CLAUDE.md

@@ -1318,37 +1318,15 @@ and fixtures, never code.
   what a bundle looks like, this asks whether the payload for a question
   carries the fasit. **Written RED, no capability**: eight rows, exit 0 only
   when all are green, 1 otherwise, 2 on wrong input, `--json`. Rows 1-4, 6, 7
-  run against a synthetic corpus this repo GENERATES and eight sets it ships
+  run against a synthetic corpus this repo GENERATES and six sets it ships
   pinned by sha256 -- no network, no private corpus, no clock; a set whose
   bytes moved is exit 2, never a quiet continuation, because **a gold set is
   an INPUT and never a constant here** (`okf_consume_measure.py`'s rule, and
   this repo is public). **THE CORPUS IS PINNED THE SAME WAY** since
   2026-09-19 (`SPECS_SHA256`). Today (measured on the default run
-  2026-09-22): **1 (14/14) - 2 (7/7) - 3 (5/5) - 4 (6/6) - 5 (0/1) -
+  2026-09-21, v1.1 K): **1 (10/10) - 2 (7/7) - 3 (5/5) - 4 (6/6) - 5 (0/1) -
-  6 (14/14) - 7 (15/15) - 8 (0 of 1 set, NOT RUN without `--real`)**,
+  6 (10/10) - 7 (11/14) - 8 (0 of 1 set, NOT RUN without `--real`)**,
-  `GATE RED: rows 5, 8`. **Row 7 fells 14 of 14 since 2026-09-22**: the three
+  `GATE RED: rows 5, 7, 8`.
-  that survived v1.1 (M06 passage body, M07 title/path weight, M10
-  `bm25.RRF_K`) each got a fixture that makes its mechanism decide a delivery
-  (`PASSAGE`, `PATH`, `FUSION`, set `set-mechanisms.json`; the fusion one keeps
-  its lead through K = 180 and loses it at 190), with `src/` untouched.
-  **THE JUDGE READS A PASSAGE AS A PASSAGE (2026-09-22).** It predated v1.1
-  C1 and required a delivered text to be the whole concept's bytes, so every
-  excerpt `as_passage` cut was class (e) even when its span carried the
-  citation -- the dominant miss class when row 8 was run on the real set.
-  `passage_span` now accepts a passage only when the delivered text IS its
-  exact reconstruction: the span is `body[start:end]` byte for byte, `of` is
-  the body's length, a `[...]` stands exactly where text is left out, and the
-  one other line allowed is a heading line of the body above the span (or a
-  prefix of one); WHICH heading is the product's choice and is not re-derived.
-  The citation is read in the SPAN alone, never in the heading, the markers or
-  across the seam. Two traps are pinned by tests: the offsets count in the
-  DELIVERED body (read in the concept file they land a frontmatter's length
-  off), and "the span occurs somewhere in the text" accepts an invented
-  sentence beside it. **M15** (a passage carrying one sentence the file does
-  not, M14's shape for passages) is row 7's fifteenth mutant, felled through a
-  new fixture that delivers a passage (`DELIVERY`, set `set-passage.json`),
-  because no synthetic concept was long enough to be cut. `src/` untouched;
-  `MUTANT_BAR` unchanged.
   **THE K2 TEST TRACK IS RETIRED (operator 2026-09-21, v1.1 K)**: material
   tied to the operator's employer is not re-measured and not frozen, and
   public tests and gates run on invented material. Row 9 (K2) and the `r761`
@@ -1357,8 +1335,8 @@ and fixtures, never code.
   the R761/N101/N200 deliveries; `okf_accounting_gate.py` has no default real
   corpus. The synthetic corpus was re-measured for BM25 (`MISS`, `LOOKUP`,
   `QUOTA`), so rows 2 and 3 are green through their own fixtures again, and
-  row 7's mutants patch `bm25` where the default runs there; the three that
+  row 7's mutants patch `bm25` where the default runs there; three survive
-  survived with 0 ranks moved are felled since 2026-09-22 (above). What
+  (passage body, field title weight, `bm25.RRF_K`) with 0 ranks moved. What
   the text below says about rows 8/9, K2 and the three sets is history.
   **FOUR OF EIGHT CHEATING ATTACKS WENT THROUGH IT AND ARE CLOSED
   (2026-09-19).** PM's checkpoint on `2c8296b` found rows 3, 5, 7 and 8 could

