[MACHINE-SPIRIT 7/8] Meta-reasoning and bounded self-improvement: failure learning, strategy evolution, rule promotion, self-model and expert synthesis #394
Labels
No labels
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
nsaspy/prolog-rlm#394
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Parent: #397
Related: #376 #377 #379 #381 #384 #385 #386 #388 #392 #395
Downstream: symbolic-memory#4 #6 #7 #9 #10 and implementation epic/slices #16 #33-#36 #43
Distinct research mandate
Treat learning how to reason better as the primary problem: symbolic experience, bounded learning, controlled promotion, rollback, self-models, expert composition, adversarial contamination control, cross-domain transfer and computational conformance.
Hard invariant: self-improvement may improve symbolic knowledge/strategy but may not silently widen host capability/authority or promote arbitrary model-generated Prolog into trusted executable code.
Depth 7 status — DESIGN-COMPLETE, IMPLEMENTATION-UNPROVEN
All four required subpasses are durably preserved in this issue's comments.
A — EPOCH: COMPLETE
Experience, Promotion & Operational Control Hierarchy establishes immutable symbolic experiences, distinct EBG / ILP-failure / case / strategy-performance candidate lanes, versioned promotion/evaluation policy, append-only admission/suspension/supersession and declarative expert composition.
B — CITADEL-EPOCH: COMPLETE
Contamination-Isolated, Tamper-Aware, Drift-Explicit Learning safeguards adds candidate exposure freeze, evidence-use roles, source/causal dependence, adaptive holdout accounting, metric/verifier noninterference, bounded counterexample campaigns, safe-baseline comparison, diagnosis-aware labels and drift/calibration epochs.
C — PACT-EPOCH: COMPLETE
Provenance-Attested Cross-Trust Learning Interchange adds a versioned Learning Artifact Contract (LAC), typed source attestations, loss-aware transfer assessments and target-local promotion.
D — CLOCKWORK-EPOCH: COMPLETE
Conformance-Locked, Ordered, Crash-safe Knowledge-Workflows for Replayable EPOCH makes A/B/C computational.
D hard decisions
independent=true. Hidden/missing provenance yieldsunknown.exact_symbolicfor finite/decidable proof obligations;bounded_counterexamplefor bounded generators/enumeration/SMT;paired_sequential_improvementfor empirical strategy improvement against admitted baseline; optionallogged_off_policyonly when logged-support assumptions hold.alpha_n = alpha_family * 6/(pi^2*n^2)before candidate n consumes validation data, ensuring the family allocation remains bounded. Richer e-value/FDR policies require separate explicit profiles.unknown; PSI/OPRF is not mandatory v1 infrastructure.stale_evaluation/conflict, not admission.rlm_async/ #288 facilities. Learning-control state does not become an execution scheduler.model_calls = 0.Conformance direction
The #404D comment records D1-D50 falsifiable fixtures covering canonical LAC encoding/signatures, exposure/dependence/retraction, adaptive statistical evaluation, exact-vs-bounded counterexample coverage, drift/transfer invalidation, crash/retraction/promotion races, differential cold/warm/rebuilt/incremental learned-state equivalence, exact replay, authority separation, foreign import and provider-disabled known-symbolic learning.
No scale claim is accepted from prose: exposure graph, counterexample, evaluation-stream and incremental-maintenance thresholds require measured implementation benchmarks.
Reconciled Depth-7 architecture
Repository ownership
prolog-rlm
symbolic-memory
The library-first implementation graph #11/#16/#33-#36/#43 is the natural implementation landing zone. Existing #4/#6/#7/#9/#10 remain canonical domain contracts.
Unresolved implementation/synthesis questions
Completion statement
Depth 7 A/B/C/D is design-complete only. Implementation and Machine Spirit acceptance remain unproven.
Exact next research work: Depth 8 / #405A — baseline cross-depth synthesis and minimum Machine Spirit v1 architecture/conformance graph.
Do not start #405B/C/D until #405A is durably complete.
Machine Spirit program progression
Depth 6 / #403 A-B-C-D is now durably design-complete and reconciled; #403 is closed for design completion only.
Exact next research subpass: #404A — meta-reasoning / bounded self-improvement foundations and representative formalisms only.
Do not execute #404B/C/D in the same run. A should establish candidate architectures for symbolic experience, meta-reasoning, explanation-based/case/strategy learning, lesson/rule promotion stages, failure learning, rollback/supersession, self-model/meta-goals and expert composition while preserving the hard boundary:
#403/RACE-TAPS now supplies deterministic bounded retrieval/projection receipts and strategy execution evidence that #404 may learn from; #404 must not mutate retrieval truth or silently promote operational statistics into epistemic facts.
Machine Spirit #404A — foundations / representative formalisms
Status: A COMPLETE — B NEXT.
This subpass treats meta-reasoning and bounded self-improvement as a symbolic learning/control problem, not as permission for a model or runtime to rewrite its own trusted code.
Research questions
Primary evidence
Classical and current sources used in this pass:
chunk/ explanation-based chunking documentation. https://soar.eecs.umich.edu/reference/cli/cmd_chunk/These mechanisms make materially different guarantees. EBG/Soar-style chunking derives an operational generalization from an explanation/proof; ILP searches a constrained hypothesis language against examples and counterexamples; Popper's generate-test-constrain loop learns from failed hypotheses; PRODIGY emphasizes that a learned control rule is useful only if its application benefit exceeds its matching/control cost; bounded-optimality work makes resource limits part of rational strategy selection rather than an afterthought.
Repository-local precedent also matters:
research/RLM-RESEARCH-008-adaptive-recursion.orgalready separates execution from promotion. Its deeper-recursion experiment requires live multi-fixture evidence, positive quality delta, bounded cost/latency and zero capability/budget/cancellation failures before promotion. That exact numeric gate is not universal, but the architecture is correct: successful execution is evidence for a promotion decision, not the promotion decision itself.Candidate architectures
Candidate 1 — universal Soar-style chunking
Every solved subgoal/explanation automatically produces a reusable production/control rule.
Strengths: cheap reuse after expensive reasoning; directly connected to proof/explanation; excellent fit for deterministic symbolic subproblems.
Rejected as the universal architecture: operationality matters; generated chunks can over-specialize, over-generalize, or create expensive matching/control behavior. One successful derivation also does not justify a universal procedural/world rule. Automatic chunk admission would collapse experience into trusted policy too early.
Candidate 2 — one central ILP learner over the experience corpus
Represent successful/failed episodes as examples and learn rules/procedures with Popper/ILASP/FastLAS-style constrained search.
Strengths: explicit hypothesis language; positive/negative examples; counterexamples; interpretable learned programs; defaults/exceptions/preferences are possible in richer ILP families; learning-from-failure can prune huge hypothesis spaces.
