AI Research Laboratory

• ResearchRES-2026-0201Why passing checks does not close the publication boundaryPapers 00–05. The five-state information chain (observed → authorized → persisted → published → externally obtainable), the green-light fallacy (V₁ ∧ … ∧ Vₙ = PASS ⇏ G), agent context as an egress surface with nine context classes, recoverability R0–R4 beyond literal secret matching, and two hypotheses about scale: organizational propagation of shared agent context, and an AI build–attack asymmetry.STABLE E1 Privacy Updated 2026-10-13
• ResearchRES-2026-0202Measuring without looking — researcher-blind measurement of public repositoriesPapers 06, 07 and 09, the RBPM runtime and Phase II. A sealed process is the first and only observer of repository content; only a closed vocabulary of features leaves it; identities are discarded; labels are locked before any grouping is revealed; UNKNOWN is never PASS; credentials are never validated. Phase II ran four fresh rounds on repositories with agent instruction files and two on individuals' AI-assisted repositories.STABLE E2 Evaluation Updated 2026-10-13
• ResearchRES-2026-0203Who is responsible for the publication boundaryPaper 08. Observation, execution, persistence and publication are four boundaries that cannot be merged; platforms have built real controls for the first three; responsibility for the fourth is layered across provider, platform, organization, repository and user.STABLE E0 AI Governance Updated 2026-10-13
• ResearchRES-2026-0002PACC conjecture — do non-probabilistic primitives converge to probability-like structure?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.EXPERIMENTAL E3 SYNTHETIC Model Representation Updated 2026-09-09
• ResearchRES-2026-0004A PACC-style runtime on language models: reasoning, intent and creative breadthDoes 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.ACTIVE E2 SYNTHETIC Reasoning Updated 2026-09-09
• ResearchRES-2026-0001Blind derivation of an adaptive epistemic architectureStarting 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?ACTIVE E2 THEORY AI Architecture Updated 2026-09-08

• TheoryTHY-2026-0201Publication-boundary closure — the integrated frameworkGenerating, testing, scanning, reviewing and pushing are five propositions, none of which is that the delivered result respects its boundary. Information passes observed → authorized → persisted → published → externally obtainable, and each arrow is its own permission. Closure is evidence that covers the intended postcondition, not more checks.PRELIMINARY E1 THEORY Privacy Updated 2026-10-13
• TheoryTHY-2026-0202The green-light fallacyV₁(x) ∧ … ∧ Vₙ(x) = PASS does not imply G(x) = PASS unless the global postcondition G was mapped into their coverage. Checks that read the same source or share a generated oracle are not independent; a scope false PASS is a correct detector pointed at the wrong surface; NOT MEASURED is a result, never a pass.PRELIMINARY E1 THEORY Privacy Updated 2026-10-13
• TheoryTHY-2026-0203Agent context as an egress surfaceThe context an agent needs — project roots, runtimes, browser profiles, internal endpoints, credential-loading conventions — is written into instruction files, configuration, fixtures and generated documents, and crosses a boundary it was never written for once they are published. Nine context classes (C1 workstation path … C9 generated diagnostics) keep sensitivity and risk as separate axes. Phase II observed it among individuals, organizations and companies.EXPERIMENTAL E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• TheoryTHY-2026-0204From secret scanning to semantic privacyPattern detectors answer whether a known secret form is present; an artifact can still carry identity, paths, topology or a value split across constants and files with no literal match. Recoverability is graded R0 not recoverable … R4 literally present. A semantic AI detector is not an oracle; pattern evidence, semantic evidence, policy context and independent falsification are combined, and UNKNOWN stays an answer.PRELIMINARY E1 THEORY Privacy Updated 2026-10-13
• TheoryTHY-2026-0205Organizational propagation of agent context (hypothesis)Shared rules, templates, skills and scanners are supply-chain roots: one context error is inherited by every repository that copies it, a widely shared scanner's PASS carries more apparent authority than it earned, and copies of a policy age at different speeds.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13
• TheoryTHY-2026-0206AI build–attack asymmetry (hypothesis)AI lowers the cost of building something that works faster than the cost of building something secure, and may lower the cost of finding weak targets. The hypothesis is narrow and does not claim that current AI is a universal attacker.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13

