Bio x AI Hackathon
  • Welcome to the Bio x AI Hackathon
  • Getting Started
    • Quickstart
    • Important Links
  • Developers
    • BioAgents
    • CoreAgents
    • Eliza Agent Framework
    • Knowledge Graphs
    • .cursorrules
    • Starter-repos
    • Plugin Guide
  • Vision and Mission
    • Bio x AI Hackathon
    • The Problems in Science
    • TechBio
    • Guidance from the Judges
      • Important Datasets and Code Repositories
      • Reading List
      • Common Mistakes for Developers new to Academia
    • Hackathon Ideas
      • Full Projects
        • The Complexity Slider - Finding Hypotheses at the Limits of Human Knowledge
        • [Hard Mode] Metadata Generation on datasets with No Manuscript or Code Associated
        • Inverse Reproducibility - Given Manuscript and Data, Make the Code
        • Atlas of Research Methods Formatted for Agentic Reuse
        • Utilizing Knowledge Graphs for the Detection of Potential Null Results
        • Creating an Iterative Publication Stack by Linking Together Existing Tooling
        • Longevity Atlas: Building a Decentralized Knowledge Network with Agentic Research Hypothesis Engine
        • CoreAgent Track - Opportunities to work with BioDAOs
        • SpineDAO Chronos Project Spec
      • Individual Plugins
        • Plug-ins for every piece of research tooling known to humankind
        • Reproducibility Assistant - Code Cleaning, Dockerization, etc
        • Finding and Differentiating Cardinal vs Supporting Assertions
        • [Easier Mode] Metadata Generation on Datasets Given the Manuscript and Code Repository
        • Sentiment Analysis on Existing Citations, Dissenting vs Confirming
        • Agentic Metadata Template Creation for Standard Lab Equipment
  • Ops
    • Calendar
      • Key Dates
      • Office Hours
    • Judges and Mentors
      • Communicating to Judges and Mentors
      • BioAgent Judging Panel
      • CoreAgent Judging Panel
      • Mentors
    • Prize Tracks
    • Hackathon Rules
    • Kickoff Speakers
    • FAQ
Powered by GitBook
On this page
  1. Vision and Mission
  2. Hackathon Ideas
  3. Individual Plugins

Finding and Differentiating Cardinal vs Supporting Assertions

Problem Statement:

Scientific manuscripts contain a complex network of information, including novel findings, methodological details, and contextual background. Extracting the core contributions (cardinal assertions) from this network and differentiating them from supporting information (supporting assertions) is crucial for efficient knowledge extraction and synthesis.

Challenge:

Develop a system that can analyze a scientific manuscript (input: PDF or text) and:

  1. Identify Assertions: Extract individual assertions (statements or claims) from the text.

  2. Classify Assertions: Categorize each assertion as either:

    • Cardinal Assertion: A novel, significant, or central claim that represents the core contribution of the research.

    • Supporting Assertion: A statement that provides context, methodology, provenance, or evidence for a cardinal assertion.

  3. Output Structured Data: Present the identified assertions and their classifications in a structured format (e.g., JSON-LD or RDF).

Detailed Description:

  • Cardinal Assertions:

    • These are the "take-home" messages of the paper.

    • They often represent new findings, novel insights, or significant theoretical advancements.

    • They can be statements of agreement or disagreement with existing knowledge.

    • They are usually found in the abstract, introduction, results, and discussion sections.

  • Supporting Assertions:

    • These provide the context, methodology, and evidence necessary to understand and evaluate the cardinal assertions.

    • Examples include:

      • Methodological details (e.g., experimental procedures, data analysis techniques).

      • Provenance information (e.g., data sources, previous studies).

      • Definitions of terms and concepts.

      • Background information and literature reviews.

    • Often found in the methods and introduction section of a paper.

  • Output Format:

    • The system should output the extracted assertions in a structured format that clearly indicates the classification (cardinal or supporting).

    • A possible format: JSON-LD or RDF

Desired Outcomes:

  • A functional system that can accurately identify and classify assertions in scientific manuscripts.

  • A demonstration of the feasibility of automatically extracting cardinal and supporting assertions.

  • Insights into the linguistic and semantic cues that distinguish these assertion types.

PreviousReproducibility Assistant - Code Cleaning, Dockerization, etcNext[Easier Mode] Metadata Generation on Datasets Given the Manuscript and Code Repository

Last updated 1 month ago