Ingest an abstract into a pedogenetic Knowledge Graph — causal_llm_ingest_abstract • edaphos

3.10.0

Reference
- Capstone — six pillars integrated
- Cross-pillar campaign
- Pilar 1 — Causal AI
- Causal backdoor on br_cerrado
- Causal on 1 095 real WoSIS profiles
- Causal-discovery trio (expert × LLM × data-driven)
- LLM-KG benchmark (Gemma 4 × GPT × Claude)
- Annotation workflow (pre-annotation + Shiny review)
- Pilar 2 — Physics-Informed ML
- Parametric ODE + Neural ODE
- Pilar 3 — 4D Pedometry
- ConvLSTM on synthetic cube
- Real MODIS + NASA POWER + EnKF
- Pilar 4 — Foundation Models
- SimCLR / MoCo embeddings
- Pilar 5 — Active Learning
- Hybrid policy + physics gate
- SoilGrids-BR live
- Pilar 6 — Quantum ML
- ZZFeatureMap + Q-KRR
- Cross-pillar bridges
- Pilar 1 × Pilar 4 — Foundation IVs
- Pilar 4 × Pilar 6 — Quantum-foundation kernel
- Unified infrastructure
- Unified uncertainty API
- Case — end-to-end Cerrado benchmark
- Releases
- v2.0.0 — Quantum kernel × Foundation (Pilar 4 × Pilar 6)
- v1.9.x — Foundation embeddings as causal IVs + Sargan/Cinelli-Hazlett
- v1.8.x — LLM benchmark infrastructure + Shiny annotation tool
- v1.7.x — Capstone vignette + native-query calibration + causal discovery
- Changelog

Wrapper that calls causal_llm_extract() on a single passage and then adds every returned claim as an edge of the supplied edaphos_causal_kg. Claims whose confidence is below min_confidence are discarded.

Usage

causal_llm_ingest_abstract(kg, abstract, source, min_confidence = 0.5, ...)

Arguments

kg: An edaphos_causal_kg to update in place.
abstract: Character scalar with the passage to annotate.
source: Character scalar used as the source attribute of every added edge (a bibliographic key, a DOI, etc.).
min_confidence: Numeric in [0, 1]. Claims with confidence < min_confidence are dropped before insertion.
...: Forwarded to causal_llm_extract() (backend, model, host, ...).

Value

The updated edaphos_causal_kg. An attribute "claims" carries the tidy data frame that was actually inserted.