README.md

@@ -84,13 +84,13 @@ here was measured; none of it is a plan.
   `--no-assets` takes the image path out entirely.
 - **Three of this repository's own gates are RED, and each red row is a stated
   finding rather than a bug to be surprised by.** The retrieval gate is red on
-  rows 5 and 8, the MCP gate on row 2, and the content accounting's judge
+  rows 5, 7 and 8, the MCP gate on row 2, and the content accounting's judge
   on rows 2, 3 and 6. For a user that means: no ranking change has yet been
   registered against a held-out set (row 5), the real-corpus row is NOT RUN
-  without its private set and so is red rather than green by omission
+  without its private sets and so is red rather than green by omission
-  (row 8) -- and since 2026-09-22 its judge reads an excerpt v1.1 cuts to its
+  (row 8), three mechanical mutants of the BM25 ranking survive with 0 ranks
-  answering passage as that passage, accepted only when it is the exact
+  moved — the passage body, the title field weight and the fusion constant —
-  reconstruction from the bundle's bytes. MCP anchors and concept ids are different
+  so the gate cannot yet tell those parts from their absence (row 7), MCP anchors and concept ids are different
   vocabularies so `okf_fetch` cannot be addressed with a set's anchor (row 2),
   and the accounting still reports real losses on the reference corpus (rows 2,
   3, 6). The rows and their numbers are under [Judge the
@@ -1196,18 +1196,18 @@ set names a consumer's documents and this repository is public. **The corpus
 is pinned the same way** (`SPECS_SHA256`): every row counts against those
 documents, so moving them without moving the pin is exit 2.
 
-**It is RED today, on rows 5 and 8**, and each of those is a
+**It is RED today, on rows 5, 7 and 8**, and each of those is a
 finding rather than a defect in the gate:
 
 | row | what it asks | today |
 |---|---|---|
-| 1 | hit@payload, one fasit entry = one unit | 14 of 14 |
+| 1 | hit@payload, one fasit entry = one unit | 10 of 10 |
 | 2 | every miss carries exactly one class, each forced by its own fixture | 7 of 7 |
 | 3 | the `rule` the payload prints for a withheld fasit is the true one | 5 of 5 |
 | 4 | an uncovered question comes back marked, a covered one does not | 6 of 6 |
 | 5 | a hold-out set, frozen and with its threshold written first | 0 of 1 |
-| 6 | every delivery confirmed against the bundle's own bytes | 14 of 14 |
+| 6 | every delivery confirmed against the bundle's own bytes | 10 of 10 |
-| 7 | mechanical mutants of the ranking and the cut, felled | 15 of 15 |
+| 7 | mechanical mutants of the ranking and the cut, felled | 11 of 14 |
 | 8 | the real set, from path + sha256 | 0 of 1 set, NOT RUN without `--real` |
 
 **The public rows run on invented material only** (operator decision
@@ -1230,28 +1230,13 @@ delivered excerpt answers — facts, no verdict, and the one bar is the gate's
 own `UNANSWERED_BAR = 2/3` — 3 of 6 to 6 of 6.
 
 Row 7's mutants patch the code the DEFAULT ranking runs (BM25 since v1.1),
-and it fells all 15. Until 2026-09-22 three survived with **0 ranks and 0
+and it reports three survivors with what they moved rather than with a shrug:
-deliveries** moved -- the passage signal reading no body, the field signal
+the passage signal reading no body, the field signal weighing no title and no
-weighing no title and no path, and a flattened fusion (`bm25.RRF_K`) -- because
+path, and a flattened fusion (`bm25.RRF_K`) each moved **0 ranks and 0
-every synthetic concept was short and opened with its own title, so none of the
+deliveries** on these fixtures. Each has a mechanism: the field signal still
-three ever decided a delivery. Three fixtures now make each one decide one
+reads every body, every synthetic body opens with its own title as a heading,
-(`set-mechanisms.json`): a long concept answered in one window of its body
+and over two signals `K` only reorders a concept whose two ranks lie far apart,
-against short concepts whose titles carry the question's words; a concept named
+which no fixture holds.
-by its path alone against decoys denser in the body; and a concept first in one
-signal and 21st in the other against a decoy 10th and 11th, which a flattened
-fusion ranks first because only the rank sum then counts. Each fixture is
-delivered at the shipped defaults and falls out of `k` with its own mechanism
-switched off; `src/` did not change.
-
-A delivery is judged against the bundle's own bytes (row 6), and since v1.1 a
-concept over 4 000 characters is delivered as its answering passage: the
-nearest heading above it, `[...]`, the span, `[...]`. The judge counts such a
-passage only when it is EXACTLY that reconstruction -- the span byte for byte
-the delivered body at the passage's own offsets, markers only where text is
-left out, the heading a line of the body above the span -- and it reads the
-citation in the span alone. A looser rule ("the span occurs somewhere in the
-text") would accept an invented sentence beside the span; the fifteenth
-mutant (M15) is exactly that, and a fixture that delivers a passage fells it.
 
 Row 8 is never green by leaving something out: it requires every named set and
 is NOT RUN until it has them — one set of three used to read `6 of 6 GREEN`.

tests/fixtures/retrieval/set-mechanisms.json

@@ -1,28 +0,0 @@
-{
-  "set_id": "synthetic-mechanisms",
-  "bundle": "passage",
-  "note": "Three questions, one per mechanism the default BM25 ranking runs and no earlier fixture made decide a delivery: the passage signal's body windows (bundle `passage`), the field signal's title and path weight (bundle `path`), and the rank-fusion constant (bundle `fusion`). Each is delivered at the shipped defaults and falls out of k when its own mechanism is switched off, so row 1 is what fells M06, M07 and M10.",
-  "questions": [
-    {
-      "id": "PA1",
-      "question": "Hvem kontrollerer varmekablene i taket?",
-      "bundle": "passage",
-      "fasit": [{"by": "concept", "value": "aarbok/kapittel-tre", "quote": "kontrolleres av vaktmesteren"}]
-    },
-    {
-      "id": "PT1",
-      "question": "Hva gjelder for vester ved kanopadling?",
-      "bundle": "path",
-      "k": 6,
-      "fasit": [{"by": "concept", "value": "kanopadling/regel", "quote": "brukes paa vannet"}]
-    },
-    {
-      "id": "FU1",
-      "question": "Hva gjelder for isbading?",
-      "bundle": "fusion",
-      "k": 1,
-      "fasit": [{"by": "concept", "value": "badebok/kapittel", "quote": "isbading om morgenen"}]
-    }
-  ],
-  "controls": []
-}

