rebuttallisted

# /rebuttal > Parse review comments, atomize each concern (Rvx-Cy numbering) and map it to a wiki claim, > check whether evidence is sufficient (tracing back to wiki experiments), > simulate reviewer follow-up questions with Review LLM (stress-test, scored 1-5), and generate > a formal plain-text rebuttal and a rich-text rebuttal. > Safety checks ensure no fabrication, no overpromise, full coverage. ## Inputs - `review`: source of review comments, one of: - file path (e.g. `raw/reviews/reviewer1.txt`, `raw/reviews/meta-review.md`) - multiple file paths (comma-separated: `raw/reviews/R1.txt,raw/reviews/R2.txt,raw/reviews/R3.txt`) - directly pasted review text - `--paper-slug` (optional): slug of the associated paper in wiki/outputs/, used to locate PAPER_PLAN - `--venue` (optional): target conference/journal (ICLR / NeurIPS / ICML / ACL / CVPR); affects rebuttal format and word limits - `--stress-test` (optional, enabled by default): Review LLM simulates reviewer follow-up; disable with `--no-stress-test` - `--format` (optional, default `formal`): output format - `formal`: formal plain-text rebuttal (suitable for pasting directly into submission system) - `rich`: rich-text version (with wiki [[links]], detailed analysis, improvement plan) ## Outputs - **wiki/outputs/rebuttal-{slug}.md** — rich-text rebuttal (with [[wikilinks]], evidence tracing, analysis tables) - **wiki/outputs/rebuttal-{slug}.txt** — formal rebuttal (plain text, suitable for pasting into submi