Open Knowledge Format: when the fact already has a name, the chunker is the bug

The interesting failure in the weekly-active-users example is not that the retriever missed the right document. It is that the document, as stored, no longer holds the fact. A metric definition is a claim plus a dependency: unique customers with a delivered order in the last seven days, computed against the `orders` table, with a playbook for the days the warehouse lags its SLA ^[16]. Run that through a chunker and the sentence survives while the pointer to the schema does not ^[10]. What comes back ranks well on cosine similarity and can still be an onboarding page that happened to use the phrase "active user" ^[11]. The prose reads the same either way, and that is the operational cost: a fluent paragraph will not tell you whether the model reasoned badly or was handed the wrong slice ^[12], so there is no failing test to write.

OKF's answer is unglamorous. The path is the identity, so `metrics/weekly_active_users.md` is both the file on disk and the address other files use to reach it ^[4], and concepts point at each other with ordinary markdown links, which makes the folder a graph laid over the directory tree ^[6]. The dependency is an edge in storage rather than something the model reconstructs per question. The sample bundle that answers the WAU question is four files ^[16], one of them the index ^[7], so three concept files carry the entire answer ^[19]. Nothing gets embedded, and the v0.2 compliance surface is one required frontmatter key, `type`, against four recommended ones ^[5][21].

The example metric file also carries a `verified` stamp from finance dated 1 July 2026 and a `stale_after` of 31 December 2026 ^[17]. That is a 183-day trust window written into the artefact itself ^[18], greppable across the bundle, which is not a property a floating chunk can have.

The lineage here is short. Andrej Karpathy described the read-and-maintain wiki pattern in April 2026 ^[15]; Sam McVeety and Amir Hormati at Google Cloud shipped the format about two months later ^[1][20]. Treat it as an argument at an early stage rather than a result: the writeup names one catalog that ingests bundles today, the renamed Dataplex ^[9], and offers no retrieval-accuracy or cost comparison against the chunked version of the same corpus ^[22]. Its own division of labour is the honest part. Embed the pile when you genuinely cannot name the document ^[13]. When finance can name it, and still argues about it in Slack, hoping the right slice comes back is wasted work that discards the links you already paid to write down ^[14].