llm-ingestion-okf/docs/2026-09-12-g37-terskler.md

G37 — the thresholds, per file type, before the gate

Order 20260912T202210Z-7596115025-from-.claude, part 1. Base d310dbb (v0.8.5). Measured 2026-09-12 evening local time; the session crossed midnight, so the commit lands 2026-09-13. Python 3.14.0, guard 1.4.0, no model call and no network anywhere in what follows.

The order's own words for what this part must produce: "tabell filtype × metrikk × terskel × N × kilde", metrics restricted to what is already measured or measurable without a model, and "en filtype uten måling får terskel UNMEASURED, aldri et gjettet tall".

§ 0 — measured / not measured

Measured here. Every count in §§ 2–5: concept and document counts per file type over nine bundles, one-concept-document shares, empty-body counts, duplicate-title shares in two forms, short-concept shares, and which of the four evidence corpora carry a source_file key at all. Each is a shell or okf quality command printed beside it.

Not measured here. Boundary recall against a fasit (needs a fasit; § 6), hit@k (needs a question set and a fasit; § 6), anything about .txt, .csv, .json, .htm, .pptx, .odt, .rtf beyond the fixtures already in the tree, and whether any threshold below is the right bar — ratification is the operator's, and this document sets regression bars against a pinned artifact, which is a different thing (§ 4).

§ 1 — the three metric names, defined here because nothing defines them

The order names "grenseandel", "struktur-null-andel", "tomme konsepter", Bundle.skipped and "hit@k". Two of those five have no definition anywhere in this repository:

Measured on the base commit rather than on the working tree, because this document and the module beside it introduce both words:

• git grep -c "grenseandel\|boundary share" d310dbb -- docs src → 0 files
• git grep -ci "struktur.null\|structure.null" d310dbb -- docs src → 0 files
• known-positive control for the query form: git grep -c "hit@8" d310dbb -- docs → 19 files, so it can find.

So the definitions below are mine, written here so the gate and this document mean the same thing by them:

name	definition	what it needs
boundary_share	recovered boundaries ÷ boundaries the source itself declares	a fasit
structure_null_share	documents of a type yielding exactly ONE concept ÷ documents of that type in the bundle	the bundle alone
empty_concepts	concepts whose body holds zero non-whitespace characters ÷ concepts of that type	the bundle alone
hit@k	questions whose gold document reaches the payload at cut k ÷ questions	a fasit and a question set
run log	N, merged and coded rejections, from the bundle's own log.md	a bundle Door B wrote

Bundle.skipped does not exist under that name: the door's counts reach a bundle through corpus.CorpusReport, whose written form is the run log above (N, extracted, gated, persisted, substantive, degenerate, rejected, plus per-code counts). It is a whole-bundle figure and carries no file type, which is the limit in § 5.

§ 2 — the order's own numbers, re-measured first

The coordination note that arrived with the order asked for exactly this, and three of the five premises moved.

premise in the order	re-measured	verdict
13 extensions in the registry	_CORE_EXTRACTORS 7 + _OPTIONAL_EXTRACTORS 6 = 13	holds
four evidence corpora under a downstream consumer repository's finished-build directory	present: corpus-a, corpus-b, corpus-c, std-consumer — plus std-xml-generic and std-xml-v080, two more builds of the reference standard the order does not name	holds, and is incomplete
"the first corpus shall PASS on the measured types"	`grep -rl '^source_file:' corpus-a --include='*.md'	wc -l→ **0 of 446 concepts**. Same forcorpus-b(0 of 1 133),corpus-c(0 of 270) andstd-consumer` (0 of all its concepts)
"41,6 % grenser"	not in this repository when the order arrived — measured on the base commit, git grep -c "41[.,]6" d310dbb -- docs src → 0 files. It is the consumer's (one of its own reports), 1 148 of the reference standard's N declared STS sections, against the XML arm's N − 2 of N	holds, and the owner is another repo
"0 av 6 hit@k" on the HTML arm	two published numbers for the same HTML-arm bundle: 0 of 6 (the consumer, their six fasit questions, 10.09) and 2 of 6 → 4 of 6 with --source-quota 2 (this repo, docs/2026-09-10-k3-runde11-html-og-dominans.md:200,217, questions S1–S6)	holds for one instrument, not for the other

The last row is the reason the gate reports a denominator on every line: two true numbers about one bundle, four apart, because the question set differs.