Rejected as the sole architecture: not every improvement is a logic-program induction problem. Strategy selection, cost/latency routing, case adaptation, explanation-based specialization and expert composition have different semantics. Hypothesis search is also combinatorial and extremely sensitive to bias/example construction.
Candidate 3 — performance-only strategy portfolio
Keep fixed strategies and learn which one works best for each task/context from observed quality/cost/latency.
Strengths: bounded, practical, naturally supports meta-level resource decisions.
Rejected as the full self-improvement model: it cannot create reusable symbolic explanations, rules, procedural abstractions or expert compositions. Performance statistics alone are not semantic knowledge.
Preferred — EPOCH: Experience, Promotion & Operational Control Hierarchy
EPOCH is a staged multi-lane learning fabric over existing Machine Spirit components.
The foundational distinction is:
1. Symbolic experience is first-class
A completed or aborted reasoning attempt should emit an immutable, replayable experience envelope rather than free-form retrospective prose.
Conceptual data:
Important: the experience records what was tried and what was observed. A successful episode is not itself a rule. A failed episode is not automatically a negative example for every rule implicated in the attempt.
The envelope must distinguish predicted effects from observed effects, local strategy failure from authority denial, and semantic failure from resource exhaustion/cancellation.
2. Candidate-generation lanes stay distinct
Explanation / EBG lane
Use a trusted existing theory/explanation to derive an operational candidate from a successful or failed proof slice. Candidate stores the explanation dependency graph, operationality conditions and assumptions.
Good use: specializing a known general procedure/control rule to a recurring context.
Bad use: inventing a universal causal fact from one unexplained success.
ILP / learning-from-failures lane
For closed declared hypothesis languages, build explicit positive/negative/context-dependent examples and search bounded hypotheses. Popper-style failure constraints are attractive because a failed hypothesis prunes related hypotheses rather than merely incrementing a reward score. Fine-grained SLD failure explanations can further tighten those constraints.
This lane must declare:
No unrestricted generation of arbitrary callable Prolog.
Case / procedural abstraction lane
Verified cases may propose reusable method fragments, branch policies or adaptation constraints. They remain candidates until #401/DPEC-compatible procedure validation plus promotion succeeds.
Strategy-performance lane
Maintain empirical operational profiles over existing strategies/experts/planners/retrievers:
These statistics may drive bounded strategy choice. They are operational evidence, not epistemic warrant.
3. Promotion is an explicit lifecycle
Recommended foundational states:
Not every knowledge class needs every stage. Promotion policy is typed by risk/knowledge class.
Conceptual record:
A candidate cannot modify its own promotion policy. Promotion policy is trusted/versioned host or admitted semantic policy, not learned merely because the learner requests it.
The existing adaptive-recursion gate is a concrete repository example of a promotion policy. EPOCH generalizes the shape, not its exact
20 trials / 3 fixturesthresholds to every rule class.4. Meta-goals are ordinary typed symbolic goals
Do not add an ambient reflective interpreter. Meta-reasoning enters the same expert/planner machinery through explicit goals such as:
#288 remains the scheduler. #377 remains the expert invocation boundary. #384 remains the acceptance boundary for world/task success.
5. Self-model is empirical and versioned
Machine Spirit may maintain a bounded self-model of its own observed competence:
This supports
which strategy works here?andwhat do I not know?without claiming omniscient introspection.Hard distinction:
Russell/Subramanian-style bounded optimality is the right direction: optimize behavior relative to architecture/task/resource constraints, rather than search forever for globally optimal reasoning.
6. Expert synthesis means declarative composition, not arbitrary handler generation
Recurring successful cooperation can yield a candidate declarative composition such as:
This composition refers only to registered contracts and normal typed goals. Admission validates that the referenced expert versions/contracts exist and preserves the caller's capability/authority ceiling.
It does not create a new executable closure/handler. If a genuinely new expert implementation is required, that is ordinary trusted code/configuration work outside automatic promotion.
7. Rollback is append-only supersession, not history rewrite
Learned semantic/control objects are immutable/versioned. Current admission is a projection over lifecycle events:
Historical runs preserve the exact strategy/rule/composition versions used. Replaying an old run must not silently substitute today's replacement rule.
8. Comparison with current Prolog-RLM / Symbolic Memory
The current architecture already has the right boundaries but no complete learning fabric:
RLM-RESEARCH-008already demonstrates execution-vs-promotion separation for adaptive recursion.What #404A adds is the missing typed bridge between those experiences and admitted reusable strategy/rule knowledge.
9. Complexity / scaling
resource_limited, never arbitrary first hypothesis;10. Epistemic / provenance implications
A learned object must expose:
Do not flatten this into
confidence=.92.Correlated/mirrored episodes do not count as independent validation simply because they are separate rows. #400/#402 source-dependence semantics apply to learning evidence too.
11. Safety / authority
Hard A invariants:
Learned knowledge may rank/select among already admissible strategies or propose semantic methods/rules. It may never silently create capabilities, widen read/write scope, relax Frozen Specs, mutate VERIFY criteria, or bypass effect admission.
12. Adversarial/failure review
A-foundation failure cases already visible for B to attack more deeply:
B must attack these explicitly; A does not claim they are solved by a threshold.
13. Rejected shortcuts
assertz/1lessons after success — rejected: collapses observation, induction, validation and admission.14. Falsifiable #404A fixtures
A1. successful episode persists as experience but creates no admitted rule automatically.
A2. failed episode persists without becoming a negative semantic example by default.
A3. identical replay records preserve exact strategy/expert/rule versions.
A4. EBG candidate exposes every proof assumption used for generalization.
A5. hidden/unproved EBG assumption blocks admission.
A6. bounded ILP fixture learns a rule covering positives and excluding negatives.
A7. one negative counterexample rejects an over-general candidate when policy requires consistency.
A8. context-dependent examples do not flatten into one global rule.
A9. hypothesis-search exhaustion returns
resource_limited, not first-found promotion.A10. model-proposed candidate remains inert before schema/profile validation.
A11. learned semantic action has zero host capability absent an existing trusted binding.
A12. learned expert composition can reference only existing compatible registered contracts.
A13. composition cannot widen caller capability/authority ceiling.
A14. unknown/removed expert version makes composition stale/unsupported.
A15. strategy statistics alter selection preference but cannot alter #400 warrant for a proposition.
A16. stale performance profile is rejected for a current-only strategy decision.
A17. two mirrored episodes do not satisfy an independence requirement for promotion.
A18. VERIFY failure prevents an episode from being labeled successful merely because the worker reports success.
