Jew.tech → Data

Research & data estate

This is the corpus the rest of the site stands on, counted rather than estimated. Every figure below came from a query whose exact text is kept in a claims ledger with its result and its verification date; all of them were re-run on 2 August 2026. Where a number would flatter the work if stated loosely — deduplicated documents, indexed vector search, live versus stale copies — the looser version is not published and the reason is given instead.

34,457,680Files catalogued, 5 machines
234,591PDF files
10,232,735PDF pages
157,143Torah graph nodes
22,841Research papers ingested
202,816Research graph nodes
43,174Distinct works with provenance
34,865Vectors in Qdrant

Online right now, and what is not

An estate description that quietly counts unplugged drives is a fiction. Here is the split, as of 2 August 2026:

HoldingStateWhere
Torah knowledge graph (Neo4j)Online — queried live for this pagestudio1
File + provenance catalog (PostgreSQL 17 / pgvector, 38 GB)Onlinestudio1
Web inventory (PostgreSQL)Onlinestudio1
Vector store (Qdrant, 2 collections)Onlinestudio1
Document stores (ArangoDB, 4 databases)Onlinestudio1
Research corpus (SQLite, research.db)Onlinelocal working copy
Publisher PDF harvest + model backups (Synology NAS)Offline right now — not counted in the totals aboveNAS
Graph replicas on two Mac minisOffline right now — not counted in the totals abovemini1, mini2

The offline holdings are real and are named here for completeness, but no count from them appears in any total on this page. They will get their own verified rows in the ledger before any number from them is published.

The Torah graph

17,147 rabbinic teachings, each carrying its Hebrew source, a citable Sefaria reference, and a vector embedding — linked to 33,323 verses inside a 157,143-node graph. That is the whole claim, and every part of it is at 100% coverage. Around it sit 215,426 relationships across a 233-label schema, 15,910 verse citations, and PageRank scored over all 66,078 knowledge-base nodes. The text comes from CC-BY Sefaria sources.

157,143Nodes
215,426Relationships
17,147Teachings, 100% cited & embedded
2,504Machine-extracted rabbi→rabbi transmission links

The full breakdown, the sample node, the interactive transmission network and the extraction caveats live on its own page: the Torah knowledge graph.

Research corpus

A literature pipeline that ingests papers, extracts concepts and ideas from them, and assembles the result into a graph. 22,841 papers deduplicated on ingest produce 99,620 concepts, 81,966 extracted research ideas, and a graph of 202,816 nodes and 336,609 edges. 1,595 papers are rated high-relevance.

MeasureCount
Papers ingested (deduplicated)22,841
Papers rated high-relevance1,595
Concepts extracted99,620
Research ideas extracted81,966
Paper–concept links169,549
Graph nodes202,816
Graph edges336,609
This is a general AI/ML and education-technology corpus, not a Jewish-studies corpus. Its top concepts are machine learning (880), deep learning (748), education technology (648), computer vision (575) and large language models (460). The Judaism ∩ computer-science connection on this site is the work built on top of this literature — it is not a property of the literature itself, and nothing here should be read as implying these papers are Torah-related.

One database is the write target: research.db. The graph copies in Neo4j and ArangoDB are downstream exports, which is why the numbers in those stores lag the ones above.

File and provenance catalog

34,457,680 files indexed across five machines, with a provenance layer on top that tracks which physical copy a page came from and which OCR run produced its text. 234,591 of those files are PDFs, totalling 10,232,735 pages.

34,457,680Files catalogued
234,591PDF files
10,232,735PDF pages
274,098OCR runs
Provenance layerCountWhat it tracks
Page-link relations42,669,045Page-to-page and page-to-source links.
Pages with provenance10,233,053Pages carrying a traceable origin record.
OCR runs274,098Each text extraction, kept as its own record rather than overwritten.
Physical copies tracked127,234Distinct scans/editions of a work.
Distinct works43,174The work-level identity above the copies.
Book chapters2,445Chapter-level structure inside catalogued books.
MachineFiles catalogued
macbookpro23,102,817
JoshuascStudio111,261,114
JoshuascStudio334,674
mini132,290
Joshuas-Mini-226,785
Total34,457,680
These are files, not unique documents. Content hashing has not been run across the catalog — count(DISTINCT sha256) returns zero — so 234,591 is a count of PDF files catalogued, and the same document appearing on two machines is counted twice. Deduplication is future work; until it is done, the word "unique" does not appear next to any of these figures.

Vector stores

Two Qdrant collections holding 34,865 vectors between them, at two different embedding dimensions because they serve two different purposes: page-level retrieval over OCR'd material, and book-level retrieval over the corpus.

CollectionPointsDimensions
midrash_pages20,933384
corpus_books13,932768
Total34,865
Search here is exact, not approximate. Both collections report indexed_vectors_count: 0 — their HNSW indexes are not built, because each segment sits below the 10,000-vector threshold at which Qdrant builds one. Queries are brute-force and correct; at this scale that is fine. No claim of "HNSW-indexed vector search" is made.

Document stores

ArangoDB holds the document-shaped material: OCR output, extracted teachings, layout analysis, and an entity/relation graph over the Kroll corpus.

DatabaseCollectionDocuments
corpusocr17,161
corpusextracted_teachings2,245
corpusocr_layout2,345
vaultvaultteaching13,397 (stale snapshot — live figure is 17,147)
researchpapers8,229 (stale snapshot — live figure is 22,841)
krollrelations4,653
krollentities3,143

The two snapshots marked stale are exactly that: older exports that have not been refreshed from their write targets. They are listed rather than hidden, and their live counterparts are named beside them so no one mistakes a snapshot for the current state.

Web estate

90 web properties tracked, of which 76 are live and a further 5 are deployed on Workers — 82 live or deployed, 8 dead, 1 asleep for maintenance. 470 uptime probes and 383 DNS zones are configured across them, with 84 deploy-audit records and 76 theme-QA records on file, and 15 broken links currently outstanding and unfixed.

90Sites tracked
76Live (82 live or deployed)
470Uptime probes configured
383DNS zones

The Judaism, Torah and AI properties among them include jew.tech, torahtech.com, torahchain.com, torahtwin.com, talmudiclogic.com, gematriagraph.com, openrabbi.com, hashemlibrary.com, alephinity.com and tikkunology.org.

How this is served

All of the online holdings above run self-hosted on one machine — a Mac Studio reachable only over a private network — with no managed cloud database anywhere in the stack. Eleven containerised database engines do the serving: six Neo4j instances (the Torah graph, its earlier snapshot, and four smaller graphs), three PostgreSQL 17 instances with pgvector (the file, provenance, and web-inventory catalogs), Qdrant for vectors, and ArangoDB for documents. Four of the eleven were queried directly to produce this page; the container inventory behind the count is in the fleet map.

That arrangement is the point rather than a constraint. A corpus you own, on hardware you control, can be counted exactly, re-counted on demand, and corrected in public — which is the only basis on which any of the numbers here are worth stating.

How these numbers are made

Every figure on this page has a row in a claims ledger recording the claim, the exact query that produced it, the result, and the date it was verified. The ledger is re-run before publication; where a re-run disagrees with the page, the page is wrong and gets fixed. Three standing rules govern what appears here:

All figures verified 2 August 2026. Corrections and questions: joshua@digitaltwinpro.com.