{ "id": "EXP-2026-0101", "kind": "experiment", "label": "Experiment A — single-pass vs scaffolded controlled measurement (protocol v0.1)", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "ACTIVE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/experiments/EXP-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": "The first v0.2 experiment: for one model and a fixed task set, climb the scaffold ladder A0 native single pass → A1 extended trajectory → A2 multi-sample → A3 verifier → A4 deterministic local tools → A5 bounded full agentic loop, recording quality and physical cost at every level to obtain a scaffolding response curve, SSR/SDR, scaffold cost multipliers and marginal yields. Five hypotheses (H1 gain exists, H2 gain has physical cost, H3 marginal yield is non-constant, H4 native and system capability are distinguishable, H5 models have different scaffolding profiles), pre-registered quality projections, initial-information equality across A0–A3, budget caps, n = 5 pilot / 20 formal replicates, failure classification and the rule that a null result is not an experiment failure. Status READY FOR PILOT; the thirty-task run itself has not been executed — only the three-task instrument gates below.", "eml_summary_zh": "第一個 v0.2 實驗：對同一模型與固定任務集，沿鷹架階梯 A0 原生單次 → A1 放大軌跡 → A2 多樣本 → A3 驗證器 → A4 確定性本地工具 → A5 有界完整 agentic 迴圈往上爬，每一級同時記品質與物理成本，得出鷹架響應曲線、SSR/SDR、鷹架成本倍率與邊際產率。五個假說（H1 增益存在、H2 增益有物理成本、H3 邊際產率非常數、H4 原生與系統能力可區分、H5 不同模型有不同鷹架剖面）、預先登記的品質投影、A0–A3 初始資訊相等、預算上限、pilot n = 5／正式 n = 20 次重複、失敗分類，以及「null 結果不是實驗失敗」的規則。狀態 READY FOR PILOT；三十題的正式執行尚未進行——只跑過下面的三題儀器閘。", "eml_label_zh": "Experiment A——單次智能與鷹架增益的受控實驗協定 v0.1", "eml_primary_domain": "Evaluation", "eml_domains": [ "Agent Systems" ], "eml_program_id": "PRG-2026-0101", "eml_data_basis": "NOT RUN", "eml_hypothesis": "H1 Q_A5 > Q_A0 for at least some non-trivial tasks; H2 E, V_C, T rise with it; H3 marginal yield differs by stage; H4 SSR < 1 stably; H5 SSR and SCM differ across models even at equal Q_A5.", "eml_procedure": "30 tasks (10 math, 10 code, 10 constraint; Easy/Medium/Hard predefined) × A0–A5 × n replicates; A2 8 trajectories with deterministic majority; A3 typed verifier (same-model / independent / formal); A4 ≤ 4 deterministic local tool calls; A5 ≤ 16 invocations, ≤ 8 tool calls, ≤ 3 retry cycles with explicit termination; seeds and decoding frozen; warm weights, clean task state; run IDs IPM-XA-{model}-{task}-{condition}-{replicate}; paired within-task statistics with bootstrap CIs and effect sizes.", "eml_metrics": { "planned outputs": [ "ΔQ_k = Q_k − Q_0", "SSR = Q_0 / Q_5, SDR = 1 − SSR", "SCM_j = C_5,j / C_0,j per cost axis", "marginal yield Y_k,j", "response curves Q vs T, E, invocations, device-time", "brute-force flag ΔQ < 0.01 with ΔC/C > 0.5 (exploratory thresholds)", "selection waste ratio, discarded work" ], "minimum physical telemetry": [ "T_wall", "E_device (E-Grade C)", "M_peak", "V_C" ], "status": "READY FOR PILOT" }, "eml_controls": [ "identical prompt, initial context, decoding, system instruction and model version across conditions", "initial-information equality A0–A3; external information gain marked for A4/A5", "no cross-condition leakage; budget self-extension forbidden" ], "eml_run_count": 0, "eml_result_type": "INCONCLUSIVE", "eml_interpretation": "A protocol, not a result. Its instrument (XA-02…XA-06L) was validated synthetically and then used once on three easy tasks with a real local model; whether a scaffolding response curve exists on non-trivial tasks is still open.", "eml_limitations": [ "Deliberately does not attempt μI identification, lifecycle energy, cross-substrate comparison, high-ambiguity quality, full Shapley attribution or multi-agent settings.", "Pilot budgets are reference values, not IPM standards." ], "eml_software_environment": "protocol document + JSON run schema + YAML example run (EML-IPM-XA-01 v0.1)", "eml_reproduction_instructions": "Implement the ladder with XA-04 against XA-02 tasks, log with XA-03, run through XA-06/XA-06L; see EXP-2026-0103 for the first real execution.", "eml_benchmark_ids": [ "BEN-2026-0101" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0101/", "json": "/ai/experiments/EXP-2026-0101/index.json", "relations": [ { "id": "REL-2026-0461", "predicate": "uses_benchmark", "source": "EXP-2026-0101", "target": "BEN-2026-0101", "status": "ACTIVE" }, { "id": "REL-2026-0462", "predicate": "runs_on", "source": "EXP-2026-0101", "target": "SYS-2026-0102", "status": "ACTIVE" }, { "id": "REL-2026-0463", "predicate": "tests", "source": "EXP-2026-0101", "target": "THY-2026-0109", "status": "ACTIVE" }, { "id": "REL-2026-0464", "predicate": "tests", "source": "EXP-2026-0101", "target": "CLM-2026-0104", "status": "ACTIVE" }, { "id": "REL-2026-0465", "predicate": "produced", "source": "EXP-2026-0101", "target": "ART-2026-0112", "status": "ACTIVE" }, { "id": "REL-2026-0466", "predicate": "extends", "source": "EXP-2026-0102", "target": "EXP-2026-0101", "status": "ACTIVE" }, { "id": "REL-2026-0471", "predicate": "extends", "source": "EXP-2026-0103", "target": "EXP-2026-0101", "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 } }