tests/fixtures/retrieval/set-passage.json

@@ -1,13 +0,0 @@
-{
-  "set_id": "synthetic-passage",
-  "bundle": "delivery",
-  "note": "One question whose answer lies in a concept over consume.PASSAGE_CHARS, so it is delivered as a passage: heading, [...], span, [...]. The span carries the citation. Rows 1 and 6 count it only when the judge accepts a passage that is its exact reconstruction from the bundle's bytes, and M15 (one sentence added to the passage) fells both.",
-  "questions": [
-    {
-      "id": "PD1",
-      "question": "Hvem gir varmepumpa i kjelleren service?",
-      "fasit": [{"by": "concept", "value": "husbok/drift", "quote": "service av roerleggeren"}]
-    }
-  ],
-  "controls": []
-}

tests/test_retrieval_gate.py

@@ -524,37 +524,6 @@ def test_a_mutant_is_felled_by_the_row_that_got_worse_and_never_by_one_that_did_
     assert after[3] >= before[3]
 
 
-@pytest.mark.parametrize(
-    "prefix",
-    [
-        # The three that survived v1.1: each is a mechanism the default ranking
-        # RUNS, so a gate that cannot see it removed cannot see it break.
-        "M06 ",  # the passage signal reads no body
-        "M07 ",  # the field signal weighs no title and no path
-        "M10 ",  # the fusion is flattened
-        # A passage carrying one sentence the file does not: M14's shape for
-        # the delivery form v1.1 C1 added.
-        "M15 ",
-    ],
-)
-def test_row_seven_fells_every_mutant_of_a_mechanism_the_ranking_runs(
-    tmp_path: Path, prefix: str
-) -> None:
-    """A survivor of row 7 is a mechanism the synthetic corpus never makes
-    decide a delivery. Felled means a row got WORSE on the pinned sets and the
-    pinned corpus -- never a row that merely moved."""
-    (mutant,) = [m for m in gate.MUTANTS if m.label.startswith(prefix)]
-    cases, _ = gate.synthetic_cases(tmp_path / "bundles", FIXTURES)
-    before = {row.number: row.k - row.m for row in gate.deterministic_rows(cases)}
-    with mutant.patch():
-        rows = gate.deterministic_rows(
-            [gate.measure_case(case.question_set, case.bundles) for case in cases]
-        )
-    after = {row.number: row.k - row.m for row in rows}
-    worse = [number for number in sorted(before) if after[number] < before[number]]
-    assert worse, f"{mutant.label} survives: no row got worse ({before} -> {after})"
-
-
 # --- row 8 --------------------------------------------------------------------
 
 
@@ -635,18 +604,14 @@ def test_the_gate_is_red_today_and_says_which_rows(tmp_path: Path) -> None:
     by_number = {row.number: row for row in rows}
     assert sorted(by_number) == [1, 2, 3, 4, 5, 6, 7, 8]
     # Rows 2 and 3 are green again since the synthetic corpus was re-measured
-    # for BM25 (2026-09-21). Row 7 fells all 14 since 2026-09-22, when the three
+    # for BM25 (2026-09-21). Row 7 is red on three survivors, each printed with
-    # v1.1 survivors each got a fixture that makes their mechanism decide a
+    # what it moved.
-    # delivery (`set-mechanisms.json`, three more row-1 units), and all 15
+    assert [row.number for row in rows if row.fails] == [5, 7, 8]
-    # since the judge reads a passage as its exact reconstruction and one
+    assert (by_number[1].k, by_number[1].m) == (10, 10)
-    # fixture delivers a passage (`set-passage.json`, one more unit), so M15
-    # has something to fell.
-    assert [row.number for row in rows if row.fails] == [5, 8]
-    assert (by_number[1].k, by_number[1].m) == (14, 14)
     assert (by_number[2].k, by_number[2].m) == (7, 7)
     assert (by_number[3].k, by_number[3].m) == (5, 5)
-    assert (by_number[6].k, by_number[6].m) == (14, 14)
+    assert (by_number[6].k, by_number[6].m) == (10, 10)
-    assert (by_number[7].k, by_number[7].m) == (15, 15)
+    assert (by_number[7].k, by_number[7].m) == (11, 14)
 
 
 def test_the_same_tree_measures_the_same_twice(tmp_path: Path) -> None:
@@ -662,7 +627,7 @@ def test_the_command_exits_one_and_prints_every_row(
     printed = capsys.readouterr().out
     for number in range(1, 9):
         assert f"\n{number} " in f"\n{printed}"
-    assert "GATE RED: rows 5, 8" in printed
+    assert "GATE RED: rows 5, 7, 8" in printed
 
 
 def test_the_json_form_carries_the_same_rows(capsys: pytest.CaptureFixture[str]) -> None:
@@ -1034,140 +999,6 @@ def test_the_mutant_roster_is_pinned_apart_from_the_list_it_names() -> None:
     assert len(set(gate.MUTANT_ROSTER)) == len(gate.MUTANT_ROSTER)
 
