{ "section": "computation", "kind": null, "canonical": "https://evemisslab.com/ai/computation/", "count": 15, "records": [ { "id": "PAP-2026-0005", "kind": "paper", "label": "Paper 05 — Memory, algorithm libraries and reusable solution paths", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0005/", "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": "Algorithms, tools, contracts, costs and outcome history become capability nodes; Reuse ≻ Adapt ≻ Create.", "eml_summary_zh": "算法、工具、契約、成本與成敗歷史成為能力節點；Reuse ≻ Adapt ≻ Create。", "eml_label_zh": "記憶、算法庫與可重用問題求解路徑——從世界模型到能力模型的累積式智能架構", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0001", "eml_publication_type": "series paper (Adaptive Epistemic Systems Series, 11 papers)", "eml_data_basis": "THEORY", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_date": "2026-09-08", "eml_source_artifact": "Adaptive_Epistemic_Systems_Series_Paper_05_Memory_Algorithms_and_Reusable_Solution_Paths_v0.1.md", "eml_checksums": { "sha256": "e54a04fb440fef6a2835017bf92338d1f85b7e3188252c2bd5b2ed213b8d52cd" }, "eml_tags": [ "zh-TW", "canonical UTF-8 Markdown", "paper 5/11" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0005/", "json": "/ai/papers/PAP-2026-0005/index.json" }, { "id": "PAP-2026-0006", "kind": "paper", "label": "Paper 06 — Substrate-neutral computational containers", "created_at": "2026-09-08", "updated_at": "2026-09-08", "values": { "eml_status": "STABLE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0006/", "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": "Any execution environment with representable input, valid transition and readable output is a compute container; algorithms and containers are scheduled jointly.", "eml_summary_zh": "任何具可表示輸入、有效轉換與可讀輸出的執行環境都是計算容器；算法與容器聯合調度。", "eml_label_zh": "載體中立的計算容器理論——從算法選擇到異質計算載體聯合調度", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0001", "eml_publication_type": "series paper (Adaptive Epistemic Systems Series, 11 papers)", "eml_data_basis": "THEORY", "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_date": "2026-09-08", "eml_source_artifact": "Adaptive_Epistemic_Systems_Series_Paper_06_Substrate_Neutral_Computational_Containers_v0.1.md", "eml_checksums": { "sha256": "dca4838b1274db5f51668e3dde0babdaaf27fd7e6f1ce9d2a2a82c1b978b3d33" }, "eml_tags": [ "zh-TW", "canonical UTF-8 Markdown", "paper 6/11" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0006/", "json": "/ai/papers/PAP-2026-0006/index.json" }, { "id": "THY-2026-0001", "kind": "theory", "label": "Asymmetric spacetime tension: temporally heterogeneous world knowledge", "created_at": "2026-09-07", "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/theory/THY-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": "Asymmetry is lifted from edge direction or weight to the effective time scale of nodes and relations. Each node carries stability, information-decay rate, update tension, system impact and local valid time; refresh is triggered by tension, external disturbance, information age, change velocity and event relevance rather than by one global clock, so stable knowledge sleeps, volatile knowledge refreshes often, and a rarely changing high-impact node triggers wide dependency recomputation when it does change.", "eml_summary_zh": "把非對稱性從邊的方向或權重，提升到節點與關係的有效時間尺度。每個節點帶有穩定性、資訊衰減率、更新張力、系統影響度與局部有效時間；刷新由張力、外部擾動、資訊年齡、變化速度與事件相關性觸發，而不是一個全域時鐘——穩定知識沉睡、快變知識高頻更新、低頻高影響的基礎節點一旦改變就觸發大範圍依賴重算。", "eml_label_zh": "非對稱時空張力：時間異質的世界知識", "eml_primary_domain": "Context & Memory", "eml_domains": [ "Computation", "AI Architecture" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "THEORY", "eml_assumptions": [ "Knowledge stability is highly non-uniform across formal, physical, social and real-time domains.", "Update cost is not free; over-refresh and under-refresh are both failures." ], "eml_claims": [ "World knowledge is temporally heterogeneous.", "Freshness is not a timestamp: it is decided jointly by world change rate, source reliability, dependency structure, task risk and system impact (Paper 02)." ], "eml_predictions": [ "Architecture contribution AC(λ=0) ≈ 0 in a static world, while AC(λ_heterogeneous) > 0; a fixed synchronous-refresh baseline should be worse in highly heterogeneous time-scale environments (Paper 11 §80–82)." ], "eml_falsification_conditions": [ "No measurable staleness/recomputation advantage over fixed-TTL and event-driven refresh under heterogeneous dynamics.", "The tension field is only an LLM guess with no runtime enforcement — then the theory has not been tested (Paper 11 §29)." ], "eml_known_limitations": [ "R1 found that in an event-rich deterministic world, pure event invalidation is cheaper than tension scheduling (AER 3 recomputations vs 2)." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0001/", "json": "/ai/theory/THY-2026-0001/index.json" }, { "id": "THY-2026-0007", "kind": "theory", "label": "Capability memory and substrate-neutral compute: Reuse ≻ Adapt ≻ Create", "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/theory/THY-2026-0007/", "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": "Beyond facts, the system keeps the algorithms, tools, execution contracts, costs, versions, applicability conditions and success/failure history it has used, and prefers reusing a known solution path over adapting one over creating one. Algorithms and compute containers are different layers: any environment that accepts representable input, performs a valid state transition and returns readable output is a container with its own cost, latency, error and availability model, so algorithm/container pairs are selected jointly.", "eml_summary_zh": "除了事實之外，系統也保存用過的算法、工具、執行契約、成本、版本、適用條件與成敗歷史，並且偏好重用已知求解路徑，勝過調整，再勝過重造。算法與計算容器是不同層：任何能接受可表示輸入、執行有效狀態轉換並回傳可讀輸出的環境都是一個容器，各有自己的成本、延遲、誤差與可用性模型，因此算法／容器成對聯合選擇。", "eml_label_zh": "能力記憶與載體中立計算：Reuse ≻ Adapt ≻ Create", "eml_primary_domain": "Computation", "eml_domains": [ "AI Architecture", "AI Infrastructure" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "THEORY", "eml_claims": [ "Reuse ≻ Adapt ≻ Create.", "Algorithm ≠ container; a capability/container pair is the unit of selection and of execution trace." ], "eml_predictions": [ "Planning cost falls with repeated related tasks; ReuseGain grows with task similarity within the applicability range, and constraint mismatch produces measurable false reuse (Paper 11 §83–84)." ], "eml_falsification_conditions": [ "No planning-cost reduction with experience; negative transfer dominates." ], "eml_known_limitations": [ "R1/R2: persistent workflow memory outside the model is not unique to AER; the capability/container separation was 'AER default distinct' only because no core LangGraph primitive was found, not because it cannot be built there." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0007/", "json": "/ai/theory/THY-2026-0007/index.json" }, { "id": "EXP-2026-0103", "kind": "experiment", "label": "XA-06 first real-model pilot — Qwythos-9B-v2 on the A0→A5 ladder (36 trials, 2026-09-03)", "created_at": "2026-09-03", "updated_at": "2026-09-07", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0103/", "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 time a real model was placed inside the IPM instrument: hf.co/empero-ai/Qwythos-9B-v2-GGUF:Q4_K_M served by Ollama on an RTX 3070, run locally on 2026-09-03 by Splice (Claude Code) on Neo.K's authorization through XA-06L — MATH-003, CODE-001, CON-003 × A0–A5 × 2 replicates, 36 trials, 186 invocations, 162 trajectories, telemetry complete on every trial. Sealed REAL_MODEL_PILOT_INCOMPLETE: 33/36 complete, three trials aborted because the same-model verifier returned non-JSON to a strict parser (a real model behaviour, deliberately not re-rolled). SSR = 1.0, SDR = 0.0: scaffolding brought no measured quality gain on these three easy tasks while A5 used 3.10× the device energy and 3.13× the wall time of A0, and the fixed eight-sample conditions A2–A4 used 7.9–9.3×. The apparent A3/A4 quality rise to 0.667 is a missingness artifact; and for two of the three tasks the recorded 'quality' was output-format compliance, not task correctness (post-hoc: 33/33 completed outputs semantically correct; strict output-contract compliance 12/36).", "eml_summary_zh": "第一次把真實模型放進 IPM 儀器：hf.co/empero-ai/Qwythos-9B-v2-GGUF:Q4_K_M 由 Ollama 在 RTX 3070 上服務，2026-09-03 由 Splice（Claude Code）在 Neo.K 授權下透過 XA-06L 於本地執行——MATH-003、CODE-001、CON-003 × A0–A5 × 2 次，36 次試驗、186 次呼叫、162 條軌跡，每次試驗遙測完整。封存為 REAL_MODEL_PILOT_INCOMPLETE：33/36 完成，三次試驗因同模型驗證器對嚴格解析器回了非 JSON 而中止（真實的模型行為，刻意不重擲）。SSR = 1.0、SDR = 0.0：在這三個簡單任務上鷹架沒有帶來可測的品質增益，A5 卻用了 A0 的 3.10× 裝置能量與 3.13× wall time，固定八樣本的 A2–A4 用了 7.9–9.3×。A3/A4 看似升到 0.667 是缺值造成的假象；且三個任務裡有兩個，記錄到的「品質」是輸出格式服從性而非任務正確性（事後檢查：33/33 完成的輸出語意正確；嚴格輸出契約合規 12/36）。", "eml_label_zh": "XA-06 第一次真實模型 pilot——Qwythos-9B-v2 走 A0→A5 階梯（36 試驗，2026-09-03）", "eml_primary_domain": "Evaluation", "eml_domains": [ "Agent Systems", "Computation" ], "eml_program_id": "PRG-2026-0101", "eml_data_basis": "REAL MODEL", "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT) — protocol, instrument packages and the 2026-09-07 diagnostic", "Splice (Claude Code, Anthropic) — local execution, sealing and the RESULT note" ], "eml_hypothesis": "Experiment A's H1–H4 on the three-task gate matrix: does scaffolding raise quality, at what physical cost, with non-constant marginal yield, and is SSR < 1?", "eml_model_ids": [ "MOD-2026-0006" ], "eml_benchmark_ids": [ "BEN-2026-0101" ], "eml_hardware": "NVIDIA GeForce RTX 3070 (8 GiB VRAM; peak 7.59 GiB used, peak 208.9 W, 73 °C), Windows 10 host; physical boundary local-runner-plus-visible-accelerator; energy type device_measured (E-Grade C, CST-B)", "eml_software_environment": "Ollama serving the model through an OpenAI-compatible endpoint at 127.0.0.1:11434; XA-02/03/04/06/06L v0.1 (hashes verified byte-exact against their manifests before the run); Python 3.14.5; XA-03 collectors system + nvidia_smi at 250 ms target (observed ~335–350 ms)", "eml_configuration": { "provider": { "mode": "openai_compatible", "provider_id": "local-openai-compatible", "model_id": "hf.co/empero-ai/Qwythos-9B-v2-GGUF:Q4_K_M", "base_max_tokens": 1024, "temperature": 0.2, "top_p": 1.0, "seed": 7, "budget_control_validated": true, "auth_mode": "none" }, "matrix": { "tasks": [ "MATH-003", "CODE-001", "CON-003" ], "conditions": [ "A0", "A1", "A2", "A3", "A4", "A5" ], "replicates": 2 }, "allow_code_evaluation": false, "telemetry": { "collectors": [ "system", "nvidia_smi" ], "physical_boundary": "local-runner-plus-visible-accelerator", "required": false } }, "eml_procedure": "XA-06L configure → preflight (all checks PASS; isolated MATH-003/A0 quality 1.0) → run (36/36 terminal, 0 runtime failures) → verify gate (3 points xa03_not_complete) → analyze → seal. The three aborted points were not re-run with resume --force: re-rolling until the gate turns green would erase a real failure mode.", "eml_metrics": { "gate": { "status": "REAL_MODEL_PILOT_INCOMPLETE", "verified_complete_count": 33, "invalid_or_missing": [ { "point": "CODE-001__A3__r2", "reason": "xa03_not_complete" }, { "point": "CON-003__A3__r1", "reason": "xa03_not_complete" }, { "point": "CON-003__A4__r1", "reason": "xa03_not_complete" } ] }, "headline": { "ssr": 1.0, "sdr": 0.0, "scm_device_energy": 3.1019, "scm_wall_time": 3.1264, "protocol_compliance_rate": 0.3333, "quality_available_rate": 0.6111 }, "by_condition": { "A0": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 10.21, "device_energy_j": 1715.6, "energy_ratio_vs_A0": 1.0, "gpu_peak_memory_gib": 7.23, "gpu_memory_residency_gib_s": 72.1, "gpu_utilization_integral_s": 6.57 }, "A1": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 9.87, "device_energy_j": 1819.0, "energy_ratio_vs_A0": 1.06, "gpu_peak_memory_gib": 7.32, "gpu_memory_residency_gib_s": 70.0, "gpu_utilization_integral_s": 6.26 }, "A2": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 79.09, "device_energy_j": 15143.0, "energy_ratio_vs_A0": 8.827, "gpu_peak_memory_gib": 7.28, "gpu_memory_residency_gib_s": 570.0, "gpu_utilization_integral_s": 54.09 }, "A3": { "quality_mean": 0.6667, "quality_n": 3, "success_rate": 0.6667, "wall_time_s": 99.13, "device_energy_j": 15921.5, "energy_ratio_vs_A0": 9.281, "gpu_peak_memory_gib": 7.34, "gpu_memory_residency_gib_s": 714.6, "gpu_utilization_integral_s": 70.02 }, "A4": { "quality_mean": 0.6667, "quality_n": 3, "success_rate": 0.6667, "wall_time_s": 69.08, "device_energy_j": 13546.2, "energy_ratio_vs_A0": 7.896, "gpu_peak_memory_gib": 7.28, "gpu_memory_residency_gib_s": 496.9, "gpu_utilization_integral_s": 46.93 }, "A5": { "quality_mean": 0.5, "quality_n": 4, "success_rate": 0.5, "wall_time_s": 31.91, "device_energy_j": 5321.5, "energy_ratio_vs_A0": 3.102, "gpu_peak_memory_gib": 7.24, "gpu_memory_residency_gib_s": 228.7, "gpu_utilization_integral_s": 22.17 } }, "operational_totals": { "model_invocations": 186, "trajectories": 162, "retries": 0, "tool_calls": 0, "verifier_passes": 18, "candidates_created": 162, "candidates_selected": 33, "candidates_discarded": 105, "failure_events": 6, "candidates_abandoned_on_abort": 24 }, "verifier_failure": { "count": 3, "verifier_enabled_trials": 18, "rate": 0.16666666666666666, "by_condition": { "A3": "2/6", "A4": "1/6", "A5": "0/6" } }, "strict_protocol_compliance": { "count": 12, "total": 36, "rate": 0.3333333333333333 }, "posthoc_semantic_diagnostic (non-canonical)": { "canonical": false, "math": "12/12 canonical correct", "code": "11/11 selected outputs pass all hidden tests after outer Markdown fence removal", "constraint": "10/10 selected outputs satisfy all constraints after format-only normalization", "completed_selected_outputs_correct": "33/33" }, "physical_totals": { "total_measured_gpu_energy_j": 320800.7795, "total_measured_gpu_energy_kwh": 0.0891, "summed_trial_wall_time_min": 29.9277, "max_gpu_memory_gib": 7.5908, "max_gpu_power_w": 208.88, "max_gpu_temperature_c": 73.0, "mean_sampling_call_wall_fraction": 0.2436 }, "quality_availability_reporting_inconsistency": { "aggregate_analysis": "22/36", "protocol_compliance_csv": "33/36", "inconsistency": true } }, "eml_controls": [ "fresh provider per trial; frozen temperature 0.2, top-p 1.0, seed 7; base_max_tokens 1024 with validated 2× budget for A1", "identical initial task text across conditions; calculator tool contract only in A4/A5 generator requests", "scoring after XA-03 finalization; private references never in context; code evaluation disabled on the host" ], "eml_random_seeds": [ "seed 7 (frozen into every HTTP request); model nondeterminism otherwise uncontrolled" ], "eml_run_count": 1, "eml_result_type": "MIXED", "eml_interpretation": "As an instrument gate it did its job: real numbers, full telemetry, a sealed and relocatable bundle, and an honest INCOMPLETE. As science it says three things and no more. (1) On three tasks the native single pass already solves, scaffolding cannot show a quality gain — SSR = 1 is a legal null result, and it cost 3.1× (A5) to 9.3× (A3) the device energy of A0; A5 was cheaper than the fixed eight-sample conditions only because its loop stopped early. (2) The instrument's quality axis conflated output-format obedience with task correctness on CODE-001 (correct code inside a Markdown fence) and CON-003 (correct assignment written as A=X, not JSON) — exactly the SyntacticValidity ≠ SemanticCorrectness split Paper 06 predicts, now observed in the lab's own instrument. (3) The same-model verifier's serialization failed in 3 of 18 verifier trials and discarded eight candidates each time; tool access was enabled but never used, so tool and retry effects are unidentified. The A3/A4 'gain' is survivor bias from the aborted low-format trials. Seven instrument revisions are required before XA-07; the dataset stays immutable.", "eml_limitations": [ "Three easy tasks, two replicates, one 9B model at 4-bit, one machine; not a population-level estimate of anything.", "Gate INCOMPLETE (33/36); CODE-001 quality unmeasured (execution disabled) so 12 of 36 trials have no measured quality; quality-availability is reported inconsistently inside the bundle (22/36 vs 33/36).", "Device-measured GPU energy only — not marginal, not whole-system; telemetry sampling itself cost ~24 % of trial wall time.", "Same-model verifier; no independent or formal verifier condition." ], "eml_reproduction_instructions": "Unpack XA-02/03/04/06/06L as siblings, .\\configure.ps1 (local_openai_compatible, base_url http://127.0.0.1:11434, the model id above), .\\preflight.ps1, .\\run-pilot.ps1, .\\seal-results.ps1; verify the sealed bundle against its manifest.json (266 files). The bundle's raw events/telemetry/summaries are unchanged by sealing.", "eml_completed_at": "2026-09-03", "eml_authors": [ "Neo.K (EveMissLab)" ] }, "canonical_url": "https://evemisslab.com/ai/experiments/EXP-2026-0103/", "json": "/ai/experiments/EXP-2026-0103/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" }, { "id": "RES-2026-0103", "kind": "research", "label": "Capability line — how much intelligence remains without the loop, and the unified intelligence event", "created_at": "2026-09-02", "updated_at": "2026-09-07", "values": { "eml_status": "EXPERIMENTAL", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/research/RES-2026-0103/", "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": "Papers 09–10 and the v0.2 Experiment A instrument. A system is (model, scaffolding vector); single-pass quality Q_SP and full-system quality Q_F give the scaffolding survival ratio SSR = Q_SP/Q_F, the dependence ratio SDR, the scaffold cost multiplier SCM and marginal scaffolding yields along a controlled ablation ladder A0…A5 — all read together with the physical overhead, because a loop is not cheating; hiding its cost is. Paper 10 packs quality, semantic work, physical computation and scaffolding into the canonical intelligence event, compares systems on Pareto frontiers under a no-premature-scalarization rule, and fixes a minimum reporting standard. The line's first real data point is the 2026-09-03 pilot on a local 9B model.", "eml_summary_zh": "第 09–10 篇與 v0.2 Experiment A 儀器。系統 =（模型，鷹架向量）；單次品質 Q_SP 與完整系統品質 Q_F 給出鷹架存活率 SSR = Q_SP/Q_F、依賴率 SDR、鷹架成本倍率 SCM 與受控消融階梯 A0…A5 上的邊際鷹架產率——全部要跟物理額外成本一起讀，因為 LOOP 不是作弊，隱藏成本才是。第 10 篇把品質、語意工作、物理計算與鷹架封裝成 canonical intelligence event，在「不過早純量化」規則下用 Pareto 前沿比較系統，並固定最低報告標準。這條線的第一個真實數據點是 2026-09-03 在本地 9B 模型上的 pilot。", "eml_label_zh": "能力線——拿掉 LOOP 還剩多少智能，以及統一的智能事件", "eml_primary_domain": "Evaluation", "eml_domains": [ "Agent Systems", "Computation" ], "eml_program_id": "PRG-2026-0101", "eml_research_questions": [ "Of a final answer, how much came from the model's native single pass and how much from retries, sampling, verifiers, tools, memory and planners — at what physical cost?", "Does a stable scaffolding response curve exist for a fixed model and task set, and where does it enter the brute-force region?", "Can two systems with the same final quality be told apart by capability source and physical cost rather than by a leaderboard score?" ], "eml_claims": [ "System capability ≠ model-native capability; Pass@k ≠ Pass@1; tool access ≠ tool utilization intelligence; invisible output ≠ zero cost.", "SSR/SDR describe the structure of an intelligence source, not a defect; they must be read with SCM and the scaffolding physical overhead.", "Intelligence is not any single element of the tuple (task, quality, semantic work, physical computation, scaffolding, metadata); the research object is the relation P_compute → N_μ → 𝔔.", "First real pilot (three easy tasks, local 9B, 2026-09-03): SSR = 1.0 with a 3.1× device-energy multiplier from A0 to A5 — and the instrument's quality axis turned out to measure output-format compliance on two of the three tasks." ], "eml_limitations": [ "One model, three tasks, two replicates, same-model verifier, code quality unmeasured, gate INCOMPLETE — a dataset for instrument revision, not an estimate.", "Shapley-style scaffold attribution, information-matched tool controls and the 900-trial physical comparison are all still ahead." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0103/", "json": "/ai/research/RES-2026-0103/index.json" }, { "id": "SYS-2026-0101", "kind": "system", "label": "XA-03 — telemetry and run logger (physical execution evidence layer)", "created_at": "2026-09-03", "updated_at": "2026-09-03", "values": { "eml_status": "STABLE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/systems/SYS-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": "Provider-agnostic logger that records one benchmark run as append-only events plus telemetry and derives a typed summary deterministically: model-invocation, trajectory, tool-call and verifier spans, candidate created/discarded accounting, wall time, device-time, GPU power integrated to device_energy_j (energy type device_measured, never relabelled as marginal), peak memory and memory residency, with unknowns kept null (Unknown ≠ 0) and forbidden conversions (tokens → J, TDP → J, price → J, GPU-hours → J). Golden fixture 450 J / 1.75 util·s / 12 GB peak / 33 GB·s residency verified; 35 passed, 1 skipped in 0.39s; instrumentation burden is calibrated and reported, not subtracted.", "eml_summary_zh": "與模型供應商無關的記錄器：把一次 benchmark 執行記成只增不改的事件流與遙測，再確定性地導出型別化摘要——模型呼叫、軌跡、工具呼叫與驗證器區段，候選建立／丟棄會計，wall time、裝置時間、GPU 功率積分成 device_energy_j（能量型別 device_measured，絕不改標成 marginal）、峰值記憶體與記憶體駐留，未知值保持 null（Unknown ≠ 0），並禁止 tokens → J、TDP → J、price → J、GPU-hours → J 的換算。黃金夾具 450 J／1.75 util·s／12 GB 峰值／33 GB·s 駐留驗證通過；35 passed, 1 skipped in 0.39s；儀器負擔經校準並報告，不自動扣除。", "eml_label_zh": "XA-03——遙測與執行記錄器（物理執行證據層）", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_purpose": "Make the physical side of an IPM event (wall time, device energy, memory residency, utilization, operational counts, discarded work) reproducible evidence rather than a claim.", "eml_architecture": "RunSession → EventLogger (paired spans) + TelemetryCollector (Null / System via psutil / NvidiaSmi) → MetricIntegrator (deterministic) → RunSink with atomic finalization (.partial → COMPLETE | ABORTED) and crash recovery that never invents end events; JSON schemas for events, telemetry and run summary.", "eml_documentation": "README.md, SPEC.md (36 sections), IMPLEMENTATION_PLAN.md, validation_report.json inside the package", "eml_tags": [ "EML-IPM-XA-03", "v0.1", "PRE_RELEASE_VERIFIED", "Python ≥3.11, no runtime dependencies" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/systems/SYS-2026-0101/", "json": "/ai/systems/SYS-2026-0101/index.json" }, { "id": "PAP-2026-0101", "kind": "paper", "label": "Paper 01 — What is a 'single turn', really? User turns, hidden loops, and the redefinition of single-pass intelligence", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "STABLE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/papers/PAP-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": "Separates the chat-interface turn from model invocation, generation trajectory, agent loop and physical computation; defines externally loopless intelligence, a five-kind loop taxonomy and the single-pass condition U=1, G=1, R=1, L=0, S=0; introduces the event vector (Q, U, G, I, L, R, S, T, E, V_CST) and twelve invariants, starting with 'interaction compression ≠ computation compression'.", "eml_summary_zh": "把聊天介面的一輪從模型呼叫、生成軌跡、agent 迴圈與物理計算中分離；定義外部無迴圈智能、五類 LOOP 分類與 single-pass 條件 U=1、G=1、R=1、L=0、S=0；引入事件向量 (Q, U, G, I, L, R, S, T, E, V_CST) 與十二個不變式，第一條是「互動壓縮 ≠ 計算壓縮」。", "eml_label_zh": "一輪到底是一輪什麼？：使用者回合、隱藏 LOOP 與單次智能的重新定義", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_publication_type": "series paper (Intelligence Physical Metrology series, 10 papers); 公開純理論論文, 無 MVP", "eml_data_basis": "THEORY", "eml_date": "2026-09-02", "eml_doi_or_external_id": "EML-IPM-01", "eml_source_artifact": "IPM_01_一輪到底是一輪什麼_v0.1.zip!/IPM_01_一輪到底是一輪什麼_使用者回合隱藏LOOP與單次智能的重新定義_v0.1.md", "eml_checksums": { "paper .md sha256": "995cb61c0c35f14eeebf51a467e98c705a48e64f6d4fbd3d9880bff642220d2f" }, "eml_tags": [ "zh-TW", "canonical UTF-8 Markdown", "paper 1/10", "role: 回合與執行邊界" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0101/", "json": "/ai/papers/PAP-2026-0101/index.json" }, { "id": "PAP-2026-0104", "kind": "paper", "label": "Paper 04 — From neurons to joules: energy, thermodynamics, and physical lower bounds of intelligent computation", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "STABLE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0104/", "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": "Builds the energy account bottom-up the way neural energetics does (ion flux → ATP → joule), shows that a spike — and therefore a token or a μI — has no fixed energy, types energy as gross/baseline/marginal/attributed with a declared boundary, and keeps Landauer's kT ln 2 as a bound on erasure rather than the price of reasoning.", "eml_summary_zh": "照神經能量學的方式由下而上建能量帳（離子流 → ATP → 焦耳），說明一個 spike——因此一個 token 或一個 μI——沒有固定能量，把能量分型為 gross／baseline／marginal／attributed 並宣告邊界，Landauer 的 kT ln 2 只是抹除的下界而不是推理的價格。", "eml_label_zh": "從神經元到焦耳：智能計算的能量、熱力學與物理下界", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_publication_type": "series paper (Intelligence Physical Metrology series, 10 papers); 公開純理論論文, 無 MVP", "eml_data_basis": "THEORY", "eml_date": "2026-09-02", "eml_doi_or_external_id": "EML-IPM-04", "eml_source_artifact": "IPM_04_從神經元到焦耳_v0.1.zip!