Alchemist Review – Dashboard Glossary

Dashboard Overview

• Manuscript List (Homepage)- Displays all manuscripts processed through Alchemist Review, sorted by upload date. Users can search by Manuscript ID or title, and filter by upload date. Journal fit score is shown for each manuscript on the Manuscript List. Role based access control/Permissions determine which journals are visible to the user.
• Triage (Tab)- The main manuscript workspace, organizing manuscript analysis into clear sections for faster triage and minimizing time spent navigating manuscript documents.
• Journal Fit Score – Helps editors quickly assess how well a manuscript aligns with their journal’s scope and standards—before assigning reviewers or investing time in deeper review.
• Flagged Items – To help with early triage, the number of critical severity (red), low severity (yellow) or neutral severity (grey) references are shown on the manuscript list.

Triage Sections

• Journal Fit- Evaluates Novelty, Relevance to Scope, Scientific Rigor, and Significance & Impact to calculate an overall Journal Fit Score.
• Submission Consistency- Compares information in the manuscript document with submission metadata, including document details and author information, and flags matches, mismatches, or missing values.
• Writing Quality- Evaluates Research Rationale, Terms & Units, IMRaD, Claims to Evidence Alignment, Language Integrity, and Readability, with examples supporting the assessment.
• Citation Analysis- Summarizes checks from the Citation Evaluation tab, including missing DOIs, invalid sources, and irrelevant references.

Figure & Table Analysis

Analyzes each extracted figure and table using the checks that apply to that asset. Results are grouped by figure or table and include a severity and explanation so editors can verify each finding against the manuscript.

• Missing Axes- Checks chart-type figures for missing x-axis or y-axis labels.
• Missing Units- Checks charts and tables for omitted units when quantitative values require them.
• Legibility- Checks whether embedded text, labels, legends, annotations, and data are readable.
• Missing References- Flags in-text figure or table citations that do not resolve to an existing asset.
• Unreferenced Figures and Tables- Flags figures and tables that appear in the manuscript but are never cited in the body text.
• Statistical Checks- Applies GRIM, SPRITE, and Benford’s Law checks to applicable numeric table data to surface mathematical inconsistencies or unusual digit distributions that warrant editorial review.

Citation Evaluation

• Citation Analysis (Triage Summary)- Summarizes checks from the Citation Evaluation tab—flags missing DOIs, invalid sources, or irrelevant references.
• Citation Evaluation Tab- Detailed reference-level assessment including:
  • DOI Validity – Confirms correct DOI formatting and matching.
  • Source Validity – Verifies citations link to legitimate publications.
  • Retraction Flags – Highlights retracted papers or authors with prior retractions.
  • Severity Filters – Classifies issues as Critical, Minor, or Pass.
• Interactive Table – Clickable list linking to full references and in-text citations.
  
• Author Representation- Analyzes the proportion of self-citations and author repetition—potential signal for citation rings.
• Journal Representation- Shows how often each journal is cited, helping assess whether references align with journal scope and audience.
• Recency Analysis- Charts publication dates of cited references, allowing filtering by timeframe (e.g., last 5, 10, or 25 years).

AI Chat

AI Chat Panel – An interactive assistant built into the dashboard for manuscript-level inquiry. It is built on Open Scholar and is not limited to information in the manuscript itself. The chat history is saved per manuscript.

Users can:

• Ask about methods, data reliability, or conceptual meaning.
• Access pre-populated prompts via hover icons beside Triage items.
• Retrieve context from manuscript text, Triage analysis, and external sources via Open Scholar.
• View per-manuscript conversation history for auditability.

Inline Feedback 

Allows users to rate AI-generated content (Thumbs up/down) and provide qualitative comments (e.g., “too much information,” “irrelevant”). Feedback is reviewed by Hum’s product team regularly.

Administrative Functions

Permissions Management – Controls journal access for users; editors may have restricted visibility while staff can access multiple titles.