§ 3 — what each corpus can answer

Command: okf quality <bundle> (part 2 of this order), cross-checked against grep -rh '^source_file:' <bundle> --include='*.md' | sed 's/.*\.//' | sort | uniq -c. The index walk and the directory listing agree on the concept count of the K2 reference, the XML arm, the HTML arm and corpus-a — four bundles, both methods. Below, N is the reference standard's number of declared titled sections and M the HTML arm's number of documents.

bundle	producer	concepts	file types present
K2-bundle-default-20260912	Door B (pinned reference)	453	.pdf 32 docs, .docx 5, .xlsx 2
std-xml-generic	Door B	N	.xml 1 doc
std-pdf-default	Door B	2 182	.pdf 1 doc
html-arm	Door B	a few thousand	.md M docs
corpus-a	the consumer's own pipeline	446	none — no source_file
corpus-b	the consumer's own pipeline	1 133	none
corpus-c	the consumer's own pipeline	270	none
std-consumer	the consumer's own pipeline	N − 5	none
b3	—	—	no index.md; the gate refuses to walk a directory (SS 9.2) and exits 2

The four corpora the order names as the evidence base carry no file type. The per-file-type thresholds below therefore rest on the K2 reference bundle and, for context only, on the three single-type bundles.

§ 4 — the table

Threshold semantics, stated before the numbers: a threshold here is a regression bar against a pinned artifact, set at the value measured on that artifact and never at a rounder number nearby. PASS means no worse than the reference on this metric. It is not a claim that the bundle is good, and it is not the operator's ratified quality bar — the K3 method refuses to set one inside the measurement that produces it ("setting one inside the same work that produces the first measurement would be fitting the bar to the number").

A rate needs a denominator. MIN_DOCUMENTS_FOR_A_THRESHOLD = 5, and it binds both the threshold's N and the judged bundle's: this repository's own honesty limit is "a 1/1 is not a rate" (docs/2026-09-08-k3-runde2-per-filtype.md).

file type	metric	threshold	N	source
every type	empty_concepts	0	every concept of 4 Door B bundles, all 0	definitional: corpus.CorpusReport calls a zero-character merge degenerate
.pdf	structure_null_share	8/32	32 documents	K2-bundle-default-20260912
.docx	structure_null_share	2/5	5 documents	K2-bundle-default-20260912
.xlsx	—	UNMEASURED	2 documents	below the floor of 5
.xml	—	UNMEASURED	1 document	below the floor of 5
.md	—	UNMEASURED	M documents, structure_null_share 44 % measured	the corpus is one generator's cut of one product, and it is the bundle under suspicion; a bar read off it would pass it by construction
.html	—	UNMEASURED	0 bundles in this repository	the HTML measurement was made outside it
.htm, .txt, .csv, .json, .pptx, .odt, .rtf	—	UNMEASURED	0 corpus documents	no corpus class in extract._EVIDENCE; .pptx/.odt/.rtf are constructed, N = 1–2

Candidates measured and not shipped

Three fasit-free metrics were measured over the same four Door B bundles, with the known-bad arm (html-arm, 1 148 of N boundaries) and the known-good arm (std-xml-generic, N − 2 of N) named in advance:

candidate	known-bad arm	known-good arm	pdf arm	K2 reference	verdict
duplicate titles within a document	0.0 %	349/N (12.6 %)	355/2 182	11/453	wrong direction
concepts under 40 characters	5.6 %	402/N (14.6 %)	1/2 182	25/453	wrong direction
duplicate titles across the whole bundle	37.8 %	349/N (12.6 %)	355/2 182 (16.3 %)	26/453 (5.7 %)	orders correctly, no bar

The third orders all four bundles correctly and is still not shipped: any bar that separates them sits between 16.3 % and 37.8 %, which is a number read off the two bundles it would judge. That is the operator's call and it is stated in STATE rather than taken here.

§ 5 — three limits that are properties of the instrument

1. A rejected document leaves no trace in the bundle. The pinned K2 bundle holds 32 .pdf documents; the corpus held 33, and one was rejected extractor_empty_pdf. The gate's denominator is the bundle's, never the corpus's, and it prints the run log (N = 43, merged = 39, coded rejections = 4) beside its own numbers so the two are never read as one. A bundle without a log says "no run log" rather than reporting zero rejections.
2. The run log carries no file type. codes is per rejection code, not per extension, so "this type failed to extract entirely" is invisible to a bundle-only gate. Naming that would be a change in corpus.py, not here.
3. The reference bundle passes its own bars by construction. okf quality on K2-bundle-default-20260912 returning PASS on .pdf and .docx is a control that the gate reproduces its own reference — nothing more.