/IPM_04_從神經元到焦耳_智能計算的能量熱力學與物理下界_v0.1.md", "eml_checksums": { "paper .md sha256": "1d40befa4ae5bde20f694b7a6026dbca6a62d0d55514ebcd08629be8895a57e6" }, "eml_tags": [ "zh-TW", "canonical UTF-8 Markdown", "paper 4/10", "role: 能源與熱力學" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0104/", "json": "/ai/papers/PAP-2026-0104/index.json" }, { "id": "PAP-2026-0105", "kind": "paper", "label": "Paper 05 — Computation is more than FLOPs: memory, interconnect, hardware occupancy, and computational spacetime volume", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "STABLE", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0105/", "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": "Replaces FLOPs with a physical cost vector (typed ops, memory traffic by hierarchy, I/O, interconnect, residency, occupancy, time, energy), defines computational spacetime as a vector-first measure V_CST = ∫ R(t) dt with its own topology and peak footprint, and fixes CST measurement grades and boundaries; roofline and memory-wall results are the engineering backbone.", "eml_summary_zh": "以物理成本向量（分型運算、按層級的記憶體流量、I/O、互連、駐留、占用、時間、能量）取代 FLOPs，把計算時空定義為向量優先的測度 V_CST = ∫ R(t) dt，附拓撲與峰值占用，並固定 CST 測量等級與邊界；roofline 與 memory wall 是工程骨幹。", "eml_label_zh": "計算不是只有 FLOPs：記憶體、互連、硬體占用與計算時空體積", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_publication_type": "series paper (Intelligence Physical Metrology series, 10 papers); 公開純理論論文, 無 MVP", "eml_data_basis": "THEORY", "eml_date": "2026-09-02", "eml_doi_or_external_id": "EML-IPM-05", "eml_source_artifact": "IPM_05_計算不是只有FLOPs_v0.1.zip!/IPM_05_計算不是只有FLOPs_記憶體互連硬體占用與計算時空體積_v0.1.md", "eml_checksums": { "paper .md sha256": "588407fccc64b1bc1c6e501314543e17444729b0e6736bb9bb3d8174b25c99f8" }, "eml_tags": [ "zh-TW", "canonical UTF-8 Markdown", "paper 5/10", "role: 完整物理成本與計算時空" ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/papers/PAP-2026-0105/", "json": "/ai/papers/PAP-2026-0105/index.json" }, { "id": "RES-2026-0101", "kind": "research", "label": "Execution and physical line — what one answer costs in turns, semantic work, energy and computational spacetime", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "ACTIVE", "eml_evidence_level": "E1", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/research/RES-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": "Papers 01–05. Decomposes the chat-interface 'turn' into user turns, generation trajectories, model invocations, external loops, retries, selection and a physical execution trace; proposes the minimum intelligent semantic execution unit μI as the missing middle layer between physical primitives and task achievement; borrows the cross-level, latent-inference, population-coding and causal-perturbation method of neuroscience; types energy as gross / baseline / marginal / attributed with a declared boundary and keeps Landauer as a bound, not a price; and replaces FLOPs with a physical cost vector and a vector-first computational spacetime with its own topology.", "eml_summary_zh": "第 01–05 篇。把聊天介面的「一輪」拆成使用者回合、生成軌跡、模型呼叫、外部 LOOP、重試、選擇與物理執行軌跡；提出最小智能語意執行單位 μI 作為物理原語與任務成果之間缺失的中間層；借用神經科學的跨層、潛變量推斷、群體編碼與因果擾動方法；把能量分型為 gross／baseline／marginal／attributed 並要求宣告邊界，Landauer 只是下界不是價格；並以物理成本向量與「向量優先」的計算時空及其拓撲取代 FLOPs。", "eml_label_zh": "執行與物理線——一個答案在回合、語意工作、能量與計算時空上的代價", "eml_primary_domain": "Computation", "eml_domains": [ "Cognitive Science", "Evaluation" ], "eml_program_id": "PRG-2026-0101", "eml_research_questions": [ "What is the physical unit of 'one turn' once interaction compression is separated from computation compression?", "What does intelligence compute once — if not a token, a FLOP, a neuron activation, a layer or a thought?", "How can a semantic unit that cannot be observed directly be measured the way cognitive neuroscience measures cognition?", "Which Joule is meant — gross, baseline, marginal or attributed — and inside which boundary?", "What is the full physical cost of a computation beyond arithmetic: memory traffic, residency, interconnect, occupancy, time, topology?" ], "eml_claims": [ "One user turn ≠ one model invocation ≠ one generation trajectory ≠ one agent loop ≠ one physical computation; interaction compression is not computation compression.", "Token ≠ μI ≠ FLOP; the minimal unit of intelligent work must sit between semantics and physics and be resolution-relative, not an absolute atom.", "The same observable event type (a spike, a token, a μI) has no fixed energy; energy is a realization distribution conditioned on architecture, hardware, context and boundary.", "FLOPs are one projection; V_C + V_M + V_N + V_S has no physical meaning before normalization — computational spacetime is vector-first, and equal volume is not equal topology." ], "eml_limitations": [ "Pure theory with no MVP; the only measurement so far is device-level GPU telemetry (E-Grade C, CST-B) from a three-task pilot.", "μI remains observer-reconstructed (μI^obs); its approximation to internal semantic units is unproven and graded, not asserted." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0101/", "json": "/ai/research/RES-2026-0101/index.json" }, { "id": "THY-2026-0101", "kind": "theory", "label": "Turn decomposition and externally loopless intelligence", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "PRELIMINARY", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/theory/THY-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 'turn' is decomposed into the vector T = (U user turns, G generation trajectories, I model invocations, L external feedback loops, R retries, S selection/verification, P physical execution trace). The cleanest single pass is U=1, G=1, R=1, L=0, S=0, and it excludes only action→new-evidence→replanning, not autoregressive sequential computation. Loops come in five kinds (tool, environment, verifier, retry, candidate/selection), capability lives in four layers (intrinsic, elicited, system, product), and every 'one-turn' claim projects onto the event vector (Q, U, G, I, L, R, S, T, E, V_CST).", "eml_summary_zh": "把「一輪」分解成向量 T =（U 使用者回合、G 生成軌跡、I 模型呼叫、L 外部回饋迴圈、R 重試、S 選擇／驗證、P 物理執行軌跡）。最乾淨的 single pass 是 U=1、G=1、R=1、L=0、S=0，排除的只有「行動→新證據→重規劃」，不排除自回歸的序列計算。LOOP 分五類（工具、環境、驗證器、重試、候選／選擇），能力分四層（intrinsic、elicited、system、product），任何「一輪完成」的宣稱都要投影到事件向量 (Q, U, G, I, L, R, S, T, E, V_CST)。", "eml_label_zh": "回合分解與外部無迴圈智能", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_data_basis": "THEORY", "eml_definitions": [ "Turn Decomposition Framework T = (U, G, I, L, R, S, P).", "Externally Loopless Intelligence (ELI): during a task the system cannot re-aim on external world, tool output, an independent verifier, another candidate or a retry.", "Interaction compression C_U = internal interactions / U.", "Loop taxonomy L = (L_T, L_E, L_V, L_R, L_C)." ], "eml_assumptions": [ "Autoregressive generation is internal sequential computation, not an external loop.", "Selection over candidates is itself a capability source." ], "eml_claims": [ "UserTurn ≠ PhysicalTurn; UserTurn ≠ ModelInvocation; ModelInvocation ≠ GenerationTrajectory.", "NoExternalLoop ≠ NoSequentialComputation.", "Pass@k ≠ Pass@1; BestOfN ≠ MedianExperience.", "InteractionCompression ≠ ComputationCompression; SameFinalQuality ≠ SameIntelligenceEfficiency." ], "eml_formalization": [ "Single-pass condition: U=1, G=1, R=1, L=0, S=0 → Q_SP.", "P(at least one success in k rollouts) = 1 − (1 − p)^k.", "Unified event vector 𝔈 = (Q, U, G, I, L, R, S, T, E, V_CST)." ], "eml_predictions": [ "Systems reported as 'one turn' will separate by orders of magnitude on (L, R, S, V_CST, E) once the event vector is recorded." ], "eml_falsification_conditions": [ "If operational accounting of U, G, I, L, R, S adds nothing to predicting cost or quality beyond the visible answer, the decomposition is idle." ], "eml_known_limitations": [ "Twelve invariants and a vocabulary; no measurement of its own — the vector is filled by Papers 02–09." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0101/", "json": "/ai/theory/THY-2026-0101/index.json" }, { "id": "THY-2026-0104", "kind": "theory", "label": "Energy accounting hierarchy and thermodynamic type safety", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "PRELIMINARY", "eml_evidence_level": "E0", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0104/", "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": "Neural energetics builds energy bottom-up (membrane dynamics → ion flux → pump work → ATP → dissipation) and finds that a spike has no fixed energy and that most cortical signaling energy is spent on synaptic integration and state maintenance, not the visible pulse. IPM copies the discipline, not the numbers: energy is typed as E = (gross, baseline, marginal, attributed, thermodynamic minimum), a boundary and baseline rule must be declared, information per Joule is not intelligence per Joule, Landauer's kT ln 2 bounds erasure and is not the price of a μI, and Shannon or variational 'energies' never become physical Joules without an explicit mapping.", "eml_summary_zh": "神經能量學由下往上算能量（膜動力學 → 離子流 → 幫浦功 → ATP → 耗散），並發現一個 spike 沒有固定能量、皮質的訊號能量大半花在突觸整合與狀態維持而非顯眼的脈衝。