Operator decision 2026-09-21: the test track built on material tied to the
operator's employer (K2) is retired -- not re-measured, not frozen. Public
tests and gates run on invented material.
Retrieval gate:
- The four FUSION_PREMISE xfails are gone and pass through their INPUTS: the
synthetic MISS, LOOKUP and QUOTA bundles were re-measured for BM25 (the
miss fasit no longer shares the rare word `maa`; lookup and quota decoys
carry the question's words so each partition and the quota decide their
own fixture). SPECS_SHA256 moved with them. Rows 2 and 3 green again.
- Row 7's mutants M04, M06, M07, M08, M10 now patch `bm25`, the code the
default runs. Three survive with 0 ranks moved (passage body, title
weight, bm25.RRF_K), each with its mechanism printed. M07 was not forced:
every synthetic body carries its title as a heading.
- Row 9 (K2) removed; row 8 requires `wiki-20` alone, the `r761` and
`vegnormal` adapters are gone. Chose the broad reading of "K2" because the
operator decision defines it as employer-tied material and the order's
grep includes `vegnormal`.
Also removed: tests/test_default_bundle_pin.py, the K2 arms of
test_okf_consume, the four real-arm tests of test_quality, the R761 soft
hyphen test, the N101/N200 delivery tests and okf_accounting_gate's default
real corpus (and H5's guard, which only existed for those defaults). Two
fixtures carrying road-standard identifiers are rewritten with invented ones.
Gate after: 1 10/10, 2 7/7, 3 5/5, 4 6/6, 5 0/1, 6 10/10, 7 11/14,
8 NOT RUN -> GATE RED: rows 5, 7, 8. Suite 2423 passed, 1 skipped,
0 xfailed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
C4. `coverage` gains two keys, and every key it had keeps its bytes:
- `absent_terms`: the question's words the bundle holds in NO form -- not as
written, and not through a relative it uses (`bm25.query_groups`, the same
bridge the ranking reads through);
- `weak`: true when one such word exists or nothing was delivered.
A reading with its rule in the open, never a verdict about the bundle. It is
computed for both rankings (`bm25.absent_terms` serves the fusion). The
retrieval gate's `marked` -- the one reading both gates share -- reads `weak`
beside its own bar, never instead of it; the known-negative that strips the
payload's words now strips both readings.
Words that only FRAME a question are stopwords in both languages (`how
often`, `hvor ofte`, `hva står i`, `what does it say`), and so are the
Norwegian function words spelled without their letters (`naar`, `paa`), the way
ASCII-only text writes them. Read as topic words they would be "absent" from
any collection that never uses them, which is what the synthetic sets showed
on three answered questions before the list was extended.
The working method says what to do with it, in one sentence each: the skill
template's step 3 and the MCP server's instructions (1 253 bytes, under the
2 048 a client keeps) -- rephrase in the bundle's words, and if it stays weak,
say the bundle does not cover the question.
The search gate's table for this commit is kept in local state.
Suite on a clean tree after `git add`: 2397 passed, 2 skipped, 4 xfailed.
ruff, ruff format, mypy --strict clean. Retrieval gate unchanged at the rows
the previous commit left red.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Operator decision 2026-09-21: nothing from that consumer's collection goes out
on the public remote. The NAME stays where it is already published -- it is a
consumer of this library, named as such, and removing it would mean rewriting
published history, which this repository does not do. What goes is everything
that describes their CONTENT.
Removed across README, CLAUDE.md, CHANGELOG, four dated reports, the
consumption contract, three source modules and three test modules: their
corpus's document and page counts, the concept count of a bundle built from
it, the byte figures of a payload built from it, the question and fasit counts
and recorded score of their evaluation set, a bundle id with two content refs,
an order id naming them, and a path into their repository.
Kept, because the argument survives without the corpus: RATIOS and
percentages. A ratio is the finding -- a withheld list that is 65.5 % of a
payload is a defect at any corpus size -- and it discloses nothing about how
large anyone's collection is. Where a claim lost its denominator it now SAYS
so rather than quietly reading as unmeasured: the gate-refusal limitation in
the README states that the corpus and its counts are deliberately withheld and
points the reader at their own build, which is the number that binds them
anyway.
One integrity pin is kept and named here rather than left to be found: the
retrieval gate still pins that set by sha256, because the pin is what refuses
a self-written file in the right shape, and a checksum discloses nothing about
what it checksums. Its recorded SCORE is gone -- that was their figure about
their own corpus, and the row now says so instead of restating it.