 
-# --- a passage is judged as a passage ------------------------------------------
-#
-# Since v1.1 C1 a concept over `consume.PASSAGE_CHARS` is delivered as its
-# answering passage: the nearest heading above the span, `[...]`, the span,
-# `[...]`. The row-6 identity (delivered text == the whole body) is older than
-# that and read every such delivery as class e. The judge must now accept a
-# passage that IS its exact reconstruction from the bundle's bytes, and nothing
-# looser: "the span occurs somewhere in the text" accepts an invented sentence
-# beside it.
-
-_HOUSE_NOTE = "Styret gjennomgaar notatet og foerer det inn i arkivet. Sekretaeren sender kopi."
-_INVENTED = "En setning som ikke staar i konseptfila."
-
-
-def _house_bundle(tmp_path: Path) -> Path:
-    """One concept of about 6 600 characters: a heading ten lines in, the
-    answer thirty lines below it, and a literal `[...]` on the LAST line, far
-    outside any span centred on the answer."""
-    body = "\n".join(
-        [_HOUSE_NOTE] * 10
-        + ["## Teknisk rom"]
-        + [_HOUSE_NOTE] * 30
-        + ["Varmepumpa i kjelleren faar service av roerleggeren hvert aar."]
-        + [_HOUSE_NOTE] * 40
-        + ["Se vedlegg [...] i arkivet."]
-    )
-    spec = gate.BundleSpec(
-        "retrieval-house",
-        (
-            gate.DocumentSpec(
-                "husbok", "husbok.md", (gate.ConceptSpec("drift", "Drift av huset", body),)
-            ),
-            *(
-                gate.DocumentSpec(
-                    f"skriv-{number}",
-                    f"skriv-{number}.md",
-                    (gate.ConceptSpec("skriv", f"Skriv {number}", "Skrivet er arkivert."),),
-                )
-                for number in range(3)
-            ),
-        ),
-    )
-    return gate.build_bundle(tmp_path / "house", spec)
-
-
-def _house_question(*quotes: str) -> gate.Question:
-    return gate.Question(
-        id="H1",
-        question="Hvem gir varmepumpa i kjelleren service?",
-        fasit=tuple(gate.Fasit("concept", "husbok/drift", quote) for quote in quotes),
-    )
-
-
-def _inject(where: str) -> pytest.MonkeyPatch:
-    """A passage carrying one sentence the concept file does not: at the end of
-    the span, or between the heading's marker line and the span."""
-    original = consume.as_passage
-
-    def mutant(excerpt: dict[str, object], window: int) -> dict[str, object]:
-        out = original(excerpt, window)
-        if "passage" in out:
-            text = str(out["text"])
-            if where == "span":
-                cut = text.rindex(f"\n{consume.PASSAGE_ELISION}")
-                out["text"] = f"{text[:cut]} {_INVENTED}{text[cut:]}"
-            else:
-                marker = f"{consume.PASSAGE_ELISION}\n"
-                cut = text.index(marker) + len(marker)
-                out["text"] = f"{text[:cut]}{_INVENTED}\n{text[cut:]}"
-        return out
-
-    patch = pytest.MonkeyPatch()
-    patch.setattr(consume, "as_passage", mutant)
-    return patch
-
-
-def test_a_passage_whose_span_carries_the_quote_is_a_hit(tmp_path: Path) -> None:
-    bundle = _house_bundle(tmp_path)
-    gate.bundle_index(bundle)
-    question = _house_question("service av roerleggeren")
-    payload = consume.build_payload(bundle, question=question.question, withheld_full=True)
-    (excerpt,) = [e for e in payload["excerpts"] if e["concept_id"] == "husbok/drift"]
-    passage = excerpt["passage"]
-    assert isinstance(passage, dict), "the premise: this concept is delivered as a passage"
-    start, end = passage["start"], passage["end"]
-    assert 0 < start and end < passage["of"], "the premise: `[...]` on both sides"
-    # FELLE 1, pinned: the offsets count in the DELIVERED body. Read against
-    # the concept file they land a frontmatter's length off.
-    view = gate.bundle_index(bundle).concepts["husbok/drift"]
-    assert view.body[start:end] in str(excerpt["text"])
-    assert view.whole[start:end] not in str(excerpt["text"])
-    (unit,) = gate.measure_units(bundle, question)
-    assert (unit.hit, unit.confirmed, unit.klass) == (True, True, None), unit
-
-
-@pytest.mark.parametrize("where", ["span", "between heading and span"])
-def test_a_passage_carrying_an_invented_sentence_is_not_a_hit(tmp_path: Path, where: str) -> None:
-    """FELLE 2, pinned: the quote is still in the span and the span is still in
-    the text, so "the span occurs somewhere" would count this. The delivered
-    text must BE the reconstruction."""
-    bundle = _house_bundle(tmp_path)
-    gate.bundle_index(bundle)  # the judge reads the bundle BEFORE the payload
-    question = _house_question("service av roerleggeren")
-    patch = _inject(where)
-    try:
-        (unit,) = gate.measure_units(bundle, question)
-    finally:
-        patch.undo()
-    assert unit.hit is False
-    assert unit.confirmed is False
-    assert unit.klass == "e"
-    assert unit.detail == "the delivered passage is not its reconstruction from the bundle's bytes"
-
-
-def test_a_quote_the_passage_carries_only_outside_its_span_is_not_a_hit(tmp_path: Path) -> None:
-    """The heading and the markers are delivered and are not the span: a quote
-    found only there was delivered without the citation (class d). The first
-    unit is the known-positive of the same run."""
-    bundle = _house_bundle(tmp_path)
-    units = gate.measure_units(
-        bundle, _house_question("service av roerleggeren", "Teknisk rom", "[...]")
-    )
-    assert [(unit.hit, unit.klass) for unit in units] == [
-        (True, None),
-        (False, "d"),
-        (False, "d"),
-    ], units
-
-
-def test_row_seven_names_passage_cheating() -> None:
-    assert gate.MUTANT_COUNT == 15
-    assert gate.MUTANT_ROSTER[-1] == "M15 the passage carries a sentence the concept file does not"
-
-
 def test_the_synthetic_corpus_is_pinned_like_the_sets(tmp_path: Path) -> None:
     assert gate.specs_digest() == gate.SPECS_SHA256
     tuned = dict(gate.SPECS)

