{ "section": "research", "kind": "research", "canonical": "https://evemisslab.com/ai/research/", "count": 7, "records": [ { "id": "RES-2026-0002", "kind": "research", "label": "PACC conjecture — do non-probabilistic primitives converge to probability-like structure?", "created_at": "2026-09-08", "updated_at": "2026-09-09", "values": { "eml_status": "EXPERIMENTAL", "eml_evidence_level": "E3", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/research/RES-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": "Systems whose canonical state and update rules never require probability distributions, Bayesian posteriors or sampling are placed in the same evidence-integration tasks as an exact Bayesian reference. The lab measures whether low-complexity train-only maps carry their states to the Bayesian state, whether the maps commute with updates and survive interventions, and whether independently designed families converge — a four-level ladder (PACC-B, -R, -D, -A) with preregistered falsification conditions.", "eml_summary_zh": "把 canonical state 與更新規則都不需要概率分布、Bayesian posterior 或抽樣的系統，放進與精確 Bayesian 參考相同的證據整合任務中，量測低複雜度、只在訓練集擬合的映射能否把它們的狀態送到 Bayesian 狀態、映射是否與更新交換並在干預下存活、以及獨立設計的家族是否收斂——四層階梯（PACC-B／R／D／A）與預先登記的否證條件。", "eml_label_zh": "PACC 猜想——非概率 primitive 會不會收斂到概率表象？", "eml_primary_domain": "Model Representation", "eml_domains": [ "Formal AI", "Reasoning", "Evaluation" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_research_questions": [ "Posed deliberately as a similar-but-not-probabilistic counter-construction to the claim that modern AI is simply a probability model: some of it is, all of it need not be. The experiments are set up so that either outcome is informative — convergence says something about attractors, divergence says something about what probability is uniquely doing.", "Is probability a necessary ontology of intelligence, an effective representation, an engineering convergence form, or an observer's compression of deeper competitive state?", "Can a non-probabilistic state be mapped by a low-complexity map to a Bayesian state on held-out tasks, with the update diagram approximately commuting?", "Do three or more independently designed non-probabilistic families converge (PACC-A)?" ], "eml_claims": [ "Supported as a controlled micro-environment witness: PACC-B, PACC-R and PACC-D for N0/N1, N2 and N3 under uniform and heterogeneous evidence quality (v0.1–v0.2), with shuffled-target controls roughly two orders of magnitude worse.", "Convergence has a nontrivial basin, not a demonstrated universal attractor: N2 fails the representation threshold under adversarial geometry, and task-state convergence is architecture- and seed-sensitive once reliability must be learned (v0.2–v0.3).", "Decision-level probability coordinates can converge while a latent explanatory variable (common-cause posterior) has no direct low-complexity coordinate; the latent coordinate is hierarchical/compositional (v0.4–v0.6).", "Frozen composed coordinates transfer across dependence regimes over finite, family-specific basins; a three-chart atlas covers 8/9 of the sweep; forward cocycle coherence is robust on triple overlap, but reverse transport carries a persistent destination bias (v0.7–v0.13)." ], "eml_limitations": [ "PACC-A is not supported: N0 and N1 are exact reparameterizations, leaving two independent convergent families against a preregistered minimum of three.", "Everything is a transparent synthetic micro-lab; nothing here shows that probability is false, that Bayesian inference is unnecessary, that LLM internals are equivalent, or that probability is an observer projection.", "PACC is a conjecture. Its numbers are synthetic data and theoretical reasoning; until a real hybrid model exists, an inference is only an inference — theoretically possible is not actually possible." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0002/", "json": "/ai/research/RES-2026-0002/index.json" }, { "id": "RES-2026-0004", "kind": "research", "label": "A PACC-style runtime on language models: reasoning, intent and creative breadth", "created_at": "2026-09-09", "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/research/RES-2026-0004/", "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": "Does wrapping candidate selection in a canonical hard/derived-constraint commit space change what a generator produces? A synthetic A/B/C witness (generator only / hard verifier / PACC runtime) shows derived coherence and constraint-satisfying novelty up, soft-preference fit slightly down, and a creative-breadth collapse that a post-hoc 'elastic' exploration policy recovers. The real-language-model version of the benchmark has a validated, fail-closed harness but has not been executed.", "eml_summary_zh": "把候選選擇包進 canonical 硬約束／衍生約束的 commit 空間，會改變生成器的產出嗎？合成的 A/B/C 見證（純生成器／硬驗證器／PACC runtime）顯示衍生一致性與滿足約束的新穎度上升、軟偏好契合略降，以及一個可由事後「elastic」探索策略恢復的創造廣度塌縮。