# Stage 142: Room-A Copula Inspiration Spec (aq142_extract_cleanroom_inspiration_copula / DB-UNIT-12)

Extracts anonymous mathematical structure, Spearman rank-correlation copulas, missingness rates, and invariants in Room A without exporting raw text or rows.

- Atomic micro-queue: `aq142_extract_cleanroom_inspiration_copula` (visibility: `public_commons`)
- Backing database unit: `DB-UNIT-12` (`Context Interrogation, Persona Matrix & Problem-Situation Core`)
- Database cell: `entities-db.teleon.dev` (`teleon_core.acquired_observations`, `teleon_core.interrogation_personas_and_rubrics`, `teleon_core.problem_situations`)
- Claim row hydration: `single_self_contained_flat_task_row` (100% context inline, normalized writeback)
- Track 2 Sister queue (`SISTER-12`): `sq12-improve-interrogation-queue.teleon.dev` (Add sharper interrogation questions, expand domain personas, and prioritize high-leverage problem scenarios.)
- Lanes: Spearman Rank Copula, Marginal Quantiles, Zero Raw Verbatim

## Execution engines & AI Agent freedom contract

- **Deterministic (0 model calls)**: `interrogation_template_and_gap_compiler_v1` (Empirical quantile, missingness & Spearman correlation extractor (0 calls))
- **Hybrid (<=1 model call)**: `persona_scenario_problemizer_hybrid_v1`
- **AI Agent & Bot Fleet (1..6 calls)**: `bot_fleet_persona_interrogator_v1` (Domain-invariant & competition-mechanic structural analyst)
  - Contract: **Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions**

## Database invariants

- Partial problem situations remain valid when opportunity, context, and parent observation digests are recorded.
- Every bot-generated interrogation row records exact bot_harness, bot_version, and llm_model metadata.

## External & internal bot fleet actions

- Compute feature distributions, rank correlations, class imbalance, and monotonic invariants
- Strip original column names, prose snippets, and source identifiers at the Chinese Wall
- Emit a self-contained mathematical blueprint ready for clean Room-B twin synthesis

## Sister self-tuning areas

- Add domain personas and who/what/where/when/why question sets (DIM-02, DIM-04)
- Tune urgency weights across humanitarian SDG, competition ML, math, and science labels (DIM-01)
- Compile recurring structured-observation anomaly checks into deterministic code_blocks (DIM-03, DIM-06)