• ClaimCLM-2026-0201H1 — AI-assisted repositories disclose more than matched non-AI repositoriesAI-assisted repositories disclose more than matched non-AI repositories.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13
• ClaimCLM-2026-0202H2 — Shared organization context amplifies one disclosure pattern across many repositoriesShared organization context amplifies one disclosure pattern across many repositories.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13
• ClaimCLM-2026-0203H3 — Multiple AI reviewers sharing evidence roots overstate the independence of verificationMultiple AI reviewers sharing evidence roots overstate the independence of verification.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13
• ClaimCLM-2026-0204H4 — Conventional secret-scanning statistics undercount semantic privacy leakageConventional secret-scanning statistics undercount semantic privacy leakage.EXPERIMENTAL E1 THEORY Privacy Updated 2026-10-13
• ClaimCLM-2026-0205H5 — AI-assisted building grows low-maturity targets faster than defensive automation shrinks themAI-assisted building grows low-maturity targets faster than defensive automation shrinks them.PRELIMINARY E0 THEORY Privacy Updated 2026-10-13
• ClaimCLM-2026-0206HT — Organizations in transition into AI are a higher-risk band than AI-native onesOrganizations in transition into AI are a higher-risk band than AI-native ones.EXPERIMENTAL E1 THEORY Privacy Updated 2026-10-13

• ObservationOBS-2026-0206O6 — Individuals publish files their own AI tools treat as local, such as .claude/settings.local.jsonIndividuals publish files their own AI tools treat as local, such as .claude/settings.local.json.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ObservationOBS-2026-0207O7 — Published agent configuration files can carry concrete home-directory pathsPublished agent configuration files can carry concrete home-directory paths.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ObservationOBS-2026-0208O8 — Agent-related publication-boundary signals appear among individuals, organizations and companies alikeAgent-related publication-boundary signals appear among individuals, organizations and companies alike.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ObservationOBS-2026-0201O1 — AI collaboration files can themselves become publication surfacesAI collaboration files can themselves become publication surfaces.STABLE E1 Privacy Updated 2026-09-21
• ObservationOBS-2026-0202O2 — A checker reported PASS while recoverable excluded information sat inside the checker itselfA checker reported PASS while recoverable excluded information sat inside the checker itself.STABLE E1 Privacy Updated 2026-09-21
• ObservationOBS-2026-0203O3 — Public AI collaboration files can contain concrete workstation, runtime, session and internal-network contextPublic AI collaboration files can contain concrete workstation, runtime, session and internal-network context.STABLE E1 Privacy Updated 2026-09-21

• ExperimentEXP-2026-0101Experiment A — single-pass vs scaffolded controlled measurement (protocol v0.1)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.ACTIVE E0 INCONCLUSIVE NOT RUN Evaluation Updated 2026-09-02

• ResultRST-2026-0201Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)In the frozen 60-repository company panel, the only high-warning cells were two L3 cells on AI-native companies' agent instruction files; the same repositories were L0 or L1 on README and governance files.STABLE E2 MIXED BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ResultRST-2026-0202Pooled F1–F4: high warnings on every surface — README 3.4%, agent instruction 3.0%, governance 0.9%Primary rule, 236 repositories: README 8/233, agent instruction 7/236, governance 2/235. Rounds swung from one high-warning cell to nine. The company panel's concentration on agent instruction files did not recur; the concrete-path kind (L3) still leans toward them.STABLE E2 MIXED BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ResultRST-2026-0203Individuals: 2.75% publish .claude/settings.local.json, 10.5% an agent configuration fileOf 400 individual AI-assisted repositories, 11 published .claude/settings.local.json — a file Claude Code itself keeps out of git — and 42 published an AI agent configuration file. Five of the six high-warning agent-state cells were home-directory paths inside MCP, editor or agent configuration files. No agent conversation history appeared in this frame.STABLE E2 POSITIVE BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ResultRST-2026-0204Individual-era rule finds about twice the high-warning repositories of the organization-era rule (34 vs 17 of 400)The organization-era rule cannot see personal email addresses outside contact wording, private network addresses on operational lines, or paths inside configuration files; the individual-era rule adds them, each pre-registered.STABLE E2 POSITIVE BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ResultRST-2026-0205Registered prediction not supported: people using three or more AI tools do not leak moreP1 suggested that repositories with three or more detected AI tool families publish local files and high-warning content more often. Written down before P2 was opened; P2 reversed it.STABLE E2 NEGATIVE BLIND PUBLIC DATA Privacy Updated 2026-10-13
• ResultRST-2026-0206The frozen instrument still runs and its evidence still says what was published212 tests passed (1 skipped); all six auditors passed; 2/40, 0/59, 0/51 recomputed from released cells.STABLE E2 POSITIVE BLIND PUBLIC DATA Privacy Updated 2026-10-13

