Paper Survey

Survey mode (method reproduction)

If equations or algorithms are marked [extraction uncertain], or math needs re-extract, read /paper-extract (arXiv source first).

Templates: _templates/algorithm.md, _templates/repro-readme.md.

Replace every {{...}} in copied templates. Do not copy unused placeholder text into real notes.

Artifacts

• survey/algorithm.md — math / pseudocode faithful to the paper
• survey/repro/ — reproduction workspace (any language)

algorithm.md

• Extract math and pseudocode without altering meaning
• If extracted/ marks [extraction uncertain] on equations or algorithms, cross-check against the math reference priority before cleaning — arXiv source _raw/arxiv/ (preferred), then _raw/mathpix/, then the PDF original. On fetch failure, follow /paper-extract fallback and never substitute an arbitrary source (do not promote broken extract to source of truth)
• Include a symbol table (symbol / meaning / citation anchor)
• Attach a citation to each block whose ID already exists in extracted/ (_raw used for checking is not a citation target)
• Implementation assumptions not in the paper: say "Not stated in the attached source" and keep them out of algorithm.md (put them in repro notes)
• Do not put web supplements or illustrative examples in algorithm.md

repro/

• Language and build are free per paper; a README stub is required (_templates/repro-readme.md)
• README must map algorithm.md sections ↔ modules/functions
• Tests and validation data must mirror paper settings / boundary conditions (no junk placeholders)

Done when

• survey/algorithm.md and survey/repro/README.md exist
• Every #^ citation in algorithm.md resolves to a block ID that exists in the target file
• No {{...}} or other template wording remains
• Frontmatter mode matches the paper; status is surveying (or ready if the user asked to close the survey pass)
• _index/MOC.md status matches index.md if it was updated