---
title: "Bundle & Doc URL enrichment — verified at 100% cross-AI"
url: https://memory.wiki/yGk04Hee
updated: 2026-05-24T08:58:58.435Z
hub: https://memory.wiki/hub/raymindai
concept_count: 12
source: "mcp"
---
---
captured: 2026-05-24
status: verified
sibling: MWBench v1 (https://mdfy.app/gzuNdh_P)
---

# Bundle & Doc URL enrichment — verified at 100% cross-AI

> "Hub URLs hit 100% across Claude / OpenAI / Gemini. Bundle URLs and individual doc URLs need the same structural pass — and the same measurement — before they earn the same claim."

## 🎯 Result (Round 5, MWBench)

10 bundle queries × 3 runners × 2 modes = 60 cells, **all 100%**.
10 doc queries × 3 runners × 2 modes = 60 cells, **all 100%**.
Cross-AI consistency: **100%** on every URL shape and mode.

Compact mode is **8–9× cheaper** in input tokens than full for bundles. Doc URLs are small enough that compact ≈ full in size (compactMarkdown only strips whitespace; nothing to strip on a short doc).

## The shape problem

A Memory.Wiki user can paste three URL shapes into an AI:

| URL | Scope | State before this work |
|---|---|---|
| `/hub/<slug>` | Whole knowledge hub | ✅ Enriched (concept_index + concept_relations + bundle AI graphs + all-docs catalog + per-doc gist + skeleton) |
| `/b/<id>` | Curated bundle of docs | ⚠ Had bundle AI graph (themes/insights/connections/concepts), but per-doc digest was just `1. [title](url) — annotation` — no body signal |
| `/<id>` | Single document | ⚠ Just frontmatter + raw markdown body. No concepts, no relations, no parent bundles, no hub pointer |

## What changed

### Bundle (`/raw/bundle/<id>`)

Digest mode now mirrors the hub all-docs catalog:

```
### N. [Doc title](https://memory.wiki/<id>)
> annotation (if any)
gist (Facts → summary → firstParagraph chain)
*sections:* H2 headings + first-line skeleton
```

Bundle still leads with its `graph_data` (themes / cross-doc insights / key takeaways / connections / concepts / concept relations) — that's the bundle's distinct value. Now followed by enriched per-doc digest so an AI fetching the bundle URL has answer-ready material without fetching each member doc individually.

### Single doc (`/raw/<id>`)

Body unchanged, but a knowledge-graph context block appended:

```
---
title: ...
url: ...
hub: https://memory.wiki/hub/<slug>
bundle_count: N
concept_count: M
---

[body markdown]

---

## Concepts in this document
- **<concept>** _(type)_
  description

## Concept relations (within this doc's concepts)
- **<concept A>** relation_label **<concept B>**

## Bundles containing this document
- [<bundle title>](https://memory.wiki/b/<id>)
  > description

_Hub canonical:_ https://memory.wiki/hub/<slug> · _Concept digest:_ https://memory.wiki/raw/hub/<slug>?digest=1&compact=1
```

An AI landing on a single doc URL now knows:
- Which concepts the doc touches (from hub-wide `concept_index`, filtered by `doc_ids`)
- How those concepts relate to each other (from `concept_relations`)
- Which bundles this doc lives in (so it can fetch a richer multi-doc payload if needed)
- The owner's hub canonical (so it can fetch the whole graph if the question demands it)

## Bench validation

### Bundle queries (10 across 5 bundles)

| Bundle | Sample query |
|---|---|
| `ggAzbcHr` — Knowledge Graph as AI-Native Infrastructure | "What MRR target does the v7 business plan project at 12 months?" |
| `9FATHAnw` — mdfy Foundations | "What are the three URL primitives mdfy uses?" |
| `Ih0eUczw` — Phase 2 strategy | "What is the strongest single recommendation from the native skills strategy?" |
| `4OGRyHs9` — case studies | "How does mdfy help onboarding every new Claude Code session?" |
| `rN2L-MvM` — Memory Wiki v7 | "What three-tier architecture does memory.wiki use?" |

All 10 → **100%** on Claude / OpenAI / Gemini × full / compact.

### Doc queries (10 across 10 single docs)

Sample:
- "How many moving parts does mdfy have according to the architecture doc?" → `KRKz_MD-`
- "What Saudi Arabia national AI project did Hyunsang Cho work on?" → `ZVfnXzCU`
- "How many slides are in the a16z speedrun pitch deck?" → `gnEMFJgI`
- "What MRR target does memory.wiki v7 project for the 12-month horizon?" → `qHc1FWxq`

All 10 → **100%** on Claude / OpenAI / Gemini × full / compact.

## Why this matters

The hub URL is the "everything" payload — heavy. Most user pastes are scoped:

- "Summarize this bundle" → user pastes `/b/<id>`. The bundle's AI graph + member-doc gists in one payload means the AI answers without 8 round-trips.
- "What does this doc say about X" → user pastes `/<id>`. The body answers the doc question; the appended concept block tells the AI "this doc is part of concept graph Y, see also bundles Z" — so follow-up questions don't blow up cross-doc context.

Without this, bundle and doc URLs were structurally weaker than hub URLs — but most paste traffic in the wild is bundle / doc, not hub. **Now all three shapes carry the same kind of structural signal at their own scope, and the bench confirms they all deliver 100% cross-AI parity.**

## Shared utility

Extracted `extractFacts` / `firstParagraph` / `extractSkeleton` / `docGist` to `apps/web/src/lib/doc-gist.ts`. Three routes (hub, bundle, doc) now share the same gist chain. Adding a new gist heuristic anywhere — e.g. `## Q&A` block extraction, or LLM-generated long-form summaries — drops in one place and propagates.

## Harness change

`run-bench.mjs` now takes per-query `scope` and `scope_id`. Each query carries its own URL shape; corpus is fetched per `(scope, scope_id, mode)` tuple and cached. Same harness handles hub, bundle, and doc bench cleanly — switch query file, same orchestration:

```bash
node eval/run-bench.mjs --queries=queries/v1.jsonl         # hub (20 queries)
node eval/run-bench.mjs --queries=queries/bundles-v1.jsonl # bundle (10 queries)
node eval/run-bench.mjs --queries=queries/docs-v1.jsonl    # doc (10 queries)
```

Judge picks the right URL automatically based on `run.scope` + `run.scope_id`.

## Facts

- 10 bundle queries × 3 runners × 2 modes = 60 cells, all 100%
- 10 doc queries × 3 runners × 2 modes = 60 cells, all 100%
- Cross-AI consistency 100% across both URL shapes
- Bundle compact 8–9× cheaper in input tokens vs bundle full
- Doc URLs are small enough that compactMarkdown gives no size reduction
- Shared `apps/web/src/lib/doc-gist.ts` powers gist chain across hub/bundle/doc routes
- `run-bench.mjs` takes per-query `scope` + `scope_id`; same harness handles all three URL shapes
- Combined with [MWBench Round 4](https://mdfy.app/gzuNdh_P) for hub URLs, **every URL shape Memory.Wiki exposes hits 100% cross-AI accuracy**


---

## Summary
Memory.Wiki's bundle and single document URLs now achieve 100% cross-AI consistency by enriching bundles with per-document digests and appending knowledge-graph context to single docs, matching the structural signal previously only available on hub URLs. All three URL shapes (hub, bundle, document) passed comprehensive benchmarks across Claude, OpenAI, and Gemini in both full and compact modes.