§ 6 — what would reach the defect that started this

The 41.6 % arm is UNMEASURED under this gate, and that is the honest answer rather than a hidden one: the metric that fells it is boundary_share, which needs the publisher's own declared structure. The reference standard has one (N STS <sec> titles, <consumer repository>/fasit.json), and 4 of the 9 bundles above have no fasit at all. A --fasit input, a threshold on boundary_share, and the operator's bar are one further round, named in STATE and not begun here. That round is § 7 below (G37b, order 20260912T223334Z-132479088, 2026-09-13).

§ 7 — G37b: --fasit and boundary_share

Order 20260912T223334Z-132479088-from-.claude, on base 5e5d01c (v0.9.0, pushed, untagged). Measured 2026-09-13. Python 3.14.0, no model call, no network. The order's own instruction was measurement first: two premises measured before any threshold is set.

§ 7.0 — the correction this section owes § 2

The row above published grep -rn "41[.,]6" docs/ src/ → 0 as a present-tense fact. It stopped being true in the same commit, because the document making the claim writes the number twice. Re-measured today the working tree returns 2 hits, both in this file. The measurement it was meant to be is the one on the base commit, and it is now written that way. This is the repository's own trap (memory/falsifiser-egne-negative-paastander.md) firing on the file that records traps.

§ 7.1 — P1: the normalisation, measured on a known-positive first

The fasit is <consumer repository>/fasit.json, a JSON list of exactly N objects, each carrying title and norm (sec_type, depth, label, outline_page and id as well). Every norm is unique, and so is every title.

The normalisation is derived, not guessed. Strip all whitespace, then lowercase, reproduces the fasit's own norm from its own title on N of N rows. Two candidates were run first and fell on the same file: lower-casing and keeping only alphanumerics scores 58 of N (it eats the . in 2.1Grunnoppskrifter and the - in 3Mel- og gjærtyper). Unicode NFC makes no difference here — N of N titles and norms are already NFC — and the rule is the one the consumer's own measuring script applies, so a number produced here and a number produced there are the same number.

P1's own bar is 99 % on the known-good arm, and the literal reading of it fails — for a reason that is measured and is not the normalisation. On std-xml-generic (the declared-structure arm, N concepts):

match form	recovered of N
literal: normalised concept title equals the fasit's norm	22 (0.8 %)
pair: (concept's own directory, normalised residual title)	N − 24 (99.1 %)
either	N − 2 (99.9 %)

The cause is this repository's own id form: STS glues the numbering token into <title> (11.1Surdeigsstarter), and okf's default route moves that token into the concept id (11-1/…) while keeping the residual as the title. A gate scoring the literal form alone would report a 99.9 % arm as 0.8 % and call it a segmentation defect. Both forms therefore ship, neither as a fallback for the other: the literal form wants the title with its token, the pair form without, and no single bundle can offer both. The std-d1 build is the control in the opposite direction — literal N − 34, paired 0.

That decomposition is not this round's invention either. It is the M8 correction the consumer took verbatim from this repository's own round-14 report; the instrument here reproduces their two forms so the two repositories cannot silently measure different things.

Known-positive delivered: N − 2 of N (99.9 %), the published number to the unit. Known-negative delivered: html-arm at 1 148 of N (41.6 %), also to the unit — the arm the bundle-only gate returned UNMEASURED/exit 3 for.

§ 7.2 — P2: the threshold rests on one product, and says so

The fasit describes one document: a long reference standard. Every number below is that product's. The bar is declared with corpora = 1 in the code (quality.BOUNDARY_THRESHOLD), the row prints N = 1 corpus on every run, and the printed line also states what --fasit is: an assertion by the caller that this bundle is a build of the document the fasit describes — the same posture okf consume --ref has.

That is not a formality. Measured: the pinned 43-document K2 reference bundle scores 0 of N and corpus-a scores 0 of N. Both read FAIL, and in both cases the right reading is the assertion was wrong, not the bundle is bad. A gate that could tell those two apart would need a bar on "does this fasit describe this bundle", and that bar would have to be read off the bundles it judges.