A19. authority denial is preserved as policy/blocked outcome and is not learned as a system fault.
A20. resource exhaustion/cancellation is not converted into negative semantic evidence.
A21. promotion receipt names exact evaluation cuts/fixtures and policy version.
A22. candidate cannot modify its promotion policy or VERIFY acceptance rules.
A23. admitted rule can be suspended after a counterexample without deleting history.
A24. superseding v4 leaves historical v3 runs exactly replayable.
A25. canary/shadow evidence is labeled distinctly from production evidence.
A26. regression under admitted strategy produces a new experience and can trigger suspension policy.
A27. case-based procedural candidate still passes #401/DPEC validation before use.
A28. learned method still executes through #288 and requires fresh #384 VERIFY.
A29. known symbolic strategy-selection fixture completes with providers disabled and
model_calls = 0.A30. symbolic candidate-validation fixture completes with providers disabled and
model_calls = 0.A31. self-generated examples cannot alone satisfy a policy requiring independent external/held-out validation.
A32. promotion evaluation cannot weaken/remove a Frozen Spec obligation to improve its score.
Canonical issue changes required by A
Unresolved questions reserved for later subpasses
#404B — semantic/adversarial deepening
Poisoning of experience, reward hacking/Goodhart effects, self-confirmation, label leakage, concept drift, contradictory lessons, confidence/calibration, catastrophic promotion, strategic manipulation of VERIFY, unsafe self-model loops, and promotion under noisy/partial evidence.
#404C — heterogeneity/interoperability
Transfer/federation of learned rules across theories/namespaces/ledgers, ontology mappings, heterogeneous ILP/EBG/case/performance learners, expert portfolio interoperability, cross-formalism procedural learning, and non-flattening composition of learning guarantees.
#404D — computational realization/conformance
Incremental experience indexes, hypothesis-space/search bounds, candidate invalidation, shadow/canary execution mechanics, deterministic async learning, replay, promotion dependency graphs, scale benchmarks and executable differential conformance.
A conclusion: use staged, typed, provenance-heavy learning. Machine Spirit may learn reusable semantic/control knowledge and better strategy selection, but learned knowledge never becomes its own authority plane.
Exact next legal subpass: #404B — semantic/adversarial deepening.
Machine Spirit #404B — semantic/adversarial deepening
Status: B COMPLETE — C NEXT.
This pass attacks EPOCH's hidden assumption that a staged promotion lifecycle is safe merely because it has more stages. It is not. A sufficiently adaptive learner can contaminate its own validation evidence, optimize proxies until they diverge from intended quality, bias the distribution of future experiences, manipulate or overfit its verifier, and then cite those self-shaped observations as evidence that it should be trusted more.
The result is CITADEL-EPOCH — Contamination-Isolated, Tamper-Aware, Drift-Explicit Learning safeguards for EPOCH.
The core rule is:
and the stronger promotion boundary is:
Research questions / scope
B asks:
Out of scope for B: heterogeneous federation of multiple learning/promotion systems is C; execution-scale/indexing/replay algorithms are D.
Primary evidence
Classical and current primary/authoritative sources used in this pass:
Repository evidence:
research/RLM-RESEARCH-008-adaptive-recursion.orgalready has the correct execution-vs-promotion distinction: live multi-fixture evidence is required and deterministic fixture evidence cannot self-promote deeper recursion.docs/evolution-kernel.mdalready keeps fitness vectors, evaluator identity and candidate lineage separate, rejects arbitrary generated callable operators, and explicitly leaves promotion/rollback outside the generic evolution kernel.These are compatible with CITADEL; they are not sufficient by themselves because a learning loop can still reuse or influence its own evaluation data.
Candidate architectures
Candidate 1 — fixed hidden benchmark / sealed regression suite
Every candidate is evaluated against a hidden, trusted benchmark; promotion occurs if its score exceeds a threshold.
Strengths:
Failure:
Rejected as the complete architecture.
Candidate 2 — Bayesian/global confidence learner
Maintain posterior confidence/trust for each learned rule/strategy from successes/failures; automatically promote above a threshold and decay under failures.
Strengths:
Failure:
Rejected as the universal model. Probabilistic/calibration profiles may exist for declared empirical strategy classes only.
Candidate 3 — always-online bandit/RL adaptation
Treat strategy/expert/rule selection as an online decision problem and continuously update from reward/VERIFY outcomes.
Strengths:
Failure:
Accepted only as an optional bounded strategy-selection mechanism inside the stronger promotion firewall.
Preferred — CITADEL-EPOCH
CITADEL wraps EPOCH in an explicit evidence-independence, evaluator-noninterference and drift-control layer.
CITADEL does not add another scheduler or verifier. It defines which evidence #404 promotion may accept and how it must classify uncertainty/contamination.
1. Evaluation evidence is a separate semantic class
EPOCH A recorded experiences and promotion receipts, but B requires explicit evidence roles:
The same observation may be retained in history under several relations, but it cannot count as statistically/epistemically independent evidence merely because it has multiple IDs.
Conceptual record:
Hard rule:
Ten retries, ten mirrors, ten model summaries, or ten derived features from the same underlying outcome do not create ten independent validations.
2. Candidate exposure closure is first-class
Every candidate gets an exposure closure describing what could have influenced its content/parameters/selection.
Conceptually:
A validation fixture is contaminated for that candidate if its answer/expected result/material derivation is in the candidate's exposure/causal ancestry under the configured independence policy.
Important: exact byte duplication is not required for leakage. A paraphrase, derived rule, model-generated summary, prior failed validation message, or previously promoted rule can carry the relevant information.
CITADEL therefore treats contamination as a provenance/causal relation, not only text overlap.
3. Adaptive evaluation has an explicit information budget
Dwork et al.'s adaptive-data-analysis result matters directly: repeated adaptive decisions based on one holdout can invalidate naive significance/generalization claims.
CITADEL does not require differential privacy for v1, but it adopts the architectural consequence:
insufficient_independence.This prevents:
H is now training evidence for candidate_2.
4. Promotion metrics are typed by semantic role and tamper surface
No universal
rewardorfitnessscalar.Conceptual contract:
Roles:
hard_guard: invariant violation blocks promotion regardless of average score;proxy_objective: may be optimized, but is explicitly a proxy;audit: deliberately not a direct optimization target where possible;cost: resource/latency/model usage;coverage: evaluation search/fixture completeness, never correctness by itself.Hard Goodhart rule:
If the candidate can causally influence a metric's evaluator/input channel, that metric is
tamper_exposedand cannot be the sole promotion gate.5. VERIFY noninterference becomes a learning invariant
#384 already owns final task acceptance. B strengthens the learning use of VERIFY:
A candidate-generated test can be useful generation/selection evidence. It becomes independent validation only after a separate trusted policy admits that test without relying on the candidate's assertion of adequacy, and even then the test's provenance remains visible.