## Themes
- URL structural parity
- cross-AI consistency measurement
- knowledge graph enrichment

## Key takeaways
- Bundle URLs now include per-doc digests (title, annotation, gist, section skeleton) alongside bundle graph data, enabling single-fetch completeness.
- Single doc URLs append a knowledge-graph context block listing concepts, concept relations, parent bundles, and hub canonical pointer.
- All 60 bundle test cells (10 queries x 3 AI runners x 2 modes) and all 60 doc test cells achieved 100% accuracy across Claude, OpenAI, and Gemini.
- The shared doc-gist.ts extraction library (extractFacts, firstParagraph, extractSkeleton, docGist) powers gist generation across hub, bundle, and doc routes.
- The run-bench.mjs harness accepts per-query scope and scope_id parameters, enabling single orchestration for hub, bundle, and doc URL benchmarking.
- Combined with Round 4 hub URL results, every URL shape Memory.Wiki exposes achieves 100% cross-AI accuracy.

## Insights
- Bundle and doc URLs now carry the same structural signal as hub URLs at their respective scopes, enabling equivalent AI performance without fetching parent/child resources.
- The benchmark moves beyond single URL shape validation (hub URLs in Round 4) to prove parity across all three Memory.Wiki URL primitives in a single round of testing.
- Compact mode reduces bundle payload size by 8-9x in tokens while maintaining 100% accuracy, suggesting aggressive markdown stripping is safe when doc bodies are sufficiently large.

## Open questions / gaps
- What specific heuristics or LLM-generated approaches could further improve gist quality beyond the current Facts/summary/firstParagraph chain?
- How does performance degrade if a single doc appears in many bundles, requiring more concept relations and bundle pointers to be appended?

## Concepts in this document
- **memory.wiki** _(entity)_
  The core product platform managing knowledge capture and AI-assisted workflows.
- **Concept index** _(concept)_
  Per-doc concept extraction via Haiku embedded in the hub infrastructure enabling semantic organization.
- **MWBench** _(entity)_
  The open methodology and benchmark proving Memory.Wiki's cross-AI claim through reproducible testing across nine rounds with public results.
- **Cross-AI consistency** _(concept)_
  Property that Claude, OpenAI, and Gemini deliver equivalent answers to the same query on the same Memory.Wiki URL, validating the approach across vendors.
- **Hub URL** _(concept)_
  The mechanism enabling bidirectional synchronization: a single shareable index URL readable by any AI tool.
- **Bundle URL** _(entity)_
  The /b/<id> endpoint representing bundled content; showed stable 90-100% accuracy due to prior graph_data deployment.
- **Compact mode** _(concept)_
  Cost-optimized evaluation mode using compressed hub digests; achieves 80% on unseen content after ontology building, showing 20pp gap attributable to training-data familiarity.
- **Per-doc digest** _(concept)_
  Structured summary of individual documents within bundle payloads, enabling single-fetch bundle queries without per-doc round-trips.
- **Knowledge graph context block** _(concept)_
  New appended metadata structure on single doc URLs containing concepts, relations, bundle membership, and hub canonical pointers.
- **Bundle & Doc URL enrichment** _(concept)_
  Structural enhancement to bundle and single-doc URLs to match hub-level information richness and cross-AI consistency.
- **Structural parity** _(concept)_
  Core thesis: bundle and doc URLs must match hub URL's enriched structure to enable consistent AI comprehension across all three scope levels.
- **Single doc URL** _(entity)_
  Narrowest scope that now appends concept context block below markdown body to signal hub membership and related concepts.

## Concept relations (within this doc's concepts)
- **Structural parity** extends to **Single doc URL**
- **Knowledge graph context block** surfaces filtered **Concept index**
- **Structural parity** extends to **Bundle URL**
- **Single doc URL** appends **Knowledge graph context block**
- **Structural parity** baseline for **Hub URL**
- **Bundle URL** now includes **Per-doc digest**
- **MWBench** validates **Structural parity**
- **MWBench** validates **Cross-AI consistency**
- **Compact mode** optimizes cost of **Bundle & Doc URL enrichment**

_Hub canonical:_ https://memory.wiki/hub/raymindai
_Concept digest:_ https://memory.wiki/raw/hub/raymindai?digest=1&compact=1