The known-positive constants move with the contract document, as they must.
Suite green, 2372 passed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Measured 2026-09-20 on a 2313-concept bundle of one project's own
documentation: `withheld` held 2 305 entries = 186 440 B of compact JSON =
**65.5 % of the 284 850-byte payload**, and not one of those bytes counted
against the budget the same payload reports (`spent` was 45 192). A reader was
handed 239 658 bytes the budget line did not know about, to learn 2 305 concept
ids with nothing beside them -- the title being exactly what `--withheld-titles`
existed to buy, and which was off because buying it for 2 305 entries cost
another 37.9 %.
`withheld` is now a mapping: `total` (equal to `denominators.withheld`, so
SS 5.2's identity is unmoved and closes on the NUMBERS), `by_rule` (the same
total decomposed over the closed rule set, so "what kind of drop" is answerable
without the list), `nearest` (the best-ranked drops BY NAME, with title and
source document, so a reader who sees a near miss can ask for it) and
`complete`. The near misses are read off the ranking, not off `cut`'s output:
`cut` sorts by id so the partition is comparable, and that order says nothing
about which concept a reader might want next.
Same question, same bundle, after: **52 421 bytes, 18.4 % of the old file**.
The whole list stays reachable behind `--withheld-full`, and the two
instruments that classify EVERY miss by its rule -- the retrieval gate and
`okf_consume_measure` -- now ask for it explicitly and assert `complete`
rather than assuming it. `--withheld-nearest N` sets the cap (default 20,
which is `k` plus the next twelve). `--withheld-titles` is retired: a flag
whose only remaining effect would be to STRIP the title from a list the caller
asked for in full names no decision worth two shapes for one list.
`CONTRACT_REVISION` moves to `okf-consumption/2`, because a consumer indexing
the old key as a list would otherwise break silently. Three checker rules move
with it, and one of them is the interesting case: `parent_unfollowable` used
`excerpts` + `withheld` as the bundle's own denominator, which a truncated
block is not -- so that clause now runs only where the payload SAYS it is
complete, stated in SS 8.6 rather than left as a silence, with the other two
clauses (shape, self-reference) running either way. `Report` carries both
denominators, because a report claiming it examined 2 305 entries it never saw
is the same defect one level up.
The generated skill's "breaking point" section goes with it: it extrapolated a
concept count from the cost of ONE withheld entry, and there is no such slope
any more. It now states what this bundle's bookkeeping cost and that the block
is bounded by the cap rather than by the bundle -- an extrapolation from a
slope the code no longer has would be a measurement of the previous revision.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
A public repository should not carry the layout of the machine it was written
on, and it should not carry the identifiers of a queue nobody outside can see.
Six places in material this span added or changed did.
Neutral text, same facts: a private queue path in the EOL report, a private
note path in two docstrings and one report header, and four order identifiers
opening four reports. Where a sentence lost its source it says `internal
measurement note` -- the measurement is still named, the path is not.
One of them was output, not prose: row 9 of the retrieval gate printed a
`~/corpora/...` path to stdout on every run. It says the bundles exist on the
machine the row was written against; the row already takes `--k2 SET SHA
BUNDLE` from anyone who holds them.
Measured with the patterns as given, and both validated against a
known-positive on `df5a118` first -- an unvalidated pattern reporting zero is
not a measurement:
* `~/\.claude|/Users/|coord/.*/orders` over the 74 files the span touches:
**9 -> 6**. The six left are deliberate: two README lines telling a reader to
install a skill into their OWN `~/.claude/skills`, one prose line arguing
that `/Users/...` is not more portable than a relative path, and three lines
of `tests/test_retrieval_gate.py`'s own known-positive for this exact check,
which removing would disarm it.
* `[0-9]{8}T[0-9]{6}Z-[0-9]+` over the 38 files the span ADDED: **4 -> 0**.
A note on the method, because the first run of the first grep reported 0 and
was wrong: zsh does not word-split an unquoted parameter, so
`git grep -- $FILES` passed 74 names as one argument and matched no file at
all. Both numbers above come from `$(git diff --name-only ...)`, which zsh does
split, and the known-positive is what made the false zero visible.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
`coverage` carries three lists: the terms the pre-pass read the question as,
the terms no concept in the bundle answers, and the terms no delivered
excerpt answers. Without it a reader holding eight excerpts cannot tell a
bundle that ANSWERED its question from one that merely ranked something --
the two payloads have the same shape.
