SystemSYS-2026-0103v0.1

XA-06 — real-model pilot gate

Puts a real model inside the validated XA-01→XA-04 instrument: preflight (one isolated MATH-003/A0 trial through provider, XA-03 and XA-02), the canonical 36-trial matrix (MATH-003, CODE-001, CON-003 × A0…A5 × 2 replicates), gate verification and analysis. Frozen temperature / top-p / seed, the A0/A1 generation-budget multiplier forwarded into the token budget, a calculator tool contract injected only for A4/A5 generator requests, disabled code evaluation treated as quality-unavailable rather than measured zero, and the rule that engineering validation can never be promoted to pilot completion: 'no real model run, no real model claim'. Valid real outcomes explicitly include A0 = A5, A3 < A2, A5 < A0 and SSR = 1. 20 tests; the package itself contains no pilot result (status READY_FOR_REAL_MODEL).

Research status: STABLE the current conclusions are relatively stable
Evidence level: E2 Controlled experiment
Version: 0.1
Updated: 2026-09-03
Created: 2026-09-03
Domain: Evaluation
Program: PRG-2026-0101 Intelligence Physical Metrology (IPM)
Authors: Neo.K (EveMissLab)
AI collaborators: Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)

Purpose

purpose: A gate whose only way to say REAL_MODEL_PILOT_COMPLETE is 36 real-provider terminal trials that pass integrity and protocol checks — without requiring scaffolding to help.

Architecture

architecture: config (provider modes: local OpenAI-compatible / local command / cloud OpenAI-compatible with env-referenced secrets) → preflight → run_real_pilot (fresh provider per trial, XA-04 TrialExecutor, XA-03 spans) → verify_gate → analyze (condition means, SSR/SDR/SCM, marginal yield, physical by condition, protocol compliance, quality availability) → report.

Repositories and sites

documentation: README.md, SPEC.md, STATUS.json, validation_report.json inside the package

Recorded fields

tags: EML-IPM-XA-06
v0.1
READY_FOR_REAL_MODEL

Relations

Source	Relation	Target	Status	ID
`SYS-2026-0103` XA-06 — real-model pilot gate	`implements`	`THY-2026-0109` Scaffolding capability record: SSR, SDR, SCM and the ablation ladder	`ACTIVE`	`REL-2026-0455`
`SYS-2026-0103` XA-06 — real-model pilot gate	`supports`	`RES-2026-0103` Capability line — how much intelligence remains without the loop, and the unified intelligence event	`ACTIVE`	`REL-2026-0456`
`SYS-2026-0103` XA-06 — real-model pilot gate	`released_as`	`ART-2026-0117` EML-IPM-XA-06 v0.1 — real-model pilot gate (READY_FOR_REAL_MODEL, no pilot result inside) `artifact://evemisslab/intelligence-physical-metrology/IPM_v0.2_XA06_RealModel_Pilot_Gate_v0.1.zip`	`ACTIVE`	`REL-2026-0457`
`SYS-2026-0104` XA-06L — local real-model execution handoff pack	`extends`	`SYS-2026-0103` XA-06 — real-model pilot gate	`ACTIVE`	`REL-2026-0458`
`EXP-2026-0103` XA-06 first real-model pilot — Qwythos-9B-v2 on the A0→A5 ladder (36 trials, 2026-09-03)	`runs_on`	`SYS-2026-0103` XA-06 — real-model pilot gate	`ACTIVE`	`REL-2026-0477`

History and provenance

Canonical URL

https://evemisslab.com/ai/systems/SYS-2026-0103/

Machine-readable

/ai/systems/SYS-2026-0103/index.json

Snapshot

AI-SNAPSHOT-v0.1-fe85b9694a45

Provenance

source: EveMissLab research collection: Intelligence Physical Metrology (真本體論13)
extracted_by: Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports
extracted_at: 2026-09-11
generator: tools/extract_all.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports