ruvector/examples/data/discoveries/swarm_endangered.json
Claude 402d5dccd8 feat: ETL pipeline with sublinear ForwardPush PPR for cross-domain discovery
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
2026-03-16 23:17:00 -04:00

58 lines
No EOL
3.2 KiB
JSON

{
"discovery_type": "endangered_species",
"api": "GBIF Occurrence Search",
"iucn_category": "CR (Critically Endangered)",
"taxon": "Aves (Birds)",
"total_occurrences": 613578,
"entries": [
{
"title": "Critically endangered bird: Ara ambiguus",
"content": "Species: Ara ambiguus. IUCN Status: Critically Endangered (CR). Country: Costa Rica. Location: (10.033363, -83.509436). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-01T16:34:06. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Aythya baeri",
"content": "Species: Aythya baeri. IUCN Status: Critically Endangered (CR). Country: China. Location: (30.925189, 117.911175). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-03T15:46. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Gyps africanus",
"content": "Species: Gyps africanus. IUCN Status: Critically Endangered (CR). Country: Tanzania, United Republic of. Location: (-2.100957, 34.584936). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-03T09:39. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Cyanoramphus malherbi",
"content": "Species: Cyanoramphus malherbi. IUCN Status: Critically Endangered (CR). Country: New Zealand. Location: (-41.164963, 174.23098). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-02T17:49:21. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Pycnonotus zeylanicus",
"content": "Species: Pycnonotus zeylanicus. IUCN Status: Critically Endangered (CR). Country: Singapore. Location: (1.589613, 103.724626). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-01T14:21:07. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Emberiza aureola",
"content": "Species: Emberiza aureola. IUCN Status: Critically Endangered (CR). Country: Thailand. Location: (13.744109, 100.811165). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-01T07:09. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
},
{
"title": "Critically endangered bird: Necrosyrtes monachus",
"content": "Species: Necrosyrtes monachus. IUCN Status: Critically Endangered (CR). Country: South Africa. Location: (-24.218465, 30.977448). Observation type: HUMAN_OBSERVATION. Event date: 2026-01-01T18:03:14. Dataset: iNaturalist research-grade observations.",
"timestamp": "2026-03-15T23:49:06.185611Z",
"source": "gbif",
"confidence": 0.88
}
]
}