RESEARCH WORKSPACE
Create a literature database
Define what matters in your field. Turn papers into evidence you can explore.
The fundamentals are ready. Add your reaction.
AI is unavailable in this environment. You can use and edit the template below.
AI generation uses workspace API credits.Heterogeneous catalysis
Use this template directly, or ask AI to tailor evaluation. Missing evidence stays missing.
MODULE WORKSPACE
Your database
Saving & workspace limits
Saved definitions are frozen. To change them, start a new project. Up to 500 article × module tasks per project and 5 attempts per task. PDFs stay private; only reviewed results can be published.
2. Source PDFs
First validate and save your modules in Define structure. Then you can upload sources.
Up to 10 parallel uploads. PDFs are parsed one at a time to limit memory use. Keep this tab open until uploads finish.
Text-based PDFs only in this version. Figures are not read; scanned documents require OCR. Text is never silently truncated.
3. Extraction & review
Upload at least one main article before starting extraction.
Each article × module is checkpointed separately. Progress refreshes every 5 seconds; you can close the browser after submission.
Cloud extraction: up to 10 article × module tasks at once, shared across projects. Completed tasks are not rerun.
0 / 0 schema-validated modules · 0 tokens
Schema validation checks structure, not scientific correctness. Check source evidence before publishing. Missing SI is never inferred.