paper-plan

To generate a paper outline from ML research results, use a claims-to-structure planning approach that builds section-by-section plans from extracted claims, evidence, and known weaknesses. This scaffolds figures and citations before writing.

Plan paper figures and citations by generating a detailed Figure/Table plan, including a hero figure specification, alongside a citation plan to support each section. This scaffolding aligns evidence to claims before writing.

Yes, you can adapt your paper outline to fit ICLR, NeurIPS, or ICML page budgets through venue-aware layout and page budgeting. This adjusts structure and expected length to match common ML conference and journal norms.

Claims-evidence mapping in research planning aligns extracted experimental evidence to specific paper claims. It builds a structured paper plan while identifying known weaknesses, ensuring structural support before writing.

Prevent fabricating citations when scaffolding a paper outline by emitting a data-coverage GAP_REPORT. This gap-detection rule ensures all claims are backed by extracted project workspace evidence without prose copying.

To create a venue-aware ML paper plan, you need your project's narrative report and experiment evidence extracted from the workspace. Optionally, integrate a target venue and an opt-in style reference to shape the structure.