tools/okf_retrieval_gate.py

@@ -434,190 +434,6 @@ BUDGET = BundleSpec(
     ),
 )
 
-# --- three fixtures, one per mechanism the default ranking runs ---------------
-#
-# Until 2026-09-22 row 7 left three mutants standing (M06, M07, M10): every
-# synthetic concept was short and opened with its own title, so the passage
-# signal, the title/path weight and the fusion constant never DECIDED a
-# delivery here, and switching any of them off moved 0 ranks. Each bundle below
-# is built so that exactly one of them does. None of them is a tuning of the
-# ranker: the corpus is pinned (`SPECS_SHA256`) and `src/` is untouched.
-
-_NOTE = "Styret gjennomgaar notatet og foerer det inn i arkivet. Sekretaeren sender kopi. "
-
-#: THE PASSAGE SIGNAL. One long concept answers in ONE window of its body; ten
-#: short concepts carry the question's words in their TITLES and none in their
-#: bodies. The field signal reads ten title-weighted matches in short documents
-#: above one long body, so only the passage signal -- the best WINDOW, not the
-#: whole concept -- puts the gold first. Remove the body windows (M06) and the
-#: passage signal reads titles alone, where the gold has none of the words.
-PASSAGE = BundleSpec(
-    "retrieval-passage",
-    (
-        DocumentSpec(
-            "aarbok",
-            "aarbok.md",
-            (
-                ConceptSpec(
-                    "kapittel-tre",
-                    "Kapittel tre i aarboka",
-                    _NOTE * 15
-                    + "Varmekablene i taket kontrolleres av vaktmesteren hver oktober. "
-                    + _NOTE * 15,
-                ),
-            ),
-        ),
-        *(
-            DocumentSpec(
-                f"rundskriv-{number:02d}",
-                f"rundskriv-{number:02d}.md",
-                (
-                    ConceptSpec(
-                        f"skriv-{number:02d}",
-                        f"Varmekablene i taket, skriv {number:02d}",
-                        "Skrivet er sendt ut og arkivert.",
-                    ),
-                ),
-            )
-            for number in range(1, 11)
-        ),
-    ),
-)
-
-#: THE TITLE/PATH WEIGHT. The gold is named by its PATH alone -- the question's
-#: `kanopadling` is its directory and its source file and occurs in no body --
-#: while ten decoys carry the question's other word more densely than the gold
-#: does, one fewer time each. The path weight puts the gold first in the field
-#: signal, which lifts it into k (rank 4 at `k` = 6). Weigh no title and no path
-#: (M07) and both signals read bodies only, where the decoys outrank it and it
-#: falls out of k.
-PATH = BundleSpec(
-    "retrieval-path",
-    (
-        DocumentSpec(
-            "kanopadling",
-            "kanopadling.md",
-            (ConceptSpec("regel", "Regel om vester", "Vester brukes paa vannet."),),
-        ),
-        *(
-            DocumentSpec(
-                f"turnotat-{number:02d}",
-                f"turnotat-{number:02d}.md",
-                (
-                    ConceptSpec(
-                        f"notat-{number:02d}",
-                        f"Turnotat {number:02d}",
-                        " ".join(["Vester henger i boden."] * (11 - number))
-                        + " Notatet er arkivert.",
-                    ),
-                ),
-            )
-            for number in range(1, 11)
-        ),
-    ),
-)
-
-_FUSION_NOTE = "Styret gjennomgaar saken og sekretaeren arkiverer den. "
-
-#: THE FUSION CONSTANT. Reciprocal-rank fusion trades a concept with one very
-#: good rank against one with two middling ranks, and `RRF_K` sets the price.
-#: The gold is FIRST in the passage signal and 21st in the field signal (a long
-#: body, below ten short `isbading-*` path matches, nine longer ones and the
-#: decoy); the one decoy is 10th and 11th, a smaller rank SUM (19 against 20).
