to a user-confirmed target.

List recorded external reference resolutions and selection provenance.

Search scholarly metadata providers for a blocked external reference.

List scholarly reference search runs and candidates.

Apply a searched candidate as an explicit reference resolution.

Return an evidence-first first-load map for one stored paper.

Export a deterministic Markdown reading report for one stored paper.

Export a deterministic Markdown reading plan for selected papers.

Plan a Workspace Starter run without writing files.

Create starter artifacts for a first reading project.

Load a local LaTeX paper and build its theorem graph.

Download an arXiv source project and build its theorem graph.

Validate a raw arXiv request, then load it only if unambiguous.

List theorem-like environments in the currently loaded paper.

Return the full text and metadata for one theorem-like node.

Return theorem-like nodes referenced by the given theorem.

Explain how dependencies were extracted for one theorem-like node.

Return theorem-like nodes that reference the given theorem.

Save an approved finite expansion policy. Creation does not search or import.

Execute the saved policy: search, download arXiv sources, import unique strong candidates and record resolutions without per-paper prompts, within approved budgets. Resume with the same run ID.

Read saved graph, counts, decisions and continuation actions without network.

List saved expansion summaries, optionally filtered by state.

Record exactly one candidate_id, target, existing_paper_id, skip:true or retry:true. Advance separately to execute the approved choice.

Explicitly revise numeric budgets; cumulative usage is retained.

Pause scheduling after the active step. Advance explicitly to resume.

Permanently stop this run, preserving imported papers and history.

Return saved JSON or Markdown without writing client files or using network.