Verifier/config/spec fingerprints are frozen into each evaluation receipt. A candidate that changes the verifier, benchmark, test oracle or evidence-admission policy invalidates that evaluation lane unless the change itself is separately authorized and a fresh evaluation generation is created.
6. Hidden evaluator != sufficient evaluator
AI Safety Gridworlds' hidden performance function is a useful conceptual separation between observed reward and intended behavior, but secrecy alone is insufficient.
CITADEL prefers orthogonal evaluation channels:
Different evaluator implementations are not automatically independent if they share the same source oracle/data.
7. Counterexample search is mandatory for generalization claims
For rule/method candidates, promotion includes a typed hostile search obligation:
Sources may include:
no counterexample foundunder a bounded search means exactly that. It is not a proof of universal correctness unless the declared finite/decidable search space was exhaustive.8. Safe-improvement is relative to an admitted baseline
For empirical strategy/control candidates, CITADEL requires comparison to an admitted baseline under the same declared task/context distribution.
Possible evaluation profiles:
Thomas et al. and Petrik/Chow/Ghavamzadeh provide useful precedents for lower-confidence-bound / robust-baseline reasoning when executing a poor policy is costly.
CITADEL does not claim their RL guarantees automatically transfer to arbitrary expert systems. It adopts the design requirement:
not:
For deterministic finite symbolic fixtures, promotion can instead be proof/differential based; do not force fake probabilities onto exact checks.
9. Selection bias and self-fulfilling competence are recorded
An admitted strategy changes which tasks it sees, which actions it attempts, which evidence is gathered and therefore what future success statistics look like.
Example failure:
CITADEL records selection policy/context/eligibility for each experience. If candidate A and baseline B were not plausibly evaluated on comparable contexts, the promotion evaluator returns
selection_bias_unresolvedrather than treating raw success rates as causal improvement.Where policy permits, bounded randomized/shadow challenge allocation can provide cleaner evidence. High-risk/effectful exploration remains authority- and safety-gated.
10. Concept drift creates validity epochs, not memory rewriting
Learned rules/strategy profiles are scoped to context and evaluated epochs.
Conceptually:
Possible status:
ADWIN is a strong candidate detector for streaming numeric performance/error signals because it adapts window length and has formal false-positive/false-negative bounds. It is not a universal semantic drift oracle.
Hard behavior:
not:
Bitemporal #402 history preserves what was admitted, when, and under which environment generation.
11. Contradictory/noisy experience does not become majority truth
Experience labels are typed by failure/observation class and provenance.
A failed run can mean:
Therefore:
#385 diagnosis evidence determines which learning lanes may treat an outcome as a candidate counterexample.
Correlated labels remain grouped by origin/dependence. Contradictory evidence may justify scoped alternatives/defaults rather than a global winner.
12. Calibration is an empirical property, not trust or truth
For empirical selection policies, a confidence score may be calibrated against observed correctness/outcome rates for a declared cohort/version.
Guo et al. is useful evidence that raw model confidence can be poorly calibrated and post-hoc calibration can improve probability estimates. The architectural consequence is:
Calibration has a domain/time/profile fingerprint and must be re-evaluated under drift.
13. Self-models are advisory and non-authoritative
EPOCH's self-model may record:
But a self-model cannot:
A self-model observation can influence which strategy to try. It cannot define what counts as successful evidence for that strategy.
14. Catastrophic violations are not averaged away
Promotion policies may declare hard zero-tolerance classes:
One such violation may quarantine a candidate even if average quality improves.
This is different from ordinary stochastic task failure.
15. Promotion lifecycle is refined
Recommended B lifecycle:
Not every candidate class uses all stages, but
admittedmust never be reachable without the required evidence roles and independence checks for its risk class.16. Typed promotion receipt
Conceptual form:
The receipt explains both why promotion happened and what the evidence does not establish.
Complexity / performance / scaling implications
CITADEL adds real cost; it is intentionally not free.
Exposure/lineage checking
Exact candidate/evidence contamination checking is graph reachability over provenance/derivation/exposure edges. With indexed ancestry and immutable digests, ordinary checks are proportional to the demanded reachable lineage rather than the whole ledger. Worst-case ancestry can approach total history.
Use #402 shared provenance DAGs, source-dependence components and generation fingerprints. Do not duplicate entire provenance trees per candidate.
Counterexample search
Generally combinatorial/undecidable for open rule languages. Every campaign declares:
Exhaustive claims are legal only for a declared finite/decidable fragment where exhaustive completion is proven.
Adaptive holdout
Maintaining fresh independent cohorts costs data. Candidate search cannot consume an unlimited sequence of free validation queries. D must choose practical cohort-rotation/reveal-budget mechanics.
Drift
Streaming detectors such as ADWIN can be sublinear-memory summaries; semantic-context drift may require heavier structured checks. Drift monitoring is a trigger for reevaluation, not proof of a new rule.
Strategy evaluation
High-confidence/off-policy estimators may have high variance and need substantial data; robust safe-improvement formulations can be computationally hard. Return
insufficient_evidence/resource_limitedinstead of manufacturing confidence.Epistemic / provenance implications
CITADEL adds new provenance classes that must remain independent of #400 epistemic warrant:
A promotion receipt is operational/control knowledge. It does not make the learned proposition a source-explicit fact.
For a learned rule, explanations should answer:
Safety / authority implications
Hard B invariants:
Promotion may change which already-authorized semantic/control knowledge is selected. It may not enlarge the host's capability/authority envelope.
Adversarial review / failure cases
B explicitly rejects the following attacks/failures:
Rejected shortcuts
Falsifiable B conformance fixtures
At minimum implement/prove these later; design IDs B1-B40:
no_counterexample_within(bounds)not universal truth.model_calls = 0.Canonical issue changes required by B
#404
Adopt CITADEL-EPOCH as the B refinement over EPOCH. Mark A+B COMPLETE / C NEXT. C must focus on interoperability/federation between heterogeneous learners, validators, promotion authorities, stores and organizational/domain boundaries without flattening their evidence semantics.
#397
Depth 7 becomes A+B COMPLETE / C NEXT. #404C only is authorized after this B persistence; #405 remains blocked.
#384 VERIFY Expert
Add learning-specific noninterference requirements:
#385 Repair/Diagnosis Expert
Learning labels must consume diagnosis/failure class. A failed attempt is not automatically a negative example for every implicated rule/method/strategy. Preserve causal attribution uncertainty.
#386 Review/Critic Expert
Add candidate-independent adversarial counterexample campaigns and explicit status that Review-generated findings/tests are candidate evidence until grounded; Review cannot self-promote learned review policy.
#377/#379/#381
Learned operational statistics and self-models may influence selection only as typed advisory/control evidence. They may not change truth, authority, obligations or VERIFY. Strategy routing must preserve selection-policy/context lineage so #404 can detect self-selection bias.
#392/#394/#395
Learned candidate/admission/evaluation status remains separate from source truth and epistemic warrant. #395 should add contamination/Goodhart/drift/promotion conformance classes, especially provenance-grouped splits and candidate-exposure leakage.
symbolic-memory #6
Persist immutable experience, candidate exposure, evidence-use roles/origin groups, metric/evaluator versions, promotion/quarantine/suspension/supersession receipts and drift/calibration lineage. These are semantic/control history, not one mutable confidence field.
symbolic-memory #7
Query/explanation must expose learned-object status, applicability epoch/scope, evidence independence/contamination findings, baseline/evaluation profile, counterexamples, calibration/drift and promotion limitations.
symbolic-memory #9
Native/MCP transport must not flatten to
learned=true,confidence=N, orpromoted=true; preserve candidate/admitted/quarantined/suspended and evidence limitations. No transport caller may mark evidence independent merely by assertion.symbolic-memory #10
Identity/source reconciliation must participate in evaluation-origin grouping: aliases, mirrors, same-event references and derived copies cannot defeat contamination/source-dependence checks by receiving new IDs.
Repository ownership boundary
prolog-rlm owns:
symbolic-memory owns:
Host/trusted configuration owns:
A learned object may reference these; it cannot redefine them.
Unresolved questions reserved for C
Unresolved questions reserved for D
cold == warm == rebuilt == incrementalconformance for promotion decisions.B completion statement
#404B is design-complete only.
It does not prove any self-improving implementation exists, and it does not satisfy the Machine Spirit executable bar.
Surviving Depth-7 architecture after A+B:
Exact next subpass: #404C — composition / heterogeneity / interoperability of learning, validation, promotion and self-model evidence.
Do not start #404D or #405 until #404C is durably complete.
Machine Spirit #404C — composition / heterogeneity / interoperability
Status: C COMPLETE — D NEXT.
This subpass treats learned-rule/strategy portability as an interchange and transfer-validity problem, not as replication of
admitted=trueacross systems.Research questions / scope
Primary evidence
Primary/authoritative sources used in this pass:
10.1007/s10994-009-5152-4. The target-error bound depends on source error, source/target divergence, and the existence/error of a hypothesis good for both domains: source success alone is not a target guarantee. https://link.springer.com/article/10.1007/s10994-009-5152-4These sources support a common conclusion: portable provenance/attestation is feasible; portable validity is conditional. Domain-adaptation theory makes the condition explicit mathematically, while provenance/attestation standards show how claims can move without becoming ambient trust.
Candidate architectures
Candidate 1 — global learned-object registry with universal status
Replicate
{payload, status=admitted, confidence=.93}into every memory and let all hosts consume the same status.Strengths: simple UX, easy dedup/federation.
Rejected. It launders source promotion authority, evaluation conditions, source dependence, drift scope and calibration into unrelated targets.
admittedhas no context-free meaning.Candidate 2 — copy payload only; discard all source evaluation metadata
External rules/procedures arrive as fresh local candidates with no inherited evidence.
Strengths: safe and conceptually simple; no validation laundering.
Rejected as the full design. It throws away useful provenance, counterexamples, source assumptions, verifier receipts, failure history, applicability scopes and evidence that can cheaply guide target validation. It also makes independent-origin reasoning impossible.
Candidate 3 — federated consensus / majority promotion
If enough memories or organizations admit the same candidate, consider it admitted globally.
Rejected. Replica/source dependence and shared training/evaluation lineage can make ten approvals one causal origin. Different authorities can also have incompatible policies or environments. Vote count is not target validity.
Preferred — PACT-EPOCH: Provenance-Attested Cross-Trust Learning Interchange for EPOCH
The central invariant is:
1. Learning Artifact Contract (LAC)
Define a versioned typed interchange object rather than flattening all learners to one rule schema.
Conceptual shape:
Learner-specific payload/guarantee information remains typed:
A common envelope is therefore not a common guarantee.
2. Attestations are claims, not imported truth
Use an in-toto/SLSA-like pattern:
Example predicate types:
A valid signature proves who made the claim and artifact integrity, not that the proposition is universally true.
Target policy decides which issuers/predicates are admissible evidence and at what strength.
3. Target admission always has a local state
Default import mapping:
A target may record:
as provenance, but that is distinct from:
Only the latter affects ordinary target control selection.
A narrowly configured same-trust-domain optimization may reuse prior validation when all material fingerprints and declared applicability/environment assumptions are equivalent and target policy explicitly permits it. The optimization is an explicit proof/receipt, never name-based trust inheritance.
4. Validation guarantees use a non-strengthening algebra
Every imported guarantee carries scope and assumptions.
Conceptual status transformation:
Bridge operations may preserve or weaken a source guarantee. They may not strengthen it without new target evidence.
Examples:
5. Domain transfer is an explicit obligation
Ben-David-style domain-adaptation bounds motivate the correct qualitative contract:
Machine Spirit should not pretend it can estimate every term universally. Instead an imported candidate declares a transfer profile:
Relevant dimensions can include schema/vocabulary, task/goal distribution, project/runtime version, data/source populations, authority policy, resource envelope, verifier semantics, platform, dependencies, temporal epoch and failure modes.
If target overlap/equivalence cannot be established, the safe result is
requires_local_validation, notprobably_portable.6. Multi-source learning does not become vote counting
When several foreign memories provide related learned objects, preserve source-specific hypotheses and provenance. Composition may:
Do not automatically majority-vote promotion statuses or average incomparable quality metrics.
Mansour/Mohri/Rostamizadeh multi-source adaptation is useful precisely because it treats source combination as an adaptation problem with assumptions, not as
n approvals => truth.7. Cross-ledger evidence dependence is privacy-aware but conservative
CITADEL requires causal/source independence; CLFM says ledgers are independent order/authority domains. Cross-domain interchange therefore needs an origin/dependence interface that does not require dumping private source identities.
Conceptual public claim:
Rules:
Conservative failure is preferable to validation laundering.
8. Promotion authorities remain namespaced
Represent:
without selecting an ambient winner.
A target policy may explicitly trust one authority, require local validation, require multiple named authorities, or forbid external promotion evidence for a risk class.
Conflicting authority receipts are durable plural evidence. They never become one synthesized
confidencenumber.9. Procedure/expert portability stops before execution admission
Portable semantic method/procedure:
Therefore:
A foreign expert composition imports only declarative goal/component contracts. It cannot import handlers, shell commands, credentials, capabilities or authority.
10. Calibration and drift are scoped artifacts
A calibration result must name:
Moving it across any of those dimensions creates a transfer obligation. Under distribution shift, nominal calibration/coverage need not survive; recent conformal work continues to require explicit assumptions or correction for covariate/general shift.
Target monitoring creates a new local calibration/drift lineage rather than mutating the source report.
11. Repository ownership
prolog-rlm owns
symbolic-memory owns
Dependency remains
symbolic-memory -> prolog-rlm. Symbolic Memory stores portable learning artifacts and their history; Prolog-RLM defines/validates their semantics and decides target-local admission.existing expert/runtime layer owns
No new scheduler or authority plane. #288 remains scheduler; #384 remains exact requirement acceptance boundary; ordinary capability/effect checks remain authoritative.
Complexity / performance / scaling
noncomposable/resource_limitedrather than first-map wins.D owns concrete indexing, cache keys, incremental invalidation, attestation verification cost, large-scale overlap/dependence structures and deterministic concurrent import/evaluation execution.
Epistemic / provenance implications
PACT-EPOCH adds a sixth important provenance concern on top of semantic/source/logical/lifecycle/runtime provenance: learning-transfer provenance.
A target explanation must be able to answer:
No imported
confidence, approval count or signature substitutes for these answers.Safety / authority implications
Hard invariants:
External artifacts cannot mutate target promotion policy, verifier policy, Frozen Spec, read/egress policy, expert registry, host bindings or authority.
High-risk target classes may require entirely local validation regardless of external receipts.
Adversarial review / failure cases
admitted; target blindly activates it.musttoshouldbut preserves status.admitted=trueinto canonical payload, losing authority namespace.Rejected alternatives
confidence: incomparable and launders semantics;unknown;Falsifiable #404C conformance fixtures
C1.
source_admitted_imports_as_foreign_candidate_not_local_admitted.C2.
source_promotion_attestation_preserved_without_target_activation.C3.
source_quarantine_cannot_import_as_clean_candidate.C4.
source_retraction_invalidates_target_transfer_assumption.C5.
signed_attestation_authenticates_issuer_not_semantic_truth.C6.
unknown_issuer_policy_does_not_grant_validation_strength.C7.
same_verifier_name_different_fingerprint_is_non_equivalent.C8.
stricter_target_verifier_requires_target_validation.C9.
exact_finite_proof_replays_under_identical_theory_profile.C10.
lossy_ontology_mapping_weakens_or_invalidates_guarantee.C11.
ambiguous_mapping_remains_alternative_or_noncomposable.C12.
ebg_dependency_missing_in_target_blocks_preserved_guarantee.C13.
ilp_background_theory_change_requires_revalidation.C14.
case_platform_mismatch_requires_target_applicability_check.C15.
statistical_policy_distribution_shift_drops_source_calibration_claim.C16.
source_calibration_epoch_does_not_become_target_current_epoch.C17.
target_drift_creates_local_suspension_without_rewriting_source_history.C18.
replicas_do_not_count_as_independent_promotion_authorities.C19.
same_upstream_benchmark_collapses_dependence_across_organizations.C20.
privacy_hidden_origin_defaults_to_independence_unknown_not_independent.C21.
opaque_origin_commitments_can_signal_same_origin_without_raw_source_disclosure.C22.
unverified_disjointness_claim_does_not_count_as proven independence.C23.
two_conflicting_promotion_authorities_remain_plural_evidence.C24.
target_policy_can_require_local_validation_despite trusted source.C25.
foreign_expert_composition_imports_no_handler_or_authority.C26.
foreign_semantic_action_remains_inert_until local DPEC/binding admission.C27.
same_expert_name_cannot_rebind_principal_or_authority.C28.
metric_vectors_with_incompatible_definitions_are_not_averaged.C29.
source_validation_exposed_to_target_learning_is_reclassified_for descendants.C30.
translation_receipt_lists preserved weakened unsupported assumptions.C31.
unknown_learning_artifact_schema_fails_closed.C32.
source_policy_version_is_part_of_attestation_identity.C33.
redacted_source_evidence_downgrades reproducibility/guarantee state.C34.
cached_transfer_assessment_invalidates_on mapping/profile/drift/source-status change.C35.
multi_source_candidate_union_preserves per-source provenance.C36.
majority_source_approval_does_not_auto_promote.C37.
exact_equivalent payload fingerprints do not erase independent episode provenance.C38.
target_explanation_reports source and local promotion receipts separately.C39.
foreign artifact cannot mutate Frozen Spec/verifier/promotion policy/read scope.C40.
known symbolic import/compatibility/admission checks run with providers disabled and model_calls=0.Concrete canonical deltas
A+B+C COMPLETE / D NEXT.learned=true,approved=true, or one score.Unresolved questions reserved for D
Completion statement: #404C is design-complete only. It does not prove any learned artifact is safe to transfer, nor does it establish Machine Spirit. #404D is the only legal next subpass.
Machine Spirit #404D — computational realization / scaling / deterministic conformance
Status: D COMPLETE — Depth 7 ready for reconciliation.
This pass makes EPOCH + CITADEL + PACT executable as a bounded, replayable learning-control dataflow over the existing runtime. It does not introduce a second scheduler, a second authority plane, or a generic scalar-reward loop.
Preferred architecture: CLOCKWORK-EPOCH — Conformance-Locked, Ordered, Crash-safe Knowledge-Workflows for Replayable EPOCH.
Research questions
Primary evidence used
10.1126/science.aaa9375. Shows ordinary holdout reuse is invalid under adaptive analysis and gives a principled reusable-holdout construction.10.1214/20-AOS1991. Confidence sequences remain valid uniformly over time and support optional stopping under their assumptions.PAE(payloadType,payload)and intentionally authenticates exact payload bytes/type rather than relying on application reserialization.predicateType.Candidate computational architectures
Candidate 1 — one global learned-state table + mutable scores
Maintain current candidate rows, a scalar score, flattened holdout status, and periodically overwrite
admitted=true/false.Rejected. It destroys historical replay, cannot represent source/causal dependence, makes adaptive holdout leakage invisible, has no principled crash/race semantics, and turns heterogeneous guarantees into one score.
Candidate 2 — fully materialized global provenance/exposure closure + universal statistical promoter
Materialize transitive closure between every source/candidate/evaluator/fixture, feed every candidate through one statistical safe-improvement evaluator, and globally union equivalent origins.
Rejected. Closure can be O(V²) or worse in dense graphs; ATMS/provenance environments can explode; irreversible union-find-style merges are wrong under retraction/versioned identity; many symbolic candidates have exact finite proof obligations rather than stochastic performance semantics; statistical evaluation cannot manufacture a theorem for semantic correctness.