-#: A flattened fusion (M10, `RRF_K` = 10 000, where only the sum counts) puts
-#: the decoy first and `k` = 1 no longer reaches the gold. At the shipped
-#: `RRF_K` = 60 the gold leads, and measured over K in steps of 10 it keeps the
-#: lead through K = 180 and loses it at 190. The eight long log pages hold the
-#: decoy's passage rank at 10th and rank below the gold in both signals.
-FUSION = BundleSpec(
-    "retrieval-fusion",
-    (
-        DocumentSpec(
-            "badebok",
-            "badebok.md",
-            (
-                ConceptSpec(
-                    "kapittel",
-                    "Kapittel i badeboka",
-                    _FUSION_NOTE
-                    * 12
-                    + "Isbading ved brygga, isbading om morgenen, isbading med vakt, "
-                    "isbading hver dag. " + _FUSION_NOTE * 12,
-                ),
-            ),
-        ),
-        *(
-            DocumentSpec(
-                f"logg-{number:02d}",
-                f"logg-{number:02d}.md",
-                (
-                    ConceptSpec(
-                        "side",
-                        f"Loggside {number:02d}",
-                        _FUSION_NOTE * 16
-                        + "Isbading ved brygga, isbading om kvelden, isbading med vakt. "
-                        + _FUSION_NOTE * 16,
-                    ),
-                ),
-            )
-            for number in range(8)
-        ),
-        DocumentSpec(
-            "isbading-lapp-00",
-            "isbading-lapp-00.md",
-            (ConceptSpec("lapp", "Lapp 00", _FUSION_NOTE * 5 + "Isbading er tillatt."),),
-        ),
-        *(
-            DocumentSpec(
-                f"isbading-{number:02d}",
-                f"isbading-{number:02d}.md",
-                (ConceptSpec("oppslag", f"Oppslag {number:02d}", "Oppslaget er arkivert."),),
-            )
-            for number in range(10)
-        ),
-        *(
-            DocumentSpec(
-                f"isbading-arkiv-{number:02d}",
-                f"isbading-arkiv-{number:02d}.md",
-                (ConceptSpec("mappe", f"Mappe {number:02d}", _FUSION_NOTE * 10),),
-            )
-            for number in range(9)
-        ),
-    ),
-)
-
-_ARCHIVE_LINE = "Styret gjennomgaar notatet og foerer det inn i arkivet. Sekretaeren sender kopi."
-
-#: THE PASSAGE DELIVERY. Every concept above is shorter than
-#: `consume.PASSAGE_CHARS`, so no synthetic payload carried a passage and a
-#: mutant of one (M15) could not be felled. One concept of about 6 600
-#: characters: a heading ten lines in, the answer thirty lines below it, so the
-#: delivery is heading + `[...]` + span + `[...]` and the span carries the
-#: citation. Rows 1 and 6 read it as a hit only because the judge reads a
-#: passage as its exact reconstruction; M15 adds one sentence and fells both.
-DELIVERY = BundleSpec(
-    "retrieval-delivery",
-    (
-        DocumentSpec(
-            "husbok",
-            "husbok.md",
-            (
-                ConceptSpec(
-                    "drift",
-                    "Drift av huset",
-                    "\n".join(
-                        [_ARCHIVE_LINE] * 10
-                        + ["## Teknisk rom"]
-                        + [_ARCHIVE_LINE] * 30
-                        + ["Varmepumpa i kjelleren faar service av roerleggeren hvert aar."]
-                        + [_ARCHIVE_LINE] * 40
-                    ),
-                ),
-            ),
-        ),
-    ),
-)
-
 SPECS: Mapping[str, BundleSpec] = {
     "positive": POSITIVE,
     "miss": MISS,
@@ -625,10 +441,6 @@ SPECS: Mapping[str, BundleSpec] = {
     "budget": BUDGET,
     "lookup": LOOKUP,
     "quota": QUOTA,
-    "passage": PASSAGE,
-    "path": PATH,
-    "fusion": FUSION,
-    "delivery": DELIVERY,
 }
 
 
@@ -671,7 +483,7 @@ def specs_digest(specs: Mapping[str, BundleSpec] = SPECS) -> str:
 
