Case packet

Neutral case identifier: case-e5c79d4a63f396

The possible directed relationship from Artifact A to Artifact B is under review.

Artifact A

Title as claim enables traversal as reasoning

Don't name notes like topics ("thoughts on memory"). Name them like claims ("structure enables navigation without reading everything").

When you link to a claim-titled note, the link becomes part of your argument:

"because approvals guard against LLM mistakes not active attacks, we can separate the security boundary from the approval UX"

The title IS the reasoning. Traversal IS thinking. The title functions as a typed signature — you know what you're getting before you load the full note. A topic label like "memory notes" is an undocumented function; a claim like "structure enables navigation" tells you the return value. This connects to how [types applied to documents mark affordances] — a claim title is an affordance declaration.

Prior work

Propositional titles are established practice in several fields:

Academic writing — thesis statements and paper titles that state the conclusion. The abstract leads with the claim.
Journalism — headlines state the finding ("Scientists discover X"), not the topic ("Research about Y").
Evergreen notes (Matuschak) — explicitly advocates for note titles as complete propositions rather than topic labels.
Zettelkasten practice — Luhmann used precise descriptive titles; the community has extensive discussion of atomicity and title quality.

The traversal-as-reasoning consequence — when titles are claims, link-following reads as argument — came to us via [arscontexta], which likely drew on these same traditions. The [Toulmin argumentation model] provides the formal structure behind the "since/because" link semantics this enables.

TODO: This survey is from the agent's training data, not systematic. Matuschak's writing on evergreen notes and Zettelkasten community resources on title conventions are worth ingesting.

Why it works

Inline links carry richer relationship data than metadata fields. The prose surrounding a link encodes WHY the linked note matters here — "because [X]" is a causal claim, "since [Y]" is a foundation claim, "but [Z]" is a tension. Claim-as-title makes these constructions possible, because topic labels don't compose grammatically. You can write "since [claims must be specific enough to be wrong]" but not "since [specificity notes]." Our [link relationship semantics] formalize this — argumentative links ("since", "because") and referential links ("see", "as defined in") are different intents that require different anchor context.

Progressive disclosure depends on this. The first disclosure layer is titles. If titles are claims, agents can curate what to load based on what each note argues. If titles are topics, agents must load notes to discover what they argue — the disclosure layer fails. This is why [instruction specificity should match loading frequency] — the loading hierarchy assumes that titles and descriptions carry enough signal for agents to decide what to load next.

Practical benefits: - scanning file tree = scanning arguments - following links = following reasoning chains - the vault becomes readable without opening files

Where it breaks: multi-claim documents

The pattern works best for ideas that ARE single claims. It breaks for compositional documents — specs, frameworks, classification systems — that embody multiple independent design choices.

[Document classification] is a clear example. It contains several distinct claims: "types assert structure not subject matter," "status is orthogonal to type," "a document has exactly one base type but zero or more traits," "text is the root type." Each could be a standalone claim note. But no single claim subsumes them all — any attempt produces something so abstract it's useless ("documents should be classified").

The traversal-as-reasoning framing explains why. A claim-titled note can serve as a premise: "since [X], therefore Y." A multi-claim document can't serve as a single premise because it IS multiple premises. When you write "see document classification," you're not invoking a reasoning step — you're pointing to a reference. The link semantics shift from argumentative ("since," "because") to referential ("see," "as defined in").

Document kind	Title convention	Link semantics	Role in traversal
Single-claim (insight, rationale)	Claim title	"since [X]", "because [X]"	Premise in reasoning chain
Multi-claim (spec, framework)	Topical title	"see [X]", "as defined in [X]"	Reference, not premise
Definitional (term pinning)	The term itself	"see [X]", "[X] means..."	Reference, not premise

Definitional notes are a second exception. Notes like [codification], [constraining], and [context engineering] pin down how a technical term is used in this project. Their titles are the terms they define — topical by nature. They function as reference entries: you link to them for precision ("as defined in [codification]"), not as premises in reasoning chains. Like specs, they can link TO claim-notes for justification while carrying topical titles themselves.

The two layers coexist. Specs link TO their constituent claim-notes for justification ([document types should be verifiable] is the rationale extracted from the classification spec). Claim-notes link TO specs as the system they support. But they have different title conventions because they play different roles in traversal.

This maps onto the existing type system: notes with claim titles may be promoted to type: structured-claim when the argument matures; spec, index, and other structural types carry topical titles. The title convention (claim vs topical) is independent of the type — any note can use a claim title.

The shadow side

Not every idea decomposes into a single declarative sentence — some are relational, procedural, emergent, or compositional. When reformulation feels forced, the question is whether the insight isn't ready or the format can't accommodate it. The type system makes this explicit: if you can't write a claim title, the note stays type: note with a topical title, and that's fine.

Relevant Notes:

[Agentic Note-Taking 23: Notes Without Reasons] — validates from inside: an agent operating in a curated graph describes first-person the qualitative difference between following propositional links ("since [X]") and browsing embedding-based similarity results — the strongest external validation of the claim-as-traversal mechanism

Source: - Adapted from [arscontexta methodology note] on the same topic, with the multi-claim boundary analysis added

Artifact B

Agents navigate by deciding what to read next

An agent has a task and needs information she doesn't yet have. She can't read everything, so at every step she encounters pointers — links, index entries, search results, skill descriptions — and decides which to follow. That decision is the fundamental unit of navigation.

What makes the decision tractable

Every pointer asks the same question: should I follow this? The agent can never be sure before following — the content might not deliver. So the decision is always probabilistic: how likely is this pointer to lead somewhere relevant, and what does it cost to find out?

What makes it tractable is context — information surrounding the pointer that hints at what the target contains. A bare filename forces the agent to load the target just to judge relevance. A pointer embedded in explanatory prose lets her judge without paying that cost. The more context a pointer carries, the cheaper the navigation decision.

Different pointer types carry different amounts of context. Inline links carry the most — the surrounding prose explains both what the target contains and why it matters. Search results carry the least — the agent has only titles and descriptions. Since [link-following and search impose different metadata requirements], the knowledge system must invest in different metadata for each mode: surrounding prose for link-following, titles and descriptions for search, and both for indexes that bridge the two.

Design implication

If navigation is deciding what to read, the knowledge system should make that decision as cheap as possible. [Title as claim] is the shortcut that works across all pointer types. When the title carries the argument, the pointer itself becomes the hint — every link text, every search result, every index entry does navigation work for free.