FACTS, AND NO VERDICT, which is a measurement and not caution. Two readings
were built and both falsified over 81 questions (16 synthetic, 65 across the
three real sets, 2026-09-20): the share of question terms a delivered
excerpt answers separates the synthetic controls at 0.33 against 0.50 and
REVERSES on real data (covered questions down to 0.27, one genuinely
uncovered question at 0.71); the share of a bundle tying the best lexical
match is ~0.00 for every real question either way. Question style dominates
the first, corpus size the second.
The one bar this repository declares is the gate's: `UNANSWERED_BAR = 2/3`
over `unanswered_in_bundle`, swept and collapsing at both ends -- at 0.50
eleven real covered questions are marked, at 0.70 the row falls to 5 of 6,
at 2/3 the row is 6 of 6 and 0 of 65 real questions are marked. The margin
is thin (0.6087 against 0.6667) and is published that way, together with
what it does not catch: r761-sk2's own known-negative sits at 0.2857.
Row 4: 3 of 6 RED -> 6 of 6 GREEN, with the 10 answered synthetic questions
held unmarked as the known-negative. The contract's SS 8 gains point 7, the
consumption skill is told to read the block, and the SS 7.4 known-positive
moves with the document (14 721/375 -> 16 389/417). Suite 2292 passed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two checks replace `bool(threshold)`: `_as_share` parses it as a share in
[0, 1] -- so `report-only; any number is acceptable for v1` is a NO, and so
is `80` -- and `_hold_out_verdict` RUNS the registered set against the
registered bundle and prints `answered of asked = share against threshold`.
A registration naming an absent set, an unreadable bundle or an empty set
is a NO with its reason, never an exception and never a silent pass. The
row is 11 checks; it stays RED today because no registration exists.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
REAL_SET_PINS states what each set IS -- questions, fasit entries, controls
and sha256 -- so a one-question file in the right shape is refused
(`check_real_pin`, exit 2) instead of reading `1 of 1 | 3 of 3 | GREEN`.
Three counts rather than one: the digest says the bytes are the pinned
bytes, the counts are what a reader can check against the source.
Every set's line now carries `measured against <key> = <path> | bundle_id
<id> | ref <sha256-tree:...>`, for the bundles the run actually used and
SS 3.3's two halves both printed -- three builds on this machine share one
bundle_id at three refs.
Stated limit: the table lives in the file a capability session edits, as
SYNTHETIC_SETS and SPECS_SHA256 do. It raises the cost of the attack and
does not remove it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
PM's checkpoint left seven small findings beside the four bearing ones. Six
are closed here (the seventh, running row 8 against the real sets, follows).
G9 -- THE CONFIRMATION TERM IS OBSERVED NOW. `hit = bool(hit_ids) and
bool(confirmed)` survived all 46 tests, because every mutation of the text
empties `hit_ids` one step earlier. The shape that reaches it is a delivery
that still CARRIES the citation and is no longer the concept file's bytes:
`M14` is that mutation and it is FELLED (row 7 goes 11 of 13 to 12 of 14, bar
12 of 13 to 13 of 14, still RED, the same two survivors), and a test drives it
with its known-positive in the same test. No production line changed: the term
was always observable, it was unobserved.
AND THAT MEASURES THE JUDGE'S INDEPENDENCE RATHER THAN ASSERTING IT. The judge
does read the bundle through `consume.read_concept` and `delivered_text` --
PM's finding -- but the index is warmed BEFORE the first mutation, so the two
sides do not move together. Measured both ways: index warmed first, every unit
is a miss with `confirmed False`; index built UNDER the same patch, every unit
is a hit. The gate never builds one under a mutation. Stated in `LIMITS` with
that measurement, rather than closed by re-implementing a normalisation rule
this repository already owns once.
SPECS -- the synthetic corpus is pinned like the sets (`SPECS_SHA256` over
`specs_digest`). PM's corpus tuning was caught by row 2's forced classes and
not by a pin, and a more careful tuning was left standing.