§ 7.3 — every bundle measured, with the fasit

okf quality <bundle> --fasit <consumer repository>/fasit.json

bundle	concepts	literal	paired	recovered of N	verdict	rc
std-xml-generic (reference)	N	22	N − 24	N − 2 (99.9 %)	PASS	0
std-xml-v080	N	22	N − 24	N − 2 (99.9 %)	PASS	0
std-consumer	N − 5	20	N − 29	N − 9 (99.7 %)	FAIL	1
std-d1 (the consumer's own pipeline)	N − 33	N − 34	0	N − 34 (98.8 %)	FAIL	1
html-arm (known-bad arm)	a few thousand	1 130	28	1 148 (41.6 %)	FAIL	1
corpus-a (another product)	446	0	0	0	FAIL	1
K2-bundle-default-20260912 (another product)	453	0	0	0	FAIL	1

§ 7.4 — the bar, and why it sits where it sits

metric	threshold	N	source
boundary_share	999/1000	N declared boundaries, 1 corpus	std-xml-generic against fasit.json

The bar is 99.9 %, just under the known-good arm's measured share (N − 2 of N, which sits 0.03 percentage points above the bar). Unlike the two bars in § 4 it is not the measured fraction itself, and nothing turns on that: every build measured in § 7.3 reads the same verdict under 999/1000 as under the measured fraction. The semantics are the same as in § 4: a regression bar, not a quality claim. PASS means no worse than that build of that product, to within 0.03 percentage points.

It is a tight bar and the cost is stated rather than hidden: two of the four builds of the reference standard measured fall under it, at N − 9 and N − 34 of N — 0.25 % and 1.2 % below the reference. The class separation is nevertheless wide: any bar between 1 148/N (41.6 %) and (N − 34)/N (98.8 %) separates the known-bad arm from every build of the reference standard measured. The shipped bar sits above that interval, just under the one share that is read off a pinned artifact instead of off the bundles being judged. Moving it inside that interval is the operator's call, and the interval is published here so the call can be made on numbers.

A floor applies here too, in the fasit's own unit: MIN_DECLARED_FOR_A_THRESHOLD is the same 5 as the document floor, so a fasit of four rows gives UNMEASURED rather than a share.

§ 7.5 — what did not change

• Without --fasit, nothing moves. okf quality <bundle> on html-arm still prints one .md row, no boundary row, and exits 3. A test holds it, and the word "boundary" does not appear in the per-type half of the output.
• No version bump, no tag, no push. v0.9.0 was already bumped by G37 and is still untagged; the tag is the operator's.
• okf check is untouched. So is the consumer, which was read and not written.

§ 7.6 — honesty limits of this section

• N = 1 product. Every number in § 7.3 is the reference standard's. Nothing here says what boundary_share does on a second declared structure, because no second one exists in reach.
• The bar fails builds nobody calls bad. Named above rather than tuned away. The alternative — a bar at N − 34 — is a number read off a bundle the gate judges.
• A zero is ambiguous by construction. 0 of N means this fasit does not describe this bundle on both bundles where it occurred, and the gate cannot distinguish that from a total segmentation failure. It prints both match-form counts so a reader can see which it is (a real build of the product scores in the thousands on one of the two forms).
• One file was read outside this repository beyond the fasit. The order said to read only the fasit from the consumer; deriving the pair-key form required reading their measuring script (one experiment script, read-only). The alternative was to guess the match rule, which is what P1 exists to forbid. Nothing there was written.
• boundary_share is still not a hit@k. It asks whether a declared section became a concept, never whether a question reaches it.

Honesty limits

• Two thresholds, and one of them rests on five documents. .docx at 2/5 is exactly at the floor this document sets for itself. It is a bar against a pinned artifact, not a rate anyone should quote.
• structure_null_share has never fired on a real bundle. Of the five Door B bundles measured, none is worse than its reference; the rule's FAIL side is exercised on constructed bundles in tests/test_quality.py only.
• empty_concepts is 0 on every concept of the four bundles. The bar is definitional and has never fired on real data either. A metric that never fires is not evidence that nothing is wrong.
• One rule was found by running the gate, not by reading it. A one-document PDF bundle scored 0 of 1 against the 32-document reference and read as PASS. The floor now binds both denominators; the version of this document written before that run would have published the wrong rule.
• Nothing here measures answer quality. hit@k asks whether a gold document reached the payload; this gate does not even ask that.