Previous: 144 Domain Situation Context Skin Next: 146 Score 256D Pattern Tensor

Stage 145aq145_verify_zero_overlap_and_realism_gateDB-UNIT-03Confusion Diagnostics & Card Disambiguation Core

Zero-Overlap & Realism Gate

Atomic flat-row micro-queue with 0-call slot and 5-role pod.

Audits synthetic twins and rewritten contexts for 5-gram shingle overlap, residual PII, and statistical realism fidelity before publication.

/components/verify_zero_overlap_and_realism_gate.json /components/verify_zero_overlap_and_realism_gate.md Open in Queue Commons

Inputs (Flat Row)

Room-B synthetic twin & prose
Shingle digest baseline
Copula target matrix

Atomic Queue & Lanes

aq145_verify_zero_overlap_and_realism_gate
queues-db.teleon.dev
5-Gram Shingle <=0.02
Zero PII Check
Realism Fidelity >=85

Execution Modes & Agent Freedom

Deterministic (0 calls): schema_mismatch_rule_extractor_v1 (5-gram Jaccard overlap scanner, PII verifier & copula drift scorer (0 calls))
Hybrid (<=1 call): contrast_pair_card_rewriter_v1
AI Agent (1..6): multi_trace_root_cause_investigator_v1 (Adversarial memorization & copyright-similarity red-teamer; Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions)

Outputs (Table Merge)

Clean-room publication clearance verdict
Realism fidelity score >=85

Modular 6-layer envelope & 0..32 Kleisli onion middlelayers (DB substrates exempt)

Inbound and outbound calls traverse versioned envelope layers and composable Kleisli middlelayers before reaching the swappable engine slot, while backing database kernels enforce 0 inline agent wrapper steps.

1. frustration_avoidance
2. flexible_pointer_or_slice_carrier
3. thp_schema_and_version_handshake
4. surface_account_and_ring_entitlement
5. idempotent_effect_journal_and_tracking
6. preflight_self_repair_and_zero_call_check
7. 0..32 Kleisli steps (shims / budget deadlines / secret scrub)
8. slot.aq145_verify_zero_overlap_and_realism_gate (Native | Pinned OSS | Wasm)
ACID DB Core: 0 agent wrapper steps

5-role component managing pod & engine-slot twins

0-Call Slot (R1_DET_ENGINE): Executes SQL, BM25F/Roaring, AST, or fuel-metered Wasm adapters behind a fixed typed engine_slot/v1, pairing pinned upstream OSS adapters with clean Teleon-native twins.
Solver+OpenSearch (R2_PRIMARY_SOLVER): Runs under Instructions + Resources + Freedom to search for new resources and new ways not bound by instructions on 1 self-contained depth-1 flat task row per lease.
Split-Supervisor (R3_QUEUE_SUPERVISOR): Watches queue depth, stalls, and context horizons; explodes oversized tasks into wave-ordered flat subtask rows while preserving the original parent intact for rollup verification and long-horizon benchmarking.
Repair+Shim (R4_DIAGNOSTIC_REPAIR): Reviews whether the edge contract itself failed before mutating code (LE-CONTRACT-002), repairs lease timeouts and schema mismatches, and synthesizes 0..32-step middlelayer shims.
CPOP+Distill (R5_VERIFIER_DISTILLER): Grades outputs across an independent model family (reviewer != producer) and distills recurring high-cost agent wins into 0-call deterministic Sister code.

Parent-preserving supervision, catch-all & optional SCD2 packs

Supervisor split (aq41): Oversized or stalled tasks split into wave-ordered subtask rows while keeping subdivided_parent intact for rollup verification and direct long-horizon benchmarks.
Optional SCD Type 2 packs (Store S12): Versioned pack_sk rows (valid_from_utc, valid_to_utc, is_current, edited_by) supply optional locales, settings, instructions, suggestion paths, and tools across bare_baseline, pre_materialized_flat, and on_demand_claim_hydrated modes.
Flexible carriers: inline_object, swhid_cas_pointer, http_206_byte_slice, d1_row_cursor, signed_r2_uri

Normalized tables, invariants & 1 flat task row

Cell host: queues-db.teleon.dev
Backlog table: teleon_core.confusion_repair_todo_backlog
Hydration: Normalized supporting tables join server-side into 1 flat row on claim
teleon_core.agent_confusion_incidents
teleon_core.disambiguation_patches
teleon_core.negative_constraint_rules

Every confusion patch must include a deterministic regression probe reproducing the prior failure.

Atomic micro-queue & Track 2 Sister objective

Atomic queue: aq145_verify_zero_overlap_and_realism_gate via q02-confusion-queue.teleon.dev
Track 2 Sister (SISTER-03): sq03-improve-confusion-queue.teleon.dev
Sister objective: Discover new confusion aspects, sharpen agent consumption formatting, and automate recurring repairs.

host:cleanroom_teleon_devstore:S33gate:overlap_le_2pct_realism_ge_85

Bot & harness fleet actions (Codex, Claude Code, ChatGPT, Dots, Meta Muse, GrokBot)

Block promotion if 5-gram shingle overlap exceeds 0.02 or any PII token remains unredacted
Verify marginal distributions and rank-correlation matrices stay within >=85 realism fidelity
Stamp SWHID clean-room provenance certificates on approved benchmark twins

Sister self-tuning areas & HTTP queue submission

Add new diagnostic aspects for cross-model tool-call quirks
Tune negative-constraint formatting density for smaller local models (Gemma 4)
Convert recurring confusion fixes into deterministic lint code_blocks

# Zero-auth claim 1 flat-hydrated task row from this atomic micro-queue:
curl -sS "https://router.teleon.dev/v1/claim?agent=meta-muse&atomic_queue_id=aq145_verify_zero_overlap_and_realism_gate"
# Or enqueue a task directly onto this atomic micro-queue:
curl -sS https://queues.teleon.dev/v1/queues/submit \
  -H "Content-Type: application/json" \
  -d '{"atomic_queue_id":"aq145_verify_zero_overlap_and_realism_gate","db_unit_id":"DB-UNIT-03","title":"Task for verify_zero_overlap_and_realism_gate"}'