mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-25 15:03:46 +00:00
402d5dccd8
Three-stage pipeline (Extract → Transform → Load) using ruvector-solver: - Extract: loads 460+ discoveries from 48 JSON data sources - Transform: embeds into 64-dim vectors, builds 8-NN sparse graph, runs ForwardPush PPR (sublinear O(1/ε), Andersen-Chung-Lang 2006) - Load: outputs ranked cross-domain correlations + 12×12 domain matrix New data sources from parallel explorer swarms: - Humanities: Harvard Art, Library of Congress, Open Library, Nobel, Smithsonian - Genetics/Env: ClinVar variants, GBIF endangered, EPA air, marine, satellite fires - Tech/Infra: GitHub trending, Hacker News, SpaceX, ISS, crypto/forex markets Novel discoveries found by PPR: - Technology→Earth climate correlation (equatorial weather patterns) - Technology→Space-science link (ultra-short period brown dwarf) - Life-science→Academic (agentic AI + GPCR drug discovery bridge) https://claude.ai/code/session_01UWE22wnsZRSHKhT4h4Axby
15 lines
562 B
TOML
15 lines
562 B
TOML
[package]
|
|
name = "train-discoveries"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
publish = false
|
|
description = "Cross-domain discovery ETL pipeline using RuVector sublinear solver"
|
|
|
|
[dependencies]
|
|
ruvector-core = { path = "../../crates/ruvector-core", default-features = false, features = ["parallel"] }
|
|
ruvector-solver = { path = "../../crates/ruvector-solver", features = ["forward-push", "neumann"] }
|
|
serde = { version = "1.0", features = ["derive"] }
|
|
serde_json = "1.0"
|
|
rand = "0.8"
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|