ROW 9 TAKES AN INPUT. `--k2 SET SHA256 BUNDLE` reads a gold set in this gate's
own set shape; `K2_QUESTIONS` stays the denominator whatever the file carries,
and a set of another size is refused (exit 2) as another set wearing this
one's name. Without a set the row stays RED and not NOT RUN -- ITS denominator
is known, six recorded questions, so the absence is measured; row 8's is not
known until the sets arrive. Both fail the gate identically. This is a
deliberate divergence from the order's parenthetical, stated here and in the
row.
MYPY. `mypy --strict` on this file goes 8 errors to 0, the four in
`read_real_set` among them (`questions = []` against a name inferred
`tuple[Question, ...]`) -- the adapters that meet the real sets.
63 passed. The verdict is unchanged: GATE RED: rows 3, 4, 5, 7, 8, 9.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
PM's J3. `MUTANT_ROSTER` carries the thirteen labels and `MUTANT_COUNT` their
number, both written apart from `MUTANTS`, and `row_seven` refuses to run
unless the labels it was handed ARE that roster, in order, with no duplicate.
The bar is taken from the roster's length, not from `len(mutants)`.
Why a pin and not a share: the bar is a percentage, so a longer list is a
lower bar per survivor. Seven copies of `M03 k = 1` took the row to 18 of 20
GREEN with the same two survivors -- nothing new felled, the bar lowered.
Lengthening the list honestly now costs three edits in three places, each
readable as what it is; a duplicate label is refused outright, because two
copies of one mutation are one mutation whatever the roster says.
Row 7 is unchanged on the shipped list: 11 of 13, bar 12 of 13, RED, the same
two survivors with the same measured notes. 56 passed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
PM's J1. Three of row 5's ten checks now read the repository's history instead
of the registration's own fields:
- the registration is COMMITTED and unmodified against HEAD -- a file written
in a working tree is not a pre-registration;
- the commit that ADDED it is not itself a change to the ranking -- a
threshold and the change it is supposed to bind, in one commit, is neither;
- a change to the ranking landed AFTER it. This is the one that cannot be
self-attested: it is satisfied only in the order a pre-registration actually
happens, and it is red today because neither half has happened.
The three come from `git_provenance`, a `Provenance` the row receives the way
it already receives a path, so both directions are driven from the test and
the default is the real git. Outside a git tree, or with no git on PATH, the
fields come back in their REFUSING form with the reason printed -- unknown is
not unknown-and-therefore-fine.
WHAT GIT CANNOT PROVE IS STATED IN THE ROW, not implied: history shows ORDER,
never that nobody read the number before writing the threshold -- a number can
be read from an uncommitted tree. Order is what these three checks are.
Row 5 is unchanged where it matters today: `0 of 1 RED`, no registration. The
two existing direction tests move 7 -> 10 checks and a third arm is added that
drives each git check red on its own. 54 passed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
PM's J10 and J8. Two mechanisms, one per attack, and neither is a pin a
capability session can edit in the same breath as the code.
J10 -- THE DENOMINATOR IS THE SET'S. `Unit` now carries the class its question
DECLARES. Row 2's denominator is the misses plus every forced fixture that
came back a hit, and row 3's is every unit whose set declares a withheld class
(b, c, e -- (a) is not in the bundle and (d) was delivered, so neither can
carry a printed reason) plus whatever the run withheld besides. A fixture that
stops producing its declared class is a BROKEN PREMISE, printed as one, and it
counts against its row: at `k = 32` row 2 stays RED with its denominator held
and row 3 keeps 5 units where it had shrunk to 2 and called that green.
J8 -- THE ROW CARRIES A KNOWN-POSITIVE. With `--source-quota` off, every
printed reason is true; that reading is not a lie, it is an empty measurement,
and row 3 must say so rather than print `6 of 6 GREEN` beside row 1 falling to
8 of 9. A set may now declare `source_quota_in_force`, and the row is NOT RUN
for such a set when the default cut and the quota-off cut deliver the same
concepts everywhere.
THE CONTROL'S OWN PREMISE WAS MEASURED FIRST, and it was false where it was
first put: over the five existing sets the two cuts deliver the SAME concepts
(the quota is topped back up), so 52 labels move `source_quota_exceeded` ->
`below_k` without one delivery changing. `set-quota.json` is the set where the
quota genuinely decides -- measured, `oversikt-08` is delivered without the
quota and withheld with it, and the fasit `svar/broennproeve` is delivered
only with it -- so the requirement is declared there and nowhere else. It
survives the honest fix, which changes labels and not the cut.
Rows 1 and 6 go 9 of 9 to 10 of 10: one added fixture, one added hit, both
green before and after. Rows 2 (7 of 7), 3 (2 of 5), 4, 5, 7, 8, 9 and the
verdict `GATE RED: rows 3, 4, 5, 7, 8, 9` are unchanged. 52 passed.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Two of PM's eight attacks, closed where they were measured.
J2 -- a set left out. `REQUIRED_REAL_SETS` names the three (`wiki-20`,
`r761-sk2`, `vegnormal-32`) and the row is NOT RUN until all three are given,
whatever the ones that ran scored. The numbers the run DID measure are still
printed: a missing set must not cost the reader the set that was measured, and
"not run" is the row's status, never a reason to withhold a figure.
J2b -- the headline was `quoted_hits + concept_hits` over
`quoted_units + concept_units`, written one line above the detail that says
the two are not summed. The three sets do not share a unit: `wiki-20` names a
citation, `r761-sk2` a section title, `vegnormal-32` a requirement number, and
a citation hit plus a concept hit is a number that is neither. A QUESTION is
the one unit all three have, so the headline is questions answered of
questions asked -- answered meaning at least one of the question's fasit
entries arrived, the reading row 1 already prints beside its own units -- and
the two unit totals keep their own denominators below it, unsummed.
49 passed (was 46 passed, 3 failed). The gate is unchanged where it did not
run: still exit 1, still `0 of 3 NOT RUN` with PM's recorded figures carried.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
One command, one exit code, and no capability: nothing here changes the
ranking, the fusion, the tokenisation or the cut. For a frozen question set
against a bundle it asks how many of N measurement units the payload carries
the fasit for, gives every miss exactly ONE class, and asks the thing the
payload does not do at all -- say so when it does not know.
Today, on the synthetic corpus this repository generates and the five sets it
ships pinned by sha256: rows 1 (9 of 9), 2 (7 of 7) and 6 (9 of 9) green;
3 (2 of 5), 4 (3 of 6), 5 (0 of 1), 7 (11 of 13), 8 (not run) and 9 (0 of 6)
red. GATE RED, exit 1.
- Row 3 is the finding to read first. In a bundle built from ONE source
document, every concept past the first two carries that document's
`source_file`, so a concept the RANK had already lost is withheld as
`source_quota_exceeded`. The truth is decided by the SAME cut run without
the quota -- PM measured the same lie on 13 of 25 real misses 2026-09-17.
- Row 4 is the second. No payload key says "this bundle does not answer
that", so the only honest reading today is `delivered == 0`; three of six
controls come out right and the three that do not get eight excerpts and no
statement. A control the bundle DOES answer must come back unmarked, or the
marking says nothing, so both directions sit in the same row.
- A miss has exactly one class -- (a) not in the bundle, (b) below k, (c) cut
by quota or budget, (d) delivered without the citation, (e) other -- and
each is FORCED by its own fixture. An unplaced miss takes the row to 0 of N.
- The judge opens the bundle. Every concept is read off disk before a payload
is built, a delivered excerpt whose text is not the concept file's bytes is
not a hit, and the two title forms come from `quality` rather than being
written a second time.
- FELLED means a row got WORSE, never merely that something changed: removing
the quota makes row 3 green, and counting that as a kill would credit this
gate with a check it does not have. The two survivors are reported with what
they measured -- the document prior dead and RRF_K flattened each moved 0
ranks and 0 deliveries on these fixtures -- and with a mechanism for each.
- Rows 8 and 9 are never green by leaving something out. The three real sets
are read from path + sha256 and never committed: a gold set names a
consumer's documents and this repository is public. K2 is 0 of 6 because the
gold set exists nowhere while its bundles do.
Denominators re-measured against the sources 2026-09-19, and all four hold:
wiki 20 questions / 29 fasit entries (sha 972d0f57...), R761 8 (S1-S6 + KP +
KN), vegnormal 32 questions / 43 must_cite, K2 6. PM's 45 of 70 is itself a
mixed sum -- wiki at question level, vegnormal at citation level -- so this
gate carries it labelled as recorded and never sums the two granularities.
46 tests, each failing row driven both ways through inputs rather than by
editing the row. No network (the socket guard is fired before its silence
counts), no private corpus, no clock.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
