{
  "id": "BEN-2026-0002",
  "kind": "benchmark",
  "label": "AER-0 architecture-comparison suite (R1–R6)",
  "created_at": "2026-09-08",
  "updated_at": "2026-09-08",
  "values": {
    "eml_status": "EXPERIMENTAL",
    "eml_evidence_level": "E2",
    "eml_object_version": "0.1",
    "eml_canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0002/",
    "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": "Deterministic, executable comparisons that grow round by round: R1 — two facts (one stable, one changing at hours 8 and 16), eight queries over 17 simulated hours, baselines B1 stateless / B2 fixed 6-hour TTL / B3 memory + tools / B4 evented compound agent; R3 — scattered policy vs centralized application gate vs AER-ECT on provenance, stale-write, audit and dependency binding; R4 — policy-topology scaling over N ∈ {1, 4, 16, 64} callers × 6 rules; R5 — ten bypass scenarios across five threat layers; R6 — coherent full-DB forgery, anchor mutation, prefix truncation with/without a trusted head, fail-closed anchor, orphan anchor, adapter conformance.",
    "eml_summary_zh": "逐輪成長的決定性可執行比較：R1——兩個事實（一穩定、一在第 8 與 16 小時改變）、17 個模擬小時內 8 次查詢，基線 B1 無狀態／B2 固定 6 小時 TTL／B3 記憶 + 工具／B4 事件驅動複合 agent；R3——分散政策 vs 集中式應用 gate vs AER-ECT，比 provenance、stale write、audit 與依賴綁定；R4——N ∈ {1, 4, 16, 64} 個 caller × 6 條規則的政策拓撲縮放；R5——五個威脅層上的十種繞過情境；R6——連貫的整庫偽造、anchor 竄改、有／無可信 head 的前綴截斷、fail-closed anchor、孤兒 anchor、adapter 一致性。",
    "eml_label_zh": "AER-0 架構比較套件（R1–R6）",
    "eml_primary_domain": "Evaluation",
    "eml_domains": [
      "AI Architecture",
      "Agent Systems"
    ],
    "eml_program_id": "PRG-2026-0001",
    "eml_purpose": "Ask a narrower question each round: what remains distinct once the baseline is allowed to be as good as AER?",
    "eml_metrics": [
      "stale answers",
      "recomputations",
      "stable/volatile refreshes",
      "workflow reuse",
      "provenance/version-conflict witnesses",
      "policy sites, rule placements, blast radius, migration edits",
      "PREVENTED / OPEN_DETECTED / OPEN_UNDETECTED per scenario",
      "test counts"
    ],
    "eml_evaluation_protocol": "Baselines are strengthened deliberately (B4 in R1, centralized gate in R3) so ordinary mechanisms are not attributed to AER; every round states supported and not-measured claims separately.",
    "eml_limitations": [
      "Not a general-intelligence benchmark; no performance, cost, security-certification or production claim; the LangGraph round is source-grounded, not executed."
    ],
    "eml_authors": [
      "Neo.K (EveMissLab)"
    ],
    "eml_ai_collaborators": [
      "Sol (GPT-5.6, OpenAI ChatGPT)"
    ]
  },
  "canonical_url": "https://evemisslab.com/ai/benchmarks/BEN-2026-0002/",
  "json": "/ai/benchmarks/BEN-2026-0002/index.json",
  "relations": [
    {
      "id": "REL-2026-0089",
      "predicate": "evaluates",
      "source": "BEN-2026-0002",
      "target": "THY-2026-0006",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0090",
      "predicate": "evaluates",
      "source": "BEN-2026-0002",
      "target": "THY-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0100",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0001",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0106",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0002",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0117",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0003",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0128",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0004",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0138",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0005",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0143",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0006",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    },
    {
      "id": "REL-2026-0150",
      "predicate": "uses_benchmark",
      "source": "EXP-2026-0007",
      "target": "BEN-2026-0002",
      "status": "ACTIVE"
    }
  ],
  "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
  }
}