Enables researching, verifying, comparing, and composing open-source AI projects with transparent evidence and uncertainty boundaries through read-only tools.
Enables users to parse clinical prediction model manuscripts and assess reporting completeness against a deterministic, element-level checklist, then produce validated, provenance-stamped reports and corpus summaries.
Enables users to verify citations and bibliographies and to check whether source documents support factual claims, using local inference, exact evidence provenance, and deterministic verdicts.
Enables users to extract text from scanned PDF pages and images using existing text layers or Tesseract OCR, returning lines and words with bounding boxes and confidence scores. It also supports searching pages, reading specific regions, and caching results so extracted numbers can be checked against the page.
Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.
Enables relation-guided assessment and reassessment of scientific claims using a five-level rubric and audits of twelve evidence relations across initial, audit, and verification rounds. Computes diagnostics such as graph zigzag H1 persistence to select a relation for focused repair, and supports batch runs, record verification, and evaluation against gold labels.