真實語言模型版本的 benchmark 已有驗證過、fail-closed 的 harness，但尚未執行。", "eml_label_zh": "PACC 式 runtime 用在語言模型上：推理、意圖與創造廣度", "eml_primary_domain": "Reasoning", "eml_domains": [ "Evaluation", "Agent Systems" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "SYNTHETIC", "eml_research_questions": [ "Is there a reasoning-up / imagination-down trade-off, or is the observed breadth loss a selection-policy artefact separable from the commit constraints?", "Will a frontier language model show the same effect as the synthetic witness?" ], "eml_claims": [ "Within the synthetic witness: reasoning coherence ↑, valid novelty ↑, soft-preference fit slightly ↓, creative breadth ↓ under naive selection and recoverable with exploration separated from commitment (8/8 seeds sign-stable).", "Real local 9B model, thinking off, two runs (32 and 64 rows per condition): the three runtime conditions are practically equivalent on every judge axis, and by label-free measures the PACC runtime does not narrow creative breadth. The synthetic v0.1 prediction did not appear on this model.", "Real local 9B model with thinking enabled (32 rows per condition): the PACC runtime has the highest valid novelty (+0.069 vs the hard verifier, +0.038 vs the plain model) and repair, governance axes are flat to slightly lower, and breadth is again not reduced — half of the synthetic prediction, unreplicated." ], "eml_limitations": [ "Zero real LLM calls so far; no claim about real-model reasoning, intent understanding, imagination, hallucination or human-rated usefulness is permitted before a real-model result exists.", "The v0.1 numbers are synthetic data and theoretical reasoning; until a real hybrid model exists, an inference is only an inference — theoretically possible is not actually possible." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0004/", "json": "/ai/research/RES-2026-0004/index.json" }, { "id": "RES-2026-0001", "kind": "research", "label": "Blind derivation of an adaptive epistemic architecture", "created_at": "2026-09-07", "updated_at": "2026-09-08", "values": { "eml_status": "ACTIVE", "eml_evidence_level": "E2", "eml_object_version": "0.1", "eml_canonical_url": "https://evemisslab.com/ai/research/RES-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": "Starting only from first principles — temporally heterogeneous world knowledge, canonical symbolic state, adaptive representation space, capability memory, substrate-neutral compute — the eleven-paper series derives a candidate architecture and then asks the uncomfortable question the derivation raised: why does it look so much like modern compound AI, and does any of the difference survive into a runtime?", "eml_summary_zh": "只從第一原理出發——時間異質的世界知識、canonical 符號狀態、自適應表示空間、能力記憶、載體中立計算——十一篇系列推導出一個候選架構，再面對推導本身冒出的不舒服問題：它為什麼越來越像現代複合 AI？差異有沒有任何一部分能活到 runtime 裡？", "eml_label_zh": "自適應認識系統的盲推導", "eml_primary_domain": "AI Architecture", "eml_domains": [ "Context & Memory", "Agent Systems", "AI-native Systems" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "THEORY", "eml_research_questions": [ "What does an intelligent system look like when derived from world-state, freshness, memory and reuse requirements rather than from existing AI paradigms?", "Which of its architectural semantics — canonical state ownership, candidate→verify→commit, mandatory provenance, tension-scheduled refresh — survive comparison with progressively stronger baselines?", "If the differences do not survive, is the convergence itself the phenomenon to explain (an intelligent architecture attractor)?" ], "eml_claims": [ "World knowledge is temporally heterogeneous; a single global refresh clock is either wasteful or stale.", "Natural language should be an interface to canonical state, not the canonical state.", "After removing what strong baselines already do, the candidate AER core is: epistemic world-state semantics + candidate/verify/commit authority + mandatory fact provenance + node-local tension refresh + capability/container separation + explicit epistemic-operator routing (R2)." ], "eml_limitations": [ "No performance, cost or long-horizon comparison against a production agent framework has been run; R2's LangGraph comparison is source-grounded only.", "One implementation and one substrate cannot speak for all implementations, benchmarks, model families or substrates (Paper 11 §114)." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0001/", "json": "/ai/research/RES-2026-0001/index.json" }, { "id": "RES-2026-0003", "kind": "research", "label": "Does epistemic governance survive implementation? The AER-0 architecture comparison", "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/research/RES-2026-0003/", "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": "Six rounds compare the AER-0 runtime with progressively stronger baselines — a stateless recomputer, fixed-TTL state, memory + tools, an evented compound agent, LangGraph 1.2.11 (source-grounded), and finally a centralized application-level gate that is allowed to be as good as AER. Each round narrows the claim: from 'AER is distinct' to 'AER promotes epistemic governance from application convention to a runtime-level canonical-write boundary', with bounded mediation and an external signed authenticity witness, and explicitly no claim of unique computational capability.", "eml_summary_zh": "六輪把 AER-0 runtime 與越來越強的基線比較——無狀態重算、固定 TTL、記憶 + 工具、事件驅動複合 agent、LangGraph 1.2.11（僅 source-grounded）、最後是一個允許做得跟 AER 一樣好的集中式應用層 gate。