Move from raw lists to an ordered backlog fast.
Batch Formula Screener
When a team receives hundreds of compositions from an LLM, paper scrape, or brainstorming session, the screener turns that raw list into a ranked queue with stability and relevance context in seconds.
Key outcomes
What goes in
Inputs this feature expects
- Bulk formula lists from ideation, literature mining, or exports
- Optional domain filters such as battery, catalyst, or dielectric focus
- Priority rules for risk, stability, or qualification effort
What comes out
Outputs your team can act on
- A triaged batch ordered by likely relevance
- Fast elimination of low-signal or duplicate candidates
- A shortlist ready for deeper analysis in Lattice Graph
Workflow
How teams use Batch Formula Screener
Paste or upload the batch
Large candidate lists can come straight from spreadsheets or external generation tools.
Run bulk scoring
The screener normalizes the list, removes noise, and ranks the survivors by value.
Split into work queues
High-priority compositions go forward while low-priority ones are archived or deferred.
Best fit
Where this feature adds the most leverage
- Discovery teams processing large idea dumps
- Screening AI-generated candidate libraries
- Program managers building next-step work queues
Related features
More in Search & Discover
Formation Energy Predictor
LightGBM model, R²=0.933 on held-out equilibrium structures, trained on 204K corroborated structures. Performance on novel compositions may vary.
Cross-Source Confidence
Scores from 0-1 based on agreement across 9 independent DFT databases.
Similarity Search
Find materials like NMC811 but without cobalt using compositional and property context.