Data · 5

• DatasetDAT-2026-0201Phase I released features — company panel, README pass and surface matrixFeature-only evidence of the frozen 60-repository panel: 180 surface-matrix cells with neutral identifiers, the bridge aggregate and the README pass. No identity, path or source text.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• DatasetDAT-2026-0202Phase II released features — rounds F1–F4Pre-lock cells of 236 repositories (708 cells), locks, sampling accounting and aggregates. Owner type is released only as aggregates.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• DatasetDAT-2026-0203Phase II released features — individuals P1–P2Pre-lock cells and repository rows of 400 individual repositories (866 cells), locks, accounting and aggregates. The AI-tool profile and star band are released only as aggregates.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• DatasetDAT-2026-0001PACC synthetic evidence worldsDeterministically generated micro-environments: 4 hidden hypotheses × 6 binary prototypes with per-feature reliabilities; source-quality worlds for learned reliability (20 worlds / 280 episodes / 28 observations at primary scale); correlated-cluster worlds with latent shared inversion at q ∈ {0.06 … 0.42}; and regime-switching dynamic worlds. Primary seeds 20260908 (v0.1) and 20260909 (v0.3+); secondary seeds are labelled post-hoc.STABLE E2 SYNTHETIC Evaluation Updated 2026-09-09

Benchmarks · 4

• BenchmarkBEN-2026-0001PACC micro-lab protocol v0.1 (frozen gates)The preregistered decision rule reused unchanged from v0.1 to v0.13: E0 purity, held-out representation distance D_R = E[JS(Φ(S_N), S_P)] ≤ 0.05, update commutation D_U ≤ 0.05, off-manifold intervention D_I ≤ 0.08, action agreement ≥ 0.85, a shuffled-target negative control the real map must beat, a design-independence rule (agreement ≥ 0.999 and R² ≥ 0.995 collapse two designs into one family), verdict levels 0–3, and a strong PACC-A gate of at least three independent convergent families.STABLE E2 Evaluation Updated 2026-09-09
• BenchmarkBEN-2026-0003PACC-LLM Hybrid A/B/C benchmarkThree conditions over identical candidate pools: A generator-only, B hard verifier, C PACC runtime (plus post-hoc D 'elastic'). v0.1: 7 categories × 28 tasks × 8 pools × 112 candidates (1,568 shared pool instances). Metrics: explicit hard adherence, derived coherence, soft-intent satisfaction, long-horizon retention, raw and valid novelty, pattern entropy. v0.2: 16 hand-authored natural-language tasks, equal accounted budgets, gold rubric visible only to a condition-blind judge.EXPERIMENTAL E2 Evaluation Updated 2026-09-09
• BenchmarkBEN-2026-0002AER-0 architecture-comparison suite (R1–R6)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.EXPERIMENTAL E2 Evaluation Updated 2026-09-08
• BenchmarkBEN-2026-0101XA-02 — 30-task pilot pack for the A0→A5 scaffolding response30 tasks — 10 math, 10 code, 10 constraint — with a public task file (prompt, output contract, pre-registered quality projection), a private reference file that must never enter model context, a deterministic evaluator and a 30/30 self-test. Math and constraint answers are one JSON object; code answers are Python source scored by hidden tests, and code execution is refused unless explicitly enabled inside an external sandbox. The pack's own words: not a general intelligence benchmark but a controlled instrument for measuring scaffolding response under Experiment A.STABLE E2 Evaluation Updated 2026-09-02

• ProgramPRG-2026-0201AI Agent Publication Boundary and Security Closure (APBSC)What do AI coding agents carry from a private workspace into public repositories, and how can that be measured without anyone reading other people's leaks? Phase I (ten papers, 2026-09-21) built the vocabulary — the five-state information chain, the green-light fallacy, agent context as an egress surface, recoverability, warning levels — and RBPM, a researcher-blind algorithm whose only observer of repository content is a sealed machine process. Phase II (2026-10) ran it on fresh public samples of companies, organizations and individuals and found agent-related publication-boundary signals in every population. The study stops there by decision: going further would mean reading what people did not mean to publish. Algorithm, protocols, released features and reports are open source.STABLE E2 AI Safety Updated 2026-10-13
• ProgramPRG-2026-0001Adaptive Epistemic SystemsA 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.ACTIVE E2 Updated 2026-09-09
• ProgramPRG-2026-0101Intelligence Physical Metrology (IPM)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.ACTIVE E2 Evaluation Updated 2026-09-07

• ModelMOD-2026-0006Qwythos-9B-v2 (Q4_K_M, local, Ollama)Open-weight 9.0B model of the qwen35 family, GGUF Q4_K_M, served locally by Ollama 0.33.3 on an RTX 3070. Used as generator, selector and judge in the real local run of the PACC-Hybrid v0.2 protocol, with thinking disabled in runs 1–2 and enabled (effort medium, +3,500 output tokens per call) in run 3.STABLE E2 REAL MODEL Evaluation Updated 2026-09-11
• ModelMOD-2026-0001N0 — signed supportAdditive signed evidence support per hypothesis; under uniform reliability it is closely related to rescaled log-evidence accumulation, which is why the heterogeneous and adversarial stresses exist.STABLE E2 SYNTHETIC Model Representation Updated 2026-09-09
• ModelMOD-2026-0002N1 — ordinal tournamentPairwise ordinal competition between hypotheses; behaviourally and linearly identical to N0 on every tested trajectory.STABLE E2 SYNTHETIC Model Representation Updated 2026-09-09
• ModelMOD-2026-0003N2 — signed graphSigned relation graph over hypotheses with graph dynamics; the basin-boundary family — fails the representation threshold under adversarial geometry (v0.2), is less stable under high correlation (v0.4), and has the narrowest, seed-sensitive transfer basin (v0.8).STABLE E2 SYNTHETIC Model Representation Updated 2026-09-09
• ModelMOD-2026-0004N3 — constraint competitionA nonlinear constraint-field system added in v0.2 as the third structurally distinct family; converges bidirectionally across geometries (v0.7) and shares the wider N0/N1 basin (v0.8).STABLE E2 SYNTHETIC Model Representation Updated 2026-09-09
• ModelMOD-2026-0005Bayesian reference (exact posterior / Beta-Bernoulli / joint common-cause / HMM)The probabilistic side of every comparison: exact posteriors with numerical reliabilities, Beta-Bernoulli source-quality learning, the joint-likelihood common-cause model for correlated clusters (and its naive-independence negative control), and a Bayesian HMM for regime switches.STABLE E2 SYNTHETIC Model Representation Updated 2026-09-09

• PaperPAP-2026-0211AI Agents and the Public Boundary — the APBSC integrated public edition v1.0The program's public text, replacing the ten internal drafts: the vocabulary and arguments of Phase I, the researcher-blind algorithm, what it observed among companies, organizations and individuals in Phase II, what held, what did not, the defects found and handled in the open, the ethics statement and why the study stops. English and Traditional Chinese.STABLE E2 BLIND PUBLIC DATA Privacy Updated 2026-10-13
• PaperPAP-2026-0009Paper 09 — Probability is not BayesianA layered vocabulary from stochastic to generalized Bayesian and a Bayesian authenticity test for updates that are only redescribed as Bayesian.STABLE E0 THEORY Formal AI Updated 2026-09-10
• PaperPAP-2026-0005Paper 05 — Memory, algorithm libraries and reusable solution pathsAlgorithms, tools, contracts, costs and outcome history become capability nodes; Reuse ≻ Adapt ≻ Create.STABLE E0 THEORY Computation Updated 2026-09-08
• PaperPAP-2026-0006Paper 06 — Substrate-neutral computational containersAny execution environment with representable input, valid transition and readable output is a compute container; algorithms and containers are scheduled jointly.STABLE E0 THEORY Computation Updated 2026-09-08
• PaperPAP-2026-0007Paper 07 — Blind-derived AI: do different first principles converge on one engineering form?Treats the first six papers as a blind-derivation experiment and proposes a protocol and five levels of similarity for comparing the result with modern AI.STABLE E1 THEORY AI Architecture Updated 2026-09-08
• PaperPAP-2026-0008Paper 08 — Intelligent architecture attractors: at which level does difference live?Six levels of architectural difference, architecture equivalence classes and attractor basins; the executed architecture is the architecture.STABLE E0 THEORY AI Architecture Updated 2026-09-08

• SystemSYS-2026-0201RBPM v0.8.3 — the frozen researcher-blind measurement instrumentX → N → D → S → F → A → O in a sealed process: detectors for paths, networks, secret-like material and semantics; a feature builder; a context-necessity estimator; the Company Warning Gate (L0–L4); governance signals; an egress guard; independent auditors. Frozen 2026-09-22 and reused unchanged by every Phase II round (source digest recorded in each LOCK.json).STABLE E2 BLIND PUBLIC DATA Evaluation Updated 2026-10-13
• SystemSYS-2026-0202RBPM v0.8.4 fresh runner — surface-balanced sampling (F1)Code-search draw by size band, sealed screening, three surfaces per repository, an independent confirmation pass, neutral IDs, lock and an auditor that imports none of its code.STABLE E2 BLIND PUBLIC DATA Evaluation Updated 2026-10-13
• SystemSYS-2026-0203RBPM v0.8.5 runner — rounds F2–F4 with a corrected secondary ruleThree rounds in one sealed process with in-memory de-duplication; the F1 rule kept as primary for pooling, and every high-concern class confirmed separately with a seven-line local necessity window as the secondary rule.STABLE E2 BLIND PUBLIC DATA Evaluation Updated 2026-10-13
• SystemSYS-2026-0204RBPM v0.9 runner — individuals with AI-collaboration markers (P1–P2)Individual owners only, created within two years, five AI-instruction frame families with equal quotas, an agent-state surface (tool-local files, agent configuration, agent history), a sealed AI-collaboration profile, an email class, structured-file rules and a JSON secret-shape rule.STABLE E2 BLIND PUBLIC DATA Evaluation Updated 2026-10-13
• SystemSYS-2026-0002PACC-Lab — micro-lab harness for the convergence conjectureFully observable evidence-integration environments, four primitive-level non-probabilistic families (N0–N3), exact Bayesian references, train-only low-complexity mappers, shuffled/constant/broken-composition controls, a design-redundancy diagnostic and frozen preregistered thresholds carried unchanged from v0.1 through v0.13. Each release is a sealed FINAL bundle with its protocol, results and next-experiment preregistration.EXPERIMENTAL E3 Model Representation Updated 2026-09-09
• SystemSYS-2026-0003PACC-LLM Hybrid LabAn A/B/C harness — generator only, hard verifier, PACC runtime — over shared candidate pools with equal accounted budgets. v0.1 is a synthetic architecture witness (zero LLM calls); v0.2 adds hand-authored natural-language tasks, a condition-blind judge, literal machine checks independent of the judge, fail-closed behaviour without an API key, and frozen-cache replay for exact reproduction after a live run.EXPERIMENTAL E2 Reasoning Updated 2026-09-09

Research graph → · research-graph.json · relations.json

• ExperimentEXP-2026-0205Confirmatory 200 + 200 matched study (paper 07) — designed, not run by decisionA preregistrable design with a matched non-AI control group, unique-repository sampling and preserved UNKNOWN states, built to answer prevalence and difference questions. Not run: the program stopped at indirect observation rather than read what people did not mean to publish.ARCHIVED E0 INCONCLUSIVE NOT RUN Privacy Updated 2026-10-13
• PaperPAP-2026-0201Paper 00 — Agentic publication boundary and security closure: the integrated frameworkPhase I paper 00, v0.1, 2026-09-21. An internal research draft; its public replacement is the integrated edition (PAP-2026-0211). A checked summary is on the program site.SUPERSEDED E0 THEORY Privacy Updated 2026-10-13
• PaperPAP-2026-0202Paper 01 — The green-light fallacy: when agent verification succeeds and the real postcondition does notPhase I paper 01, v0.1, 2026-09-21. An internal research draft; its public replacement is the integrated edition (PAP-2026-0211). A checked summary is on the program site.SUPERSEDED E0 THEORY Privacy Updated 2026-10-13
• PaperPAP-2026-0203Paper 02 — Agent context as an egress surfacePhase I paper 02, v0.1, 2026-09-21. An internal research draft; its public replacement is the integrated edition (PAP-2026-0211). A checked summary is on the program site.SUPERSEDED E0 THEORY Privacy Updated 2026-10-13
• PaperPAP-2026-0204Paper 03 — From secret scanning to semantic privacyPhase I paper 03, v0.1, 2026-09-21. An internal research draft; its public replacement is the integrated edition (PAP-2026-0211). A checked summary is on the program site.SUPERSEDED E0 THEORY Privacy Updated 2026-10-13
• PaperPAP-2026-0205Paper 04 — Organizational agent context propagationPhase I paper 04, v0.1, 2026-09-21. An internal research draft; its public replacement is the integrated edition (PAP-2026-0211). A checked summary is on the program site.SUPERSEDED E0 THEORY Privacy Updated 2026-10-13

Research status says where a line is in its life; evidence level says how much has been shown. They are recorded separately on purpose: ACTIVE or STABLE is not a truth claim, and an ARCHIVED line can still carry E4 evidence.

Data basis says what a number was measured on. Synthetic results are labelled SYNTHETIC on every card and page: they are evidence about the architecture under synthetic conditions, not about the world.