每一輪都把主張收窄：從「AER 不一樣」收到「AER 把認識論治理從應用慣例提升為 runtime 層的 canonical-write 邊界」，附有界中介與外部簽章真實性見證，並明確不主張獨特的計算能力。", "eml_label_zh": "認識論治理能不能活過實作？AER-0 架構比較", "eml_primary_domain": "AI Architecture", "eml_domains": [ "Agent Systems", "Evaluation", "AI Infrastructure" ], "eml_program_id": "PRG-2026-0001", "eml_data_basis": "DETERMINISTIC RUNTIME", "eml_research_questions": [ "When a baseline is given persistent memory, workflow reuse, event invalidation and versioning, how much of AER remains distinct?", "Is a mandatory epistemic commit transaction a new computational capability, or the elevation of convergent mechanisms into a runtime primitive?", "Can canonical epistemic mutation be completely mediated, and can authenticity be anchored outside the writable database?" ], "eml_claims": [ "R1: AER-0 is distinct on tested mutation semantics (provenance gate, optimistic version conflict) but not dominant — the evented baseline needs fewer recomputations.", "R3: AER-ECT ≈ centralized application gate on tested governance semantics; computational uniqueness NOT SUPPORTED; architectural elevation supported.", "R4: centralization reduces policy scattering (O(NR)→O(R)) and migration surface, at the price of a larger blast radius per shared defect.", "R5–R6: bounded complete mediation without tamperproofness; an Ed25519-signed external anchor converts a coherent full-DB forgery from undetected to detectable, given a trusted key and latest-head witness." ], "eml_limitations": [ "No executable cross-runtime comparison: LangGraph could not be installed (PyPI DNS unavailable) in the R2 environment.", "No performance, cost, security-certification or general-intelligence claim; hostile same-process code and a compromised signer remain outside the trusted boundary." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Sol (GPT-5.6, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0003/", "json": "/ai/research/RES-2026-0003/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": "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": "RES-2026-0102", "kind": "research", "label": "Quality line — measuring outcome quality without asking humans for a score", "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/research/RES-2026-0102/", "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 06–08. Quality is a relation Q(Y | task, specification, environment, boundary), not a number an artifact carries: formalize what can be formalized (proof checkers, compilers, constraint solvers), structure what can be structured (requirement coverage, contradiction graphs, evidence checks, hard gates), and only then hand the genuine residual to humans — as many local binary or pairwise judgments reconstructed into a latent quality vector by a psychometric model (IBQF / BRQM), inside a typed, versioned, context-aware quality ontology for text, image, music, story and design.", "eml_summary_zh": "第 06–08 篇。品質是關係 Q(Y | 任務、規格、環境、邊界)，不是作品自帶的一個數字：能形式化的先形式化（proof checker、compiler、constraint solver），能結構化的先結構化（需求覆蓋、矛盾圖、證據核查、hard gate），最後才把真正的殘餘交給人類——以大量局部二元或成對判斷，由心理計量模型重建成潛在品質向量（IBQF／BRQM），並放在有型別、有版本、隨情境的品質本體裡，涵蓋文字、圖像、音樂、故事與設計。", "eml_label_zh": "品質線——不叫人打分數也能量成果品質", "eml_primary_domain": "Evaluation", "eml_domains": [ "Cognitive Science" ], "eml_program_id": "PRG-2026-0101", "eml_research_questions": [ "Which parts of 'quality' can be decided by a formal system, which by structured checks, and which only by human perception?", "When humans must judge, what should they be asked so that they observe and the measurement system builds the scale?", "For high-ambiguity artifacts, which constructs must be defined before any item is written — and how does the ontology grow without moving the goalposts?" ], "eml_claims": [ "Quality is not an intrinsic scalar; a scalar Q* exists only under a declared projection rule, task, weights, gates and boundary.", "Compile success ≠ correct program; all tests passed ≠ universal correctness; formal proof ≠ real-world goal correctness — specification and verification are separate axes.", "Binary observation ≠ binary phenomenon: {0,1}^N answers can reconstruct a continuous, multidimensional latent quality, and the binary-burden advantage is an empirical hypothesis (F3), not a law.", "Disagreement ≠ error; mean preference ≠ preference structure; reliability ≠ validity; novelty ≠ creativity." ], "eml_limitations": [ "No experiment on this line has run (Experiment B is declared only); the EveMissLab IBQF/FDCS sources it builds on are internal theory.", "Paper 07 explicitly does not propose a clinical scale; the pain example illustrates observer burden only." ], "eml_authors": [ "Neo.K (EveMissLab)" ], "eml_ai_collaborators": [ "Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)" ] }, "canonical_url": "https://evemisslab.com/ai/research/RES-2026-0102/", "json": "/ai/research/RES-2026-0102/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 } }