World's first cross-source credibility-scored UAP database

Government
UAP Records.
One Graph.

517,317 sighting records spanning 68 independent sources — from US Air Force Project Blue Book to the Spanish CEFAE to GEIPAN France to the Hatch UDB and Lissoni Archives — unified, scored, and cross-linked for the first time in history.

Open the Explorer View All Sources
517,317
Total Records
68
Independent Sources
43,394
Cross-Source Links
178
Countries & Territories
1500
Earliest Record
9.8
Max Credibility Score
What is a Knowledge Graph

Data Connected,
Not Just Collected

A knowledge graph is a network where entities are nodes and relationships are edges. Most UAP databases treat records as isolated rows. This platform treats them as a living graph — where a Blue Book Air Force report from 1962 can be linked to a NUFORC civilian call about the same event 40 years later.

⬡
Nodes — Individual Sighting Records
Each of the 517,317 records is a node in the graph, carrying structured attributes: date, location, shape, credibility score, source tier, and evidence types.
⟷
Edges — Cross-Source Corroborations
The Haversine geospatial algorithm identifies when two different sources document the same event within 25 km and ±7 days — same-source records are never linked. Each match is an edge in the graph — 43,394 cross-source links, each storing its distance and days apart.
◈
Credibility — Edge-Weighted Scoring
A civilian report that is corroborated by an Air Force investigation scores dramatically higher than either source alone. The graph structure elevates quality through connection — not through assertion.
Why This Is Different

Six Firsts in UAP Research

01
First Unified Cross-Government Database
For the first time, records from US (Blue Book, CIA, AARO, DIA, NSA), UK (MoD), France (GEIPAN), Spain (CEFAE), and Brazil (SIAN) exist in a single queryable schema. No aggregator has done this before.
02
Algorithmic Cross-Source Corroboration
43,394 verified links where two or more independent sources documented the same incident — computed for the first time using Haversine geospatial matching at 25 km / ±7 days across 517,317 records.
03
Structured Credibility Scoring Algorithm
Every record receives a credibility score built from five independent dimensions, on a versioned scale (legacy records reach 9.8; current PAPER-1 records reach 6.5): source tier, physical evidence, duration, geospatial precision, and cross-source corroboration. Reproducible, transparent, versioned.
04
AI-Assisted PDF Extraction at Scale
Over 800 government FOIA documents — previously unsearchable scanned PDFs — were processed using Claude Haiku via structured extraction prompts. 525 CIA records and 13 AARO analytical documents extracted this way.
05
Public API with Canned Query Endpoints
A live public JSON API serves 10 pre-defined research queries — high credibility cases, government sources, corroborated events, nuclear facility sightings — with no authentication required for read access.
06
MCP-Compatible AI Query Layer
An MCP server at uap-mcp-server.onrender.com allows any Claude-compatible AI to query the full database in natural language — the first UAP database to be AI-queryable via standardised protocol.
How It Works

The Pipeline

01 —
Source Acquisition
Sources are acquired from primary origins wherever available — NARA FOIA releases, government open data portals, academic archives — and from established research archives and collections (such as the Hatch UDB and UPDB) where no primary release exists, with structured web scraping under rate limiting and robots.txt compliance. Provenance is tracked for every record.
02 —
Structured Extraction
CSV sources are parsed with column normalisation and shape vocabulary mapping. PDF sources (800+ documents) are extracted page-by-page using pdfplumber, then processed by Claude Haiku with structured JSON prompts tuned to each document format.
03 —
Geocoding & Normalisation
Locations are resolved to latitude/longitude via OpenStreetMap Nominatim with fallback string matching. Dates are normalised to ISO 8601 with confidence levels (exact / date / month / year). Shapes are mapped to a canonical 15-category vocabulary.
04 —
Credibility Scoring
Each record receives a score across five dimensions, on a versioned scale (legacy records reach 9.8; current PAPER-1 records reach 6.5): source tier (government vs. civilian), physical evidence types, observation duration, geospatial precision, and cross-source corroboration bonus. Algorithm is versioned and logged per ingestion run.
05 —
Geospatial Cross-Linking
The Haversine linker runs against all geolocated events with confirmed dates. It links only cross-source pairs — records from the same source are never linked to each other. A pair is stored as a same_event link when the two events fall within 25 km and ±7 days, subject to a per-source-pair cap. Links are binary matches with no confidence score: each one stores its distance in kilometres and its days apart.
06 —
Auditability & Versioning
Every ingestion run is logged with script version, source file hash, record count, and error summary. The database schema and scoring algorithm are versioned. The full pipeline is reproducible from raw source files.
Credibility Score Breakdown
Source Authority
1.0 – 6.0
Physical Evidence
+0.5 – 1.5
Duration
+0.5 – 1.0
Geospatial Precision
+0.5
Cross-Source Corroboration
Up to +4.0
Score Thresholds
Legacy scale shown (records reach 9.8). Current PAPER-1 records score to 6.5.
● 9.0–9.8 Maximum
Gov + radar + corroborated
● 8.0–8.9 Very High
Gov + strong evidence
● 7.0–7.9 High
Gov or corroborated civilian
● 5.0–6.9 Medium
Expert civilian, good evidence
The Core Finding
43,394
verified cross-source corroborations
Cases where two or more completely independent databases documented the same incident at the same location within 7 days of each other — computed for the first time across 517,317 records. A civilian phone-in report and an Air Force investigation, unknowingly recording the same event decades apart.
Explore corroborated cases →
Top corroborated source pairs
International-UFO-Press
↔
NARA-AirIntel
2,899 links
Hatch-UDB
↔
NICAP
2,823 links
NARA-FAA
↔
NUFORC
1,610 links
International-UFO-Press
↔
Lissoni-Archives
1,581 links
Hatch-UDB
↔
International-UFO-Press
1,047 links
Blue Book
↔
Hatch-UDB
1,032 links
FBI-Vault
↔
Hatch-UDB
708 links
Blue Book
↔
NICAP
676 links
Hatch-UDB
↔
NUFORC
653 links

Start Exploring the Graph

The interactive map loads 5,000 high-credibility events on first view. Filter by source, score range, date, shape, and geographic area. Click any marker to see full case details and cross-source links.

Open the Explorer Data Sources Request API Access
UAP Intelligence
517,317 records · 68 sources · MCP-powered
UAP Intel
Intelligence interface online. I have direct access to the UAP Knowledge Graph — 517,317 records across 68 government and civilian sources. Ask me anything: incidents, geographic patterns, shape analysis, credibility scoring, or cross-source corroboration.