open/llm-ingestion-okf
1
0
Fork 0
Code Issues Releases 1 Activity

docs(k3): round 19, a document's own identity, per-run frontmatter, and a description from the source

Browse source 
The report for K3-19, measured from a frozen export of 77e7cab: R761 from the
base 56b00e7 against 77e7cab -- directory `14ce59dc-...` -> `r761-prosesskoden`,
2 761 concepts and 710 shells unchanged, 110 = 110, 1 807 descriptions, the
flagged edition and address on 2 761 of 2 761, hit@1/8/50 over S1-S6 6/6 at
both k, `okf check` 4 of 4 with 0 findings, and --ingested-at alone
confirmed on 2 761 of 2 761.

Reported first rather than repaired: the known-positive falls from rank 1 to
not delivered at the default k (13 at k = 50), decomposed to the directory
name alone; and the order's own `sources` value is refused by PyYAML on every
concept while `okf check` accepts it.

CHANGELOG under [Unreleased], the README and CLAUDE.md paragraphs carry the
final numbers, and the README test count moves to 1659 collected.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-09-11 03:59:34 +02:00
commit 7eeafb35c8
4 changed files with 357 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

16
CLAUDE.md
View file

@ -132,9 +132,19 @@ one boundary rule:
R761's `<full>` carries a COMMA, a flow terminator, so it is never written
and never cleaned up. A titled section's `description` is its own FIRST
spec point (first `<p>` of the first DIRECT-child `sec-type="spec"`, whole),
carried by the plan entry and screened by the gate: 2 026 of 2 761 on R761,
none invented for the rest. SS 4.1 sets no length, so the one-paragraph
limit is ours. The registries are COUPLED: a row in
carried by the plan entry, screened by the gate, and written only where a
YAML reader reads it verbatim (`inbox._yaml_plain`): 2 026 of 2 761 titled
sections on R761 carry a point, **1 807** are written (2 have no `<p>`, 217
carry `: ` and PyYAML refused exactly those frontmatters), none invented.
SS 4.1 sets no length, so the one-paragraph limit is ours. **The directory
name reaches the RANKING:** `consume`'s signal 1 reads the concept id's
segments, so on a one-document bundle every concept now carries the
document's own name, and a question naming the document matches all of
them -- measured, the known-positive went rank 1 -> not delivered at the
default `k` (13 at k=50) with S1-S6 unmoved, and renaming only the
directory back restores rank 1. Operator question, not a patch. Report:
`docs/2026-09-11-k3-runde19-dokumentidentitet-og-frontmatter.md`. The
registries are COUPLED: a row in
`_CORE_EXTRACTORS` and not in `segmentation._STDLIB_EXTRACTOR_IDS` refuses
every proposal for the type, two layers away from the extractor.
`pdf`/`docx`/`xlsx` only via