/** * @copyright Sister Software * @license AGPL-3.0 * @author Teffen Ellis, et al. * * `intersection` recipe, the real-pair intersection training source. * * Street pairs are real. The extraction matches the eval builder * (`scripts/eval/build-intersection-real.ts`). A node where two road edges (mtfcc S1*) with * distinct FULLNAMEs meet is a real crossing. Real pairs avoid teaching fake street-street * co-occurrences. * * Leakage policy (mirrors the affix recipe's VT discipline): * * - train counties: Cook IL (grid city) + Morris NJ (suburb). * - golden (`--golden`) county: Washington VT (rural) only, the corpus defaultHoldout state. * - Every crossing in data/eval/external/intersection-real.jsonl is excluded from both modes, by node * id and by order-insensitive name pair (the eval shares all three counties). * * Junction-format variety includes padded and tight `&` and `/`, `and`, `at`, `@`, and the * leading phrases `corner of` and `intersection of`, crossed with tails (bare / `, ST` / `, ST ZIP` / * `, City, ST [ZIP]`) and case variants. ZIPs are the crossing's own tiger edge zipl (real). The * locality tail comes from the OA Cook-county ZIP→city majority map. * * Audit: every emitted row is label-checked on the RAW surface via the char-offset span triple. Any * violation fails the build (throws). A JSON audit report lands next to the output. * * External inputs (`--edges-dir` and opts.edgesDir, both already on disk. Do not re-download): * * - /tl_2023_{17031,34027,50023}_edges.shp (unzipped tiger 2023 edges. default * `$MAILWOMAN_DATA_ROOT/census/tiger2023-edges`, where `mailwoman situs interpolation` puts them) * - `$MAILWOMAN_DATA_ROOT/oa-cache/us__il__cook.zip` (ZIP→city tails) */ import { type CorpusRecipe } from "#recipes/scaffold"; /** * Recipe registered with the corpus builder. * * See the file header for the parse behavior it exercises. * See `description` below for the generated surface form. */ export declare const intersectionRecipe: CorpusRecipe; //# sourceMappingURL=intersection.d.ts.map