 
 #: The synthetic corpus, pinned the way the sets are.
-SPECS_SHA256 = "089a6a9770c03c59fff2da22430e5f9aeb2b2374c49aed419bae99409a2a5cb9"
+SPECS_SHA256 = "23c447add9a58ee2e454ef5d5b92d5c3c97d441cd883d203aaf2f275dd2f68f9"
 
 
 def synthetic_bundles(root: Path, specs: Mapping[str, BundleSpec] = SPECS) -> dict[str, Path]:
@@ -836,8 +648,6 @@ SYNTHETIC_SETS: dict[str, str] = {
     "set-signals.json": "17d83f305a10af8dd2a45b72943c1285704d23ed074ecb549c05e5fac3e137e9",
     "set-quota.json": "61fda652719d7403ddf9701d50e914c46572a4fda77dc0336838695e18c498cf",
     "set-controls.json": "c2894656326e5a69ec7063fdc280e763910d20b4cbc2c0124f639283864ce506",
-    "set-mechanisms.json": "435ce620c30c94b0d151335883583520490482be2ade6797524ae928a9f1eab7",
-    "set-passage.json": "93b6de8ef7012c84516fe9aee560924d4b579669fb046e6eadc70dbf444eb627",
 }
 
 
@@ -1001,79 +811,6 @@ def _carries(text: str, quote: str) -> bool:
     return not quote or _flat(quote) in _flat(text)
 
 
-#: What class e says when a passage is not its own reconstruction.
-PASSAGE_NOT_RECONSTRUCTED = (
-    "the delivered passage is not its reconstruction from the bundle's bytes"
-)
-
-
-def passage_span(text: str, passage: object, body: str) -> str | None:
-    """The span a passage delivery carries, or None when `text` is not EXACTLY
-    what the bundle's bytes rebuild.
-
-    Since v1.1 C1 a long concept is delivered as `[heading]`, `[...]`, the
-    span, `[...]` (`consume.as_passage`), with `passage = {start, end, of}`.
-    Two traps PM measured 2026-09-22, both held here:
-
-    - **The offsets count in the DELIVERED body** (`ConceptView.body`), never
-      in the concept file: read in the file they land a frontmatter's length
-      off, and 0 of 12 real spans matched.
-    - **"The span occurs somewhere in the text" is not a check.** It accepts
-      an invented sentence beside the span. Every character of `text` must be
-      accounted for: the span is `body[start:end]` byte for byte, a marker
-      stands exactly where the span leaves text out and nowhere else, and the
-      one other line allowed is a heading line of the body ABOVE the span (or a
-      prefix of one -- `as_passage` cuts a long heading). WHICH heading is the
-      product's choice and is not re-derived here; that it is the bundle's
-      bytes is the guarantee.
-
-    The citation is then read in the span alone -- not in the heading, not in
-    the markers, and not across the seam between them, which is no sequence
-    the concept file holds.
-    """
-    if not isinstance(passage, Mapping):
-        return None
-    start, end, of = passage.get("start"), passage.get("end"), passage.get("of")
-    if not all(
-        isinstance(value, int) and not isinstance(value, bool) for value in (start, end, of)
-    ):
-        return None
-    assert isinstance(start, int) and isinstance(end, int)
-    if of != len(body) or not 0 <= start < end <= len(body):
-        return None
-    span = body[start:end]
-    tail = f"\n{consume.PASSAGE_ELISION}" if end < len(body) else ""
-    if not text.endswith(span + tail):
-        return None
-    head = text[: len(text) - len(span + tail)]
-    if start == 0:
-        return span if head == "" else None
-    marker = f"{consume.PASSAGE_ELISION}\n"
-    if head == marker:
-        return span
-    if not head.endswith(f"\n{marker}"):
-        return None
-    heading = head[: -len(f"\n{marker}")]
-    above = body[:start].split("\n")
-    if heading.startswith("#") and any(
-        line.startswith("#") and line.startswith(heading) for line in above
-    ):
-        return span
-    return None
-
-
-def _judged(excerpt: Mapping[str, object], body: str) -> tuple[str, bool, str]:
-    """(the text a citation is looked for in, whether it is the bundle's
-    bytes, the detail when it is not) for one delivered excerpt."""
-    text = str(excerpt.get("text", ""))
-    if "passage" in excerpt:
-        span = passage_span(text, excerpt["passage"], body)
-        if span is None:
-            return text, False, PASSAGE_NOT_RECONSTRUCTED
-        return span, True, ""
-    return text, _flat(text) == _flat(body), "the delivered text is not the bundle's bytes"
-
-
 def measure_units(bundle: Path, question: Question) -> list[Unit]:
     """One question, measured at the shipped defaults, plus the quota-off run
     that says what the truth of a withheld concept is.
@@ -1120,21 +857,18 @@ def measure_units(bundle: Path, question: Question) -> list[Unit]:
             for concept_id in holding
             if _carries(index.concepts[concept_id].body, fasit.quote)
         )
-        # A whole-body delivery is judged whole; a passage is judged as its
+        hit_ids = [
-        # exact reconstruction, and its citation is read in its span alone.
+            concept_id
-        judged = {
-            concept_id: _judged(delivered[concept_id], index.concepts[concept_id].body)
             for concept_id in holding
             if concept_id in delivered
-        }
+            and _carries(str(delivered[concept_id].get("text", "")), fasit.quote)
-        hit_ids = [
-            concept_id for concept_id, (text, _, _) in judged.items() if _carries(text, fasit.quote)
         ]
         # The payload SAYS it delivered this; the bundle says what it is.
         confirmed: bool | None = None
-        not_bytes = ""
         for concept_id in hit_ids:
-            _, confirmed, not_bytes = judged[concept_id]
+            confirmed = _flat(str(delivered[concept_id].get("text", ""))) == _flat(
+                index.concepts[concept_id].body
+            )
             if confirmed:
                 break
         # The concept this entry is really about: the one the bundle holds the
@@ -1164,7 +898,7 @@ def measure_units(bundle: Path, question: Question) -> list[Unit]:
                 else "no concept in the bundle answers to this name"
             )
         elif hit_ids and not confirmed:
-            klass, detail = "e", not_bytes
+            klass, detail = "e", "the delivered text is not the bundle's bytes"
         elif target in delivered:
             klass = "d"
             detail = "delivered without the citation" + (
@@ -1865,10 +1599,8 @@ class Mutant:
     expected_row: int
     patch: Callable[[], contextlib.AbstractContextManager[None]]
     #: Why this one may be invisible to a gate that judges DELIVERY. Written
-    #: for a mutant that survives, so a survivor is a statement about the
+    #: for the two that survive, so a survivor is a statement about the
-    #: mechanism and not a shrug. None does since 2026-09-22: the three that
+    #: mechanism and not a shrug.
-    #: carried a note (M06, M07, M10) each got a fixture that makes their
-    #: mechanism decide a delivery (`PASSAGE`, `PATH`, `FUSION`).
     note: str = ""
 
