Generate and test hypotheses from datasets and literature using LLMs.
npx skills add https://github.com/mwathiben/PropManager --skill hypogenic-mwathiben
Please help me install this Agent Skill. Skill: hypogenic Source: https://github.com/mwathiben/PropManager/tree/main/.claude/skills/hypogenic Command: npx skills add https://github.com/mwathiben/PropManager --skill hypogenic-mwathiben
Automated hypothesis generation and testing using large language models to accelerate scientific discovery by systematically turning data and literature into testable hypotheses and rigorous evaluation.
Install the Hypogenic library, configure a task with your dataset and prompts, and execute hypothesis generation and inference to obtain testable hypotheses.
High-intent search queries and answers about installing and using this skill.
Automate hypothesis generation by configuring a YAML task setup with your dataset and prompts to generate testable hypotheses. The system uses large language models to map hypotheses to observational data and conduct inference for validation.
LLM-based hypothesis testing applies large language models to systematically turn data and literature into testable hypotheses and rigorous evaluation. It generates hypotheses from datasets, literature, or combined signals for research tasks.
Yes, union methods combine literature-informed hypotheses with data-driven hypothesis generation to maximize coverage across domains. You can use optional literature integration alongside dataset analysis to generate robust hypotheses.
Yes, a configurable YAML task setup is required to accommodate different data schemas, datasets, and evaluation criteria. This configuration enables reproducible research workflows by defining your dataset and prompts.
Supported domains include deception detection, AI content detection, and mental health analysis. The system maps generated hypotheses to observational data in these fields for inference and validation.
Use clear extract_label workflows to map generated hypothesis outputs to dataset labels. This process maps hypotheses to observational data, conducts inference, and selects robust hypotheses for validation.
shushuznLoad therapeutics drug-discovery datasets and benchmarks via the PyTDC API.
ManfronEnricoGenerate structured, testable hypotheses and experimental plans from observations and data.
Division6066Select and optimize embedding models for semantic search and RAG applications.
silversteinGenerate testable scientific hypotheses from structured datasets and domain context.