IPM 複製的是紀律不是數字：能量分型為 E =（gross、baseline、marginal、attributed、熱力學下限），必須宣告邊界與基線規則，每焦耳資訊不等於每焦耳智能，Landauer 的 kT ln 2 只約束抹除、不是一個 μI 的價格，Shannon 或變分「能量」沒有明確映射前永遠不是物理焦耳。", "eml_label_zh": "能量帳本層級與熱力學型別安全", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_data_basis": "THEORY", "eml_definitions": [ "E_gross = ∫ P_system dt; E_base = ∫ P_baseline dt; E_marg = E_gross − E_base; E_attrib = E_marg + α·E_shared with a declared α.", "Energy boundary: accelerator / node / rack / data center / infrastructure / lifecycle; E = E(Boundary, BaselineRule, AttributionRule).", "E-grades: D estimated / C device telemetry / B node meter / A infrastructure meter / A+ marginal causal energy.", "Landauer distance D_L = E_actual / E_Landauer — an implementation distance, not an intelligence score." ], "eml_assumptions": [ "Evolution and engineering optimize a Pareto set (energy, speed, reliability, robustness, adaptability), so minimum energy is not maximum utility." ], "eml_claims": [ "Spike ≠ FixedEnergyUnit; Token ≠ FixedEnergyUnit; μI ≠ FixedEnergyUnit; SignalShape ≠ EnergyCost.", "GrossEnergy ≠ MarginalEnergy ≠ AttributedEnergy; EnergyComparison ⇒ SameBoundary.", "InformationPerJoule ≠ IntelligencePerJoule; LandauerBound ≠ ActualComputationCost; 1 μI ≠ kT ln 2.", "ShannonEntropy ≠ ThermodynamicEntropy and VariationalFreeEnergy ≠ PhysicalEnergy without an explicit mapping." ], "eml_formalization": [ "Three efficiencies η_I/E = I/E, η_μ/E = N_μ^eff / E_marg, η_Q/E = Q / E_marg — never equated.", "Energy of a μI is a realization distribution P(E | μI, architecture, hardware, context, boundary)." ], "eml_predictions": [ "Reports that give a single 'Joules per answer' without type and boundary will not be comparable across systems." ], "eml_falsification_conditions": [ "If marginal, attributed and gross energies of the same task turn out to be interchangeable in practice, the typing is unnecessary." ], "eml_known_limitations": [ "The pilot measured device energy only (E-Grade C); no marginal or attributed energy has been measured." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0104/", "json": "/ai/theory/THY-2026-0104/index.json" }, { "id": "THY-2026-0105", "kind": "theory", "label": "Physical computation cost vector and computational spacetime", "created_at": "2026-09-02", "updated_at": "2026-09-02", "values": { "eml_status": "EXPERIMENTAL", "eml_evidence_level": "E1", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0105/", "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": "Physical cost is the vector C_P = (typed operations, memory traffic by hierarchy, I/O, interconnect, memory residency, device occupancy, wall time, energy), not FLOPs. Computational spacetime is first a measure V_CST = ∫ R(t) dt = (V_C, V_M, V_N, V_S) over a resource field; the components may not be added before a declared normalization, and equal volume (8 GPU × 10 s = 1 GPU × 80 s) is not equal topology Θ_CST = (T_wall, T_serial, P_parallel, D_peak, M_peak, B_peak, Γ_comm). Roofline, memory-wall and data-movement results explain why same-FLOPs workloads differ in time and energy; a peak hardware footprint is a capacity barrier; CST grades run from D (spec estimate) to A+ (causal resource attribution).", "eml_summary_zh": "物理成本是向量 C_P =（分型的運算、按層級的記憶體流量、I/O、互連、記憶體駐留、裝置占用、wall time、能量），不是 FLOPs。計算時空首先是資源場的測度 V_CST = ∫ R(t) dt =（V_C、V_M、V_N、V_S）；未宣告正規化前各分量不可相加，體積相等（8 GPU × 10 s = 1 GPU × 80 s）不等於拓撲 Θ_CST =（T_wall、T_serial、P_parallel、D_peak、M_peak、B_peak、Γ_comm）相等。Roofline、memory wall 與資料搬移的結果解釋了為何相同 FLOPs 的工作在時間與能量上不同；峰值硬體占用是容量門檻；CST 等級從 D（規格推估）到 A+（因果資源歸因）。", "eml_label_zh": "物理計算成本向量與計算時空", "eml_primary_domain": "Computation", "eml_program_id": "PRG-2026-0101", "eml_data_basis": "THEORY", "eml_definitions": [ "C_P = (O, B_M, B_I, B_N, M_R, D, T, E); O typed by precision; nominal vs executed vs useful operations.", "V_M = ∫ M_resident dt (byte·s), V_C = ∫ D(t) dt (device·s); MemoryTraffic ≠ MemoryResidency.", "Normalized scalar V*_CST(Reference, Weights, Boundary); topology Θ_CST; peak footprint H_peak.", "Measurement confidence bundle G_M = (Grade_μ, Grade_E, Grade_CST); P_compute = (C_P, V_CST, Θ_CST, H_peak, E, Boundary_P, G_M)." ], "eml_assumptions": [ "Attainable performance is bounded by min(P_peak, BW · arithmetic intensity) (Roofline)." ], "eml_claims": [ "FLOPs ≠ PhysicalComputationalCost; SameFLOPs ≠ SameLatency ≠ SameEnergy; SameDeviceTime ≠ SameEnergy.", "SameCSTVolume ≠ SameCSTTopology; TotalResource ≠ PeakCapacityRequirement; MoreDevices ⇏ LowerLatency.", "ScalarCST ⇒ DeclaredNormalization; CSTComparison ⇒ SameBoundaryOrExplicitConversion; LowUtilization ≠ BadSystem." ], "eml_formalization": [ "V_CST = ∫ R(t) dt with R = (r_C, r_M, r_N, r_S); V*_CST = ∫ Σ_j w_j r_j(t)/C_ref,j dt.", "Vector efficiency η_Q/CST = (Q/V_C, Q/V_M, Q/V_N, Q/V_S); Pareto dominance A ≻_P B." ], "eml_predictions": [ "Controlling FLOPs will leave large independent variation in T, E, B_M, B_N and V_M across memory patterns and topologies (Falsifiable Claim 2)." ], "eml_falsification_conditions": [ "If, FLOPs held fixed, time, energy, memory traffic and residency do not vary substantially across workloads, a single FLOPs cost model suffices." ], "eml_known_limitations": [ "The pilot recorded wall time, device energy, peak VRAM, memory residency and utilization integrals for one GPU (CST-B); interconnect and memory traffic were not measured." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/theory/THY-2026-0105/", "json": "/ai/theory/THY-2026-0105/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 } }