/**
 * @copyright Sister Software
 * @license AGPL-3.0
 * @author Teffen Ellis, et al.
 *
 *   `fr-fragment` slice recipe (#727 T2) — the HOUSE-NUMBER-LICENCE change.
 *
 *   The measured problem (T1c, `2026-07-16-t1c-fragment-board-verdict.md`): the shipped model scores
 *   **0.925** on `<n> Rue X` and **0.215** on `Rue X`. Same streets, same model; the only difference
 *   is a leading number. It has learned that a house number LICENSES a street reading at all — strip
 *   it and a designator-led phrase parses as a locality, designator included:
 *
 *   ```
 *   "Rue Montmartre"        -> locality="Rue Montmartre"
 *   "Allee Poque"           -> locality="Allee Poque"
 *   ```
 *
 *   `Rue` can only mean street in French. The model is not mislabelling an ambiguous toponym; it is
 *   mislabelling `Rue`.
 *
 *   WHY THE EXISTING RECIPE DOESN'T COVER THIS. {@link frBareStreetRecipe} (#251) mints
 *   `<n> Rue <name>, <City>` — the bare COMMA form, no postcode. It targets postcode-anchoring
 *   imbalance, and every row it emits still carries a house number AND a locality. It cannot teach
 *   the class above, because it never shows the model a street standing alone.
 *
 *   WHAT THIS MINTS. Five street forms — the first three carry NO house number and NO locality, which
 *   is the whole point — plus the counter-distribution:
 *
 *   1. `bare-street`         "Rue Montmartre"
 *   2. `street-particle`     "Rue de la Paix"
 *   3. `date-name`           "Allee du 11 Novembre 1918"
 *   4. `street-housenumber`  "12 Rue Montmartre"     — the anchor, so the licence isn't UNLEARNED
 *   5. `alnum-housenumber`   "12 bis Rue Montmartre"
 *   6. `bare-locality`       "Mery-sur-Oise"         — NEGATIVE: a bare toponym that IS a locality
 *
 *   The **admin/street homonym** class (`Rue de Rome`) is deliberately NOT a separate form. Homonym
 *   streets are already in the register and fall into 1–3 naturally; there is nothing different to
 *   teach about them, because the lesson is identical — the designator makes it a street. The
 *   fragment board scores them separately (they need measuring, not minting), and the recipe would
 *   need a second pass over the commune set to label them, buying a `synth_method` string and no
 *   training signal.
 *
 *   FORM 7 IS NOT OPTIONAL. T1c's standing prediction: the board's `bare-locality` cell reads 0.980
 *   for the WRONG REASON — the model calls everything without a house number a locality, and on bare
 *   localities that is accidentally right. Teach bare streets alone and the model has every incentive
 *   to flip that default rather than learn the distinction, trading a 0.215 for a 0.980. The slice
 *   must show BOTH bare forms so the discriminating evidence is the designator, which is the only
 *   thing that actually distinguishes them. This is the same counter-distribution principle
 *   {@link noStreetRecipe} established after synth-street pushed the model into "decompose mode".
 *
 *   SPLIT. `--exclude-surfaces` takes the fragment board's reserved surface list
 *   (`mailwoman/eval-harness/fixtures/ban-fragments-fr.surfaces.txt`). Every listed surface is
 *   skipped — source-disjoint by normalized street SURFACE, never by record row. Row-disjoint leaks
 *   the surface across the boundary and measures memorization of `Rue de Rivoli` while claiming
 *   generalization to unseen streets. The recipe REFUSES to run without the list rather than
 *   silently minting a contaminated slice.
 *
 *   MIX. The slice is ~145K rows off a 120K-tuple draw; the intended corpus mix is **5–10%**, set at
 *   assembly time by slice weight rather than by row count. Keep the cap: a slice that fixes fragments
 *   by degrading full addresses has moved the failure, not fixed it — which is what
 *   `street-housenumber` / `alnum-housenumber` on the fragment board and the global parity floor are
 *   there to catch. `date-name` is ~0.5% of the slice because BAN only holds ~1,418 date-name streets
 *   after filtering and the tuple extractor already takes every one; if that class needs more, the
 *   change is slice weight, not invented data.
 *
 *   ⚠ Convention loss-mask: like {@link frBareStreetRecipe}, this recipe TEACHES FR `street_prefix`.
 *   The conventions loss-mask forbids it for FR and will `-inf` these gold labels (the v1.6.0 ~7M-loss
 *   blow-up). Disable that mask for any run including this slice.
 */
import { type CorpusRecipe } from "#recipes/scaffold";
export declare function frTitleCase(value: string): string;
/**
 * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
 * and `description` below for the surface form it generates.
 */
export declare const frFragmentRecipe: CorpusRecipe;
//# sourceMappingURL=fragment.d.ts.map