 
@@ -1955,25 +1687,6 @@ def _extend_delivered() -> contextlib.AbstractContextManager[None]:
     return _patched(delivered_text=mutant)
 
 
-def _extend_passage() -> contextlib.AbstractContextManager[None]:
-    """M14's shape for the delivery form v1.1 C1 added: the passage still
-    CARRIES the citation in its span, and one sentence at the span's end is not
-    the concept file's. A judge that asked only whether the span occurs
-    somewhere in the text would count it."""
-    original = consume.as_passage
-
-    def mutant(excerpt: dict[str, object], window: int) -> dict[str, object]:
-        out = original(excerpt, window)
-        if "passage" in out:
-            text = str(out["text"])
-            tail = f"\n{consume.PASSAGE_ELISION}"
-            cut = len(text) - len(tail) if text.endswith(tail) else len(text)
-            out["text"] = f"{text[:cut]} En setning som ikke staar i konseptfila.{text[cut:]}"
-        return out
-
-    return _patched(as_passage=mutant)
-
-
 def _drop_text_key() -> contextlib.AbstractContextManager[None]:
     original = consume.excerpt_for
 
@@ -2004,12 +1717,23 @@ MUTANTS: tuple[Mutant, ...] = (
     Mutant("M04 the ranking is reversed", 1, _reverse_scores),
     Mutant("M05 the source quota is removed", 3, lambda: _wrap_cut(source_quota=None)),
     Mutant(
-        "M06 the passage signal reads no body", 1, lambda: _patched_bm25(windows=lambda body: [])
+        "M06 the passage signal reads no body",
+        1,
+        lambda: _patched_bm25(windows=lambda body: []),
+        note=(
+            "the field signal still reads every body, and no synthetic concept is "
+            "long enough for its best window to decide a delivery"
+        ),
     ),
     Mutant(
         "M07 the field signal weighs no title and no path",
         1,
         lambda: _patched_bm25(TITLE_WEIGHT=0, PATH_WEIGHT=0),
+        note=(
+            "every synthetic body opens with its own title as a heading "
+            "(`build_bundle`), so the weight only re-weights words the body "
+            "already carries"
+        ),
     ),
     Mutant("M08 every token matches every token", 4, _every_term_everything),
     Mutant("M09 no stem, no prefix: equality only", 1, _equality_only),
@@ -2017,6 +1741,10 @@ MUTANTS: tuple[Mutant, ...] = (
         "M10 the fusion is flattened (bm25.RRF_K = 10 000)",
         1,
         lambda: _patched_bm25(RRF_K=10_000),
+        note=(
+            "over two signals K reorders only a concept whose two ranks lie far "
+            "apart against one whose ranks are close, and no fixture here holds that"
+        ),
     ),
     Mutant("M11 the cut takes the LAST k", 1, _last_k),
     Mutant("M12 the delivered text is truncated to 40 characters", 6, _truncate_delivered),
@@ -2024,7 +1752,6 @@ MUTANTS: tuple[Mutant, ...] = (
     Mutant(
         "M14 the delivered text carries a sentence the concept file does not", 6, _extend_delivered
     ),
-    Mutant("M15 the passage carries a sentence the concept file does not", 6, _extend_passage),
 )
 
 
@@ -2051,11 +1778,10 @@ MUTANT_ROSTER: tuple[str, ...] = (
     "M12 the delivered text is truncated to 40 characters",
     "M13 the excerpt carries no text",
     "M14 the delivered text carries a sentence the concept file does not",
-    "M15 the passage carries a sentence the concept file does not",
 )
 
 #: The roster's length, written as a number so appending is not one edit.
-MUTANT_COUNT = 15
+MUTANT_COUNT = 14
 
 
 def _score(rows: Sequence[Row]) -> dict[int, int]: