{
  "section": "programs",
  "kind": "program",
  "canonical": "https://evemisslab.com/ai/programs/",
  "count": 2,
  "records": [
    {
      "id": "PRG-2026-0001",
      "kind": "program",
      "label": "Adaptive Epistemic Systems",
      "created_at": "2026-09-07",
      "updated_at": "2026-09-09",
      "values": {
        "eml_status": "ACTIVE",
        "eml_evidence_level": "E2",
        "eml_object_version": "0.1",
        "eml_canonical_url": "https://evemisslab.com/ai/programs/PRG-2026-0001/",
        "eml_provenance": {
          "source": "EveMissLab research collection: Adaptive Epistemic Systems (真本體論13)",
          "extracted_by": "Splice (Claude Code), reading the canonical UTF-8 sources and each lab's own result reports",
          "extracted_at": "2026-09-11",
          "generator": "tools/extract_aes/extract.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"
        },
        "eml_summary": "A research program that derives an AI runtime from first principles — world knowledge changes at heterogeneous rates, natural language is a rendering rather than the canonical state, capability must be remembered and reused, algorithm and compute substrate are separate — and then forces the derivation into executable reality: the AER-0 reference runtime with six architecture-comparison rounds, and the PACC micro-lab on whether non-probabilistic primitives converge to probability-like structure.",
        "eml_summary_zh": "從第一原理推導 AI runtime 的長期研究線：世界知識以不同速率變化、自然語言是 rendering 而非 canonical state、能力必須被記憶與重用、算法與計算載體分離；然後把推導結果逼進可執行的現實——AER-0 參考 runtime 與六輪架構比較，以及檢驗非概率 primitive 是否收斂到概率表象的 PACC 微型實驗室。",
        "eml_label_zh": "自適應世界狀態系統的第一原理框架",
        "eml_limitations": [
          "Everything measured so far is synthetic data plus theoretical reasoning, or a deterministic scenario in a reference runtime. Until a real hybrid model exists, an inference is only an inference: theoretically possible is not actually possible."
        ],
        "eml_goals": [
          "Derive an adaptive world-state architecture without starting from existing AI technology names, then test whether its differences survive implementation.",
          "Decide, falsifiably, between Distinct Advantage, Operational Convergence, Behavioral Equivalence Only, Inconclusive and Architecture Worse.",
          "Test the Probabilistic Appearance Convergence Conjecture (PACC) in fully observable micro-environments before touching language models."
        ],
        "eml_open_questions": [
          "PACC-A (architecture attractor) is not closed: only two independent convergent families exist under the preregistered redundancy rule.",
          "Reverse chart transport in the PACC atlas carries a persistent destination bias that neither a bounded quadratic transition nor a base-point residual field explains (v0.12–v0.13); v0.14 tests a sign-free residual subspace.",
          "AER-0 has no executable cross-runtime comparison yet: LangGraph could not be installed in the comparison environment (R2), and R7 (independent witness, transparency proof, signer rotation) is not started.",
          "The real-language-model PACC A/B/C benchmark has a validated harness but has never been executed with a real model."
        ],
        "eml_milestones": [
          "Adaptive Epistemic Systems Series papers 01–11 complete (canonical UTF-8 sources, SHA-256 manifest).",
          "Adaptive Epistemic AI Runtime technical whitepaper v0.1 with schemas, pseudocode and the AER-0 roadmap.",
          "AER-0 MVP v0.1 (Python + SQLite, 25 tests) and comparison rounds R1–R6 (79 tests at R6).",
          "PACC conjecture paper (2026-09-08) and PACC-Lab v0.1–v0.13.",
          "PACC-LLM Hybrid Lab v0.1 (synthetic A/B/C) and v0.2 (real-LLM harness, not yet executed)."
        ],
        "eml_authors": [
          "Neo.K (EveMissLab)"
        ],
        "eml_ai_collaborators": [
          "Sol (GPT-5.6, OpenAI ChatGPT)"
        ]
      },
      "canonical_url": "https://evemisslab.com/ai/programs/PRG-2026-0001/",
      "json": "/ai/programs/PRG-2026-0001/index.json"
    },
    {
      "id": "PRG-2026-0101",
      "kind": "program",
      "label": "Intelligence Physical Metrology (IPM)",
      "created_at": "2026-09-02",
      "updated_at": "2026-09-07",
      "values": {
        "eml_status": "ACTIVE",
        "eml_evidence_level": "E2",
        "eml_object_version": "0.1",
        "eml_canonical_url": "https://evemisslab.com/ai/programs/PRG-2026-0101/",
        "eml_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"
        },
        "eml_summary": "A research program that asks not how smart an AI is but what one answer costs a physical system: how many user turns, generation trajectories and hidden loops it took, how much effective semantic work was done, how much energy and computational spacetime was occupied, how much external scaffolding was leaned on, and how much verifiable quality came back. Ten theoretical papers (2026-09-02) define the measurement objects — task, quality, semantic work, physical computation, scaffolding capability, measurement metadata — and five falsifiable propositions; the v0.2 experimental protocol (Experiment A, single-pass vs scaffolded) is instantiated as the XA-02…XA-06L instrument packages and was executed once on a local 9B model.",
        "eml_summary_zh": "這個研究計畫問的不是「AI 有幾分聰明」，而是一個答案讓物理系統付出了什麼：花了幾次使用者回合、幾條生成軌跡、幾層隱藏 LOOP，做了多少有效語意工作，占用多少能量與計算時空，依賴多少外部鷹架，最後換回多少可驗證品質。十篇理論論文（2026-09-02）定義了測量物件——任務、品質、語意工作、物理計算、鷹架能力、測量詮釋資料——與五個可證偽命題；v0.2 實驗協定（Experiment A：single-pass vs scaffolded）落實為 XA-02…XA-06L 儀器套件，並在本地 9B 模型上執行過一次。",
        "eml_label_zh": "智能的物理計量（IPM）",
        "eml_primary_domain": "Evaluation",
        "eml_domains": [
          "Computation",
          "Cognitive Science",
          "AI Architecture"
        ],
        "eml_goals": [
          "Replace token, FLOP, benchmark score and 'one turn' as units of intelligence with a typed event 𝔍_IPM = (task, quality, semantic work, physical computation, scaffolding, metadata).",
          "Measure the relation physical computation → effective semantic work → verifiable quality, and compare systems on a Pareto frontier instead of a single score.",
          "Put the five falsifiable propositions — token hypothesis, FLOPs sufficiency, binary burden, scaffolding separation, semantic intermediate utility — in front of experiments in the order A → D → B → C → E.",
          "Publish under the IPM Minimum Reporting Standard: boundary, energy type, hidden work, uncertainty and measurement grade on every number."
        ],
        "eml_milestones": [
          "2026-09-02: EML-IPM v0.1 theoretical series complete, 10/10 papers with a SHA-256 manifest; canonical index with unified notation and the v0.2 experimental entry point.",
          "2026-09-02: Experiment A protocol (EML-IPM-XA-01 v0.1, READY FOR PILOT).",
          "2026-09-03: instrument packages XA-02 (30-task pack), XA-03 (telemetry logger), XA-04 (A0→A5 runner), XA-05 (36-trial synthetic smoke gate), XA-06 (real-model pilot gate), XA-06L (local execution handoff).",
          "2026-09-03: first real-model pilot on a local Qwythos-9B-v2 — 36 trials, sealed REAL_MODEL_PILOT_INCOMPLETE (33/36 complete).",
          "2026-09-07: diagnostic analysis of the pilot with seven instrument revisions required before XA-07."
        ],
        "eml_open_questions": [
          "μI has no operational identification yet (Experiment C); the series itself says μI must pass a predictive/explanatory utility test or be revised or eliminated.",
          "The pilot's quality axis measured output-format compliance for two of three tasks; task semantic quality, output-contract compliance, system completion reliability and verifier reliability have to be separated before scaling.",
          "Same-model verifier serialization failed in 3 of 18 verifier trials; candidates abandoned on abort are not yet accounted; telemetry sampling costs about 24 % of trial wall time.",
          "CODE tasks have no measured quality until the pilot runs inside a disposable sandbox with code evaluation enabled.",
          "Experiments B, C, D and E are declared, not run."
        ],
        "eml_authors": [
          "Neo.K (EveMissLab)"
        ],
        "eml_ai_collaborators": [
          "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)"
        ]
      },
      "canonical_url": "https://evemisslab.com/ai/programs/PRG-2026-0101/",
      "json": "/ai/programs/PRG-2026-0101/index.json"
    }
  ],
  "snapshot": {
    "snapshot_id": "AI-SNAPSHOT-v0.1-fe85b9694a45",
    "created_at": "2026-09-11T05:00:27Z",
    "format_version": "0.1",
    "sedb_baseline": "v0.4B contract; static source content/ai/",
    "generator_version": "evemisslab-com ai_research 0.1",
    "object_count": 124,
    "relation_count": 499,
    "artifact_count": 58
  }
}