Candidate 3 — event-only ledger with full recomputation on every decision
Persist only immutable events and recompute all exposure, evaluation and transfer state from genesis on every promotion.
Semantically clean but rejected as the normal execution model. It remains the correctness oracle/rebuild path, but ordinary operation requires exact rebuildable indexes and dependency-directed incremental maintenance.
Preferred — CLOCKWORK-EPOCH
1. Canonical learning ledger is append-only; indexes are disposable
Canonical durable objects/events include:
Current candidate state, exposure closures, strategy summaries, validation eligibility and transfer caches are rebuildable derived views.
This follows the same canonical-vs-derived rule already established by #402/SAFIRE and symbolic-memory#6.
2. Exposure/dependence graph: direct facts canonical, closure query-scoped
Use typed nodes such as:
and typed directed/undirected relations such as:
Maintain exact adjacency indexes in both directions. Do not require global transitive-closure materialization.
A candidate's exposure closure is computed by bounded graph traversal from a frozen candidate/version and evidence frontier. Cache the normalized closure/interface digest against graph generation. Direct-edge changes invalidate only descendants/dependents known by reverse indexes.
Worst-case exact traversal remains
O(V+E)over the reachable subgraph. Incremental/cache maintenance is workload optimization, not a stronger guarantee.Important accelerator rule:
A negative independence claim requires complete exact closure for the declared graph/profile. Missing/hidden provenance yields
independence=unknown, never true.Do not use irreversible DSU/union-find as canonical source-dependence truth. Active dependence equivalence/components are versioned rebuildable views because origin/identity mappings can be retracted/superseded.
For larger workloads, semi-naive/incremental view maintenance is the first implementation step. Differential-dataflow/DBSP-style machinery is optional if measurements justify nested incremental graph maintenance; no second universal runtime is required for v1.
3. LAC byte identity + attestation verification
Define a closed LAC v1 typed data model first. Reject cyclic/non-ground objects and unknown critical schema/profile fields.
Preferred cross-language canonical payload:
Conceptually:
For JSON-only boundaries, RFC 8785 JCS is an allowed adapter fingerprint profile, but it is not silently considered byte-identical to CBOR. Exact numeric/rational semantics must be explicit; security-sensitive fingerprints should not depend on ambiguous host floating-point serialization.
Attestation transport:
DSSE is preferred for signatures because PAE binds exact payload bytes and content type, avoiding reserialization confusion.
Verification returns distinct fields:
A valid signature never sets
semantic_claim_status=verifiedby itself.4. Candidate freeze and immutable EvaluationSnapshot
Before validation evidence is consumed, freeze:
Evaluation observations cite this snapshot exactly. A candidate/descendant exposed to an observation cannot later reclassify it as fresh validation.
5. Three primary evaluation profiles + one specialized profile
exact_symbolicUse for finite/decidable symbolic rules, procedure invariants, schema contracts, capability boundaries and equivalent deterministic properties.
Mechanisms:
Only this class may report
coverage=exhaustivewhen the declared domain/solver fragment is actually exhaustive/complete.bounded_counterexampleUse property generators, SmallCheck-style finite-depth enumeration, QuickCheck-style seeded generators, bounded model/constraint search, and delta-debug/shrinking of found failures.
Receipt contains:
Hard rule:
paired_sequential_improvementDefault empirical promotion profile when candidate and admitted baseline can both be evaluated on the same fresh target-task stream.
For each target task
i, compute a predeclared bounded utility delta:where utility components/weights are fixed by the metric contract and catastrophic hard guards remain separate rather than averaged into utility.
Use a time-uniform confidence sequence (empirical-Bernstein or another declared valid CS) for mean delta. Promotion requires:
Optional stopping is allowed only because the selected CS/e-process profile explicitly supports it.
Repeated adaptive candidate families consume a precommitted summable risk allocation. Simple v1 family-wise profile:
assigned before candidate
nconsumes validation data, sosum alpha_n <= alpha_family. Each candidate's sequential interval uses its allocatedalpha_n. This is deliberately conservative but auditable; richer e-value/FDR policies can be separate named profiles rather than implicit upgrades.The guarantee applies only when the candidate is frozen before its fresh validation stream and the declared CS assumptions hold. If these conditions fail, the receipt is weakened/invalidated rather than silently reused.
logged_off_policy— optional/specializedOnly for strategy/control policies where logged-action propensities/support and required statistical assumptions are actually available. High-confidence OPE lower bounds may be used. If support/propensity requirements are missing, return
unsupported/hold.SPIBB-style guarantees are restricted to an explicitly declared compatible finite-MDP/batch-RL profile. They are not the default theorem for arbitrary Prolog expert selection.
6. Reusable holdout policy: no magical forever-holdout in v1
Dwork et al. prove adaptivity must be part of the validation mechanism. CLOCKWORK therefore does not implement
hidden=trueas a validity guarantee.V1 default:
A differential-privacy reusable-holdout mechanism may be added as a named future evaluation profile with its own privacy/validity budget. It is not silently approximated.
7. Concrete safe-improvement policy
Promotion is candidate-kind specific.
If evidence cannot establish improvement over the admitted baseline, the action is hold, not "best observed wins".
Hard-guard classes remain zero-tolerance regardless of average utility:
8. Drift and calibration are epoch/dependency scoped
An admitted learned object's active applicability is bound to an evaluation epoch including at least:
Structural generation changes are deterministic invalidators and can immediately require reevaluation/suspension according to policy.
For numeric streaming performance/error drift, ADWIN is an admissible detector profile because it supplies explicit statistical guarantees under its model. It is not a semantic-drift oracle. Store detector version/config/input stream ordering and decision receipt so replay can reproduce the decision.
A detector observation may create
drift_suspected; policy decides whether confirmation is required. A hard incompatible environment/verifier/schema change may directly make an admissionstale/inapplicablewithout waiting for statistical detection.9. Privacy-preserving origin overlap — conservative v1 decision
V1 does not require general cross-organization PSI/OPRF infrastructure.
Within one configured trust/federation domain, allow privacy-scoped opaque
origin_group_idor keyed commitments generated by a trusted origin service. Never expose raw private fixture IDs and never use unsalted/public hashes of low-entropy private identifiers as a privacy mechanism.Across trust domains where a shared comparison mechanism is absent:
not independent.
RFC 9497 VOPRF/POPRF or a dedicated PSI protocol is a legitimate later mechanism for privacy-preserving equality/intersection checks, but adding one requires its own threat model/key lifecycle and must not be smuggled into v1 merely to avoid returning
unknown.10. Incremental invalidation graph
Promotion/transfer caches depend on explicit generations:
Reverse dependency indexes identify impacted candidates/transfers. Recompute only affected nodes. Propagation may stop if a recomputed normalized interface digest is unchanged.
