Launch the interactive gold-standard review app — llm_annotation_launch • 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

Opens a Shiny application that presents every abstract in the draft JSONL and lets the annotator accept / edit / reject each LLM-drafted claim, plus add any claim the LLM missed. Writes to output_path after every abstract, so interrupted sessions resume exactly where they left off.

Usage

llm_annotation_launch(
  draft_path,
  output_path = NULL,
  keyboard_shortcuts = TRUE,
  port = NULL
)

Arguments

draft_path: Path to the draft JSONL produced by llm_preannotate().
output_path: Where to write the reviewed JSONL. Defaults to draft_path (in-place review).
keyboard_shortcuts: Logical; enable keyboard bindings.
port: Optional integer port for the Shiny app.

Value

Called for its side-effect (launches app); invisibly returns the path of the reviewed JSONL.

Details

Keyboard shortcuts (when keyboard_shortcuts = TRUE): a – accept all and next | r – reject all | n – next abstract (save) | p – previous | + – add claim | 1..9 – toggle accept on claim n.