/**
 * corpus-v2.ts — SYNCED COPY of test/bench/recall-harness/corpus-v2.ts
 * (the flair recall-eval harness's eval instrument v2).
 *
 * flair-bench ships standalone (npx-able, no monorepo checkout required at
 * runtime), so it cannot import the harness's corpus at runtime from
 * test/bench/ — that directory is dev-only and excluded from the published
 * package. This file is a build-time copy kept faithful by
 * test/corpus-sync.test.ts, which deep-equals this file's exported CORPUS
 * and QUERIES against the live harness source on every `bun test` run
 * inside the monorepo checkout — any drift fails CI loudly. Regenerate with
 * `bun run sync:corpus` (packages/flair-bench/scripts/sync-corpus.mjs)
 * whenever the harness corpus changes.
 *
 * Below this header, content is byte-for-byte the harness's corpus-v2.ts —
 * see that file for the full design rationale (near-duplicate clusters,
 * cross-cluster lexical traps, durability/recency stress pairs).
 *
 * ORIGINAL HEADER (test/bench/recall-harness/corpus-v2.ts):
 *
 *  * corpus-v2.ts — eval instrument v2: a larger, harder synthetic corpus +
 * ground-truth query set for the isolated recall-eval harness
 * (test/bench/recall-harness/run.ts, --corpus v2).
 *
 * WHY THIS EXISTS (vs. corpus.ts / v1): v1 is 87 records / 30 queries. A
 * flair#504 Phase 2 prefix A/B on v1 measured a small regression (p@3
 * 0.967→0.933) that is, at N=30, just 1-2 queries shifting rank — not enough
 * queries for the instrument to tell "ship" from "park" apart from noise. v2
 * exists to have enough queries per "kind" (see QueryKind below) that a
 * kind-level delta is a real signal, not a coin flip. v2 does NOT replace v1
 * — v1's frozen numbers (README.md) stay reproducible verbatim by never
 * touching corpus.ts; v2 is additive and becomes the standing gate for
 * future embedding/scoring changes (larger N, same design principles).
 *
 * DESIGN — same three axes as v1, just wider:
 *   1. NEAR-DUPLICATE / ADJACENT DENSITY — every cluster below holds one or
 *      two pairs of records about the SAME narrow sub-topic from different
 *      angles (see each record's "Near-dup facet of X" note). A "hard" query
 *      targets the specific facet, with the sibling as the plausible
 *      rank-2/3 confusion.
 *   2. CROSS-CLUSTER LEXICAL "TRAP" PAIRS — three genuinely different-domain
 *      cluster pairs deliberately share one pivotal, ambiguous term used in
 *      a different sense in each domain, with high token overlap:
 *        - DBSTORE (database internals) ↔ FINOPS (finance operations): "transaction"
 *        - GITWF (git branching workflows) ↔ HORTIC (gardening/horticulture): "branch"
 *        - MUSICPROD (music production) ↔ SPORTAN (sports analytics): "score"
 *      Every record in a trap-pair cluster uses its cluster's sense of the
 *      shared term naturally and prominently (not shoehorned in for the
 *      trap alone) — the trap only works if the token overlap is real.
 *   3. VARIED DURABILITY + createdAt (recency) — 17 of the 30 clusters carry
 *      a deliberate "stress pair": one older, standard/persistent-durability
 *      CORRECT record vs. a same-topic, fresh (~2-4 day) permanent-durability
 *      DISTRACTOR sibling — the same composite-vs-raw discriminator
 *      mechanism v1 uses (see corpus.ts's header and flair#623). The
 *      remaining records in every cluster (stress or not) still spread
 *      naturally across all four durability levels and a wide age range
 *      (~4-100 days), not just the engineered stress pairs.
 *
 * 30 topic clusters, genuinely different domains (distributed systems,
 * medical scheduling, logistics, cooking, astronomy, legal contracts,
 * fitness, team process, home renovation, marine biology, typography,
 * database internals, finance ops, git workflow, horticulture, music
 * production, sports analytics, cloud infra, winemaking, ornithology,
 * carpentry, meteorology, chess, photography, aviation, insurance,
 * archaeology, perfumery, ceramics, linguistics), 9 records each = 270
 * records.
 *
 * ALL content below is authored synthetic prose — no real memories, no real
 * project/people/host/key names, nothing copied from ~/ops or any
 * production corpus. Every domain fact is invented-but-plausible, written
 * fresh for this file.
 *
 * GROUND TRUTH: identical convention to v1 (see corpus.ts's header) — every
 * query was written by hand against ONE specific record, then checked that
 * no other record in the corpus answers the query's literal question as
 * directly. See QueryKind below for what each kind tests.
 *
 * ageDays is relative to seed time (computed fresh by run.ts on every seed),
 * matching v1.
 */
export type Durability = "permanent" | "persistent" | "standard" | "ephemeral";
export interface CorpusRecord {
    /** Unique marker, e.g. "DISTSYS::1". Also used to derive the record's id. */
    marker: string;
    cluster: string;
    text: string;
    durability: Durability;
    /** Age in days at seed time (createdAt = now - ageDays). */
    ageDays: number;
    /** Free-form note on why this record's durability/age was chosen. */
    note?: string;
}
export type QueryKind = "stress" | "trap" | "hard" | "clean";
export interface GroundTruthQuery {
    q: string;
    expectMarker: string;
    kind: QueryKind;
    /** What this query is specifically testing, and against which distractor. */
    note: string;
}
export declare const CORPUS: CorpusRecord[];
export declare const QUERIES: GroundTruthQuery[];