Model · Life sciences
Life Sciences
A planned model for life-sciences research, starting with Ayurveda, medicinal plants and natural products. It answers with citations, confidence and contradicting evidence, and is grounded in a knowledge graph of plants, compounds, targets and diseases.
Model card
- Identifier
- truth-ls
- Area
- Life sciences
- Status
- Planned
- Version
- none released
- Access
- Planned as research access first.
- Licence
- To be stated at release.
Model names start with truth- after the foundation's mission. The name is not a claim that the model's outputs are correct; each model card states what has been measured.
Intended use
- Evidence review for researchers, practitioners and regulators.
- Hypothesis generation for discovery and formulation research.
- Standardisation and authentication research for herbal products.
Out of scope
- Diagnosis, prescribing or treatment decisions.
- Use by patients as medical advice.
- Conversation without citations. If it cannot cite, it abstains.
Status now
Planned. The data foundation built for Herb–Drug Interactions (truth-hdi) is the starting point for the knowledge graph. Nothing about this model has been measured yet, so this card describes the plan, not results.
Plan
Phase 1
Continued pre-training of an existing open foundation model on curated Ayurveda and life-sciences data.
Scale-up
Knowledge-graph grounding, partner datasets, expert evaluation and scientific benchmarks.
Phase 2
A foundation-owned model, with weights, training stack, evaluation and deployment held by the foundation.
Evaluation
Planned
- Citation accuracy, checked against the cited source.
- Abstention when evidence is insufficient.
- Expert review by practitioners and pharmacologists, with agreement reported.
- Results by language where classical and modern sources differ.