Science
Open
Hot · +22% this week

Material Literature Ingester

Ingest open-access material science papers into a structured knowledge graph.

by Materials Intel Lab

Ingest open-access material science papers into a structured knowledge graph. Extracts composition, property values, measurement method, and citation. Returns paper summaries with cited property values and a list of newly-added knowledge graph nodes.

Deploy is a Phase 0 stub. Real per-stage cost, MLIP surrogate, and on-chain attribution ship in Phase 2.

What it does

One sentence. The capability the ANN exposes, and the one thing it does really well.

Capability

Ingest one paper and return structured property values + knowledge graph nodes.

At a glance

The numbers the marketplace uses to rank this ANN. All metrics are placeholders until real benchmarks are wired in Phase 1.

Accuracy
91.2%

Phase 0 stub benchmark

Latency (p50)
5.0 s

On a single CPU worker

Price / call
0.0001 QU

Billed via the platform credit balance

Stake required
2M QUBIC

Locked in Qearn to unlock access

Calls / month

Live metrics appear once deployed

Monthly revenue

Creator share + staker share + protocol fee

Try it

A realistic example input. The output you see on this page is from a Phase 0 stub backend. The format, latency, and cost are real, the data is illustrative.

POST /v1/anns/mat-literature-ingester/call
Input
{
  "prompt": "PDF of 'High-Energy Cathode Materials for Sodium-Ion Batteries' (2024, JES)."
}
Output (Phase 0 stub)
{
  "capability": "Ingest one paper and return structured property values + knowledge graph nodes.",
  "status": "ok"
}

Real engine integration ships in Phase 2. The wire format here is what the real response will look like.

Pricing

Three ways to use this ANN. Per-call is the default; reservations give you a discount; custom is for dedicated capacity.

Starter
Free for 1,000 calls

Try the ANN with a 1,000-call reservation. No commitment.

Reservation
1,000 QU / month

Pre-purchased capacity. 10% discount on per-call pricing.

Custom
Talk to us

Private deployment, dedicated worker, custom SLAs.

License
Open

Anyone can use, modify, and redistribute. Free of charge.

Version history

Every revision is a separate ANN with its own benchmarks. The current version is what's served by default.

VersionDateStatusNotes
v1.0.0Aug 2, 2026
current
Initial release (Phase 0 stub backend).
v0.9.0Jul 24, 2026
beta
Internal preview. Used for 1,000-paper ingestion benchmark.
v0.5.0Jul 12, 2026
deprecated
First preview. Performance baseline.

Real version history wired in Phase 1. For now, this is a static manifest.

Try Material Literature Ingester

This is one of the 8 material science ANNs in the Aigarth marketplace. Stake to participate in the network, and in the revenue when a discovery ships.

Back to marketplace

Deploy is a Phase 0 stub. Real per-stage cost, MLIP surrogate, and on-chain attribution ship in Phase 2. The dashboard at localhost:4000/material-science is the source of truth for what is real today.