This mirrors #402D/#403D: direct generation/delta invalidation first; DBSP/differential-style general incrementalization only after workload evidence.
11. Crash-safe promotion lifecycle
Promotion is a conditional append-only state transition, not a mutable flag.
Conceptual API:
Commit atomically appends the promotion event only if:
Otherwise return
stale_evaluation/conflictand do not admit.No promotion transaction changes host capability/authority or executable handler registration.
12. Deterministic race semantics
Important source-retraction/evaluation race:
Both produce a current state in which the candidate is not silently active, while preserving the actual historical order. Wall-clock timestamp is not the arbiter; canonical ledger/frontier order and dependency generations are.
Concurrent duplicate promotion requests use candidate/version + snapshot fingerprint idempotency. Same key/same digest returns same logical transition; same key/different digest is conflict.
13. Explainability/replay receipt
Every active learned selection can resolve:
Exact historical replay requires retained nondeterministic observations/model artifacts. Re-running a remote model/evaluator later is a new observation lineage, not exact replay.
Complexity / scaling implications
O(log N)or backend-specific equivalent;O(V+E)reachable graph, with generation-keyed memoization;O(V²);O(1)incremental summary per metric per observation for standard streaming CS implementations, plus retained audit samples/refs per policy;Epistemic / provenance implications
independence=unknownis a first-class valid result.Adversarial/failure review
CLOCKWORK explicitly fails closed on:
Rejected alternatives
unknown;D conformance fixtures
Canonicalization / attestation
D1. Equivalent normalized LAC emits identical deterministic CBOR bytes/fingerprint.
D2. Semantically different LAC emits different fingerprint.
D3. Map/input serialization order cannot change LAC fingerprint.
D4. Unknown critical LAC schema version is quarantined.
D5. DSSE payloadType substitution invalidates signature verification.
D6. Valid source signature + untrusted issuer does not become accepted source guarantee.
D7. Trust-root rotation invalidates/reclassifies only dependent attestation views.
Exposure/dependence
D8. Ancestor candidate exposure propagates to descendant closure.
D9. Source copy/paraphrase with explicit origin edge remains dependent.
D10. Retracted mistaken dependence link changes current closure without destroying historical closure.
D11. Missing private provenance returns independence
unknown.D12. Probabilistic accelerator negative cannot produce
independent=true.D13. Cold closure == cached closure for same graph generation.
D14. One unrelated provenance edge update does not invalidate unrelated candidate closure.
Adaptive/statistical evaluation
D15. Candidate fixed before fresh validation can consume assigned alpha tranche.
D16. Candidate exposed to validation result cannot reuse that result as fresh validation.
D17. Sequential stopping at first LCB crossing preserves declared anytime-valid policy receipt.
D18. Fixed-time interval used with optional stopping is rejected by profile validation.
D19. Sum of allocated candidate-family alpha never exceeds family budget.
D20. Candidate with positive mean proxy but failed hard guard is quarantined.
D21. Candidate whose LCB never clears required margin remains held.
D22. Baseline fingerprint changes mid-run -> stale evaluation.
D23. Metric contract/range changes mid-run -> stale evaluation.
D24. Unknown OPE support/propensity -> unsupported/hold, not promoted.
D25. Exact finite symbolic candidate can promote without statistical sampling when exhaustive proof obligations pass.
Counterexamples
D26. Finite declared domain exhaustive enumeration reports
exhaustiveonly after all cases checked.D27. Search hitting case/work/depth limit reports
bounded/resource_limited.D28. Found property counterexample is retained with generator/seed/profile.
D29. Shrinking/delta-debugging retains a witness that still reproduces the failure.
D30. No bounded counterexample found never emits universal-correctness status.
Drift/transfer
D31. Structural verifier/schema/environment generation change invalidates dependent admission.
D32. Numeric ADWIN-style drift observation is stored as detector-relative evidence, not semantic truth.
D33. Confirmed material drift appends suspension; historical admission remains queryable.
D34. Foreign transfer cache invalidates when translator/ontology/target verifier changes.
D35. Source calibration receipt cannot satisfy target calibration after population epoch change.
Crash/race/replay
D36. Crash before promotion append -> no admitted state after restart.
D37. Crash after durable promotion append but before projection/cache write -> rebuild restores admitted state.
D38. Concurrent duplicate same transition is idempotent.
D39. Same idempotency identity + different decision digest -> conflict.
D40. Source retraction committed before promotion -> promotion stale/rejected.
D41. Promotion committed before source retraction -> later append-only invalidation/suspension; current candidate inactive.
D42. Different async evaluator completion permutations normalize to same decision for fixed evidence set/profile.
D43. Cold rebuild == warm cache == cache-drop/rebuild == incremental current learned-state view for same exact frontier/generations.
D44. Historical replay resolves exact candidate/policy/verifier/LAC versions originally used.
D45. Live remote/model re-evaluation produces new observation lineage, not exact replay.
Authority / zero-model
D46. Admitted learned semantic method does not create handler registration.
D47. Admitted expert composition resolves only registered target-local expert contracts.
D48. Promotion operation cannot widen capability/authority ceiling.
D49. Imported source
admittedLAC remains target candidate until local admission.D50. Known symbolic experience → exact candidate validation → local promotion decision → selection executes with providers disabled and
model_calls=0.Repository ownership
prolog-rlmOwn:
Reuse existing
rlm_async/ #288 for latency-bearing evaluation. Do not create a learning scheduler.symbolic-memoryOwn:
The newly created library-first implementation graph #11/#16/#33-#36/#43 is the natural landing zone; existing #6/#7/#9/#10 remain canonical semantic-memory domain contracts.
Concrete canonical deltas
unknown; no mandatory PSI/OPRF dependency.Unresolved questions reserved for Depth 8 synthesis
Completion statement
Depth 7D is design-complete only. This research defines executable algorithms, state transitions and falsifiable fixtures but does not claim they are implemented or that Machine Spirit exists.
After canonical reconciliation, the exact next legal research work is Depth 8 / #405A — baseline cross-depth synthesis and minimum Machine Spirit v1 architecture/conformance graph. #405B/C/D remain blocked until A completes.
Depth-8 #405B cross-layer note (does not reopen Depth 7): AEGIS-MS generalizes CITADEL/CLOCKWORK contamination tracking beyond learned-candidate evaluation. When a learned candidate can influence retrieval, verifier/profile/metric/test/control selection used in a later Machine Spirit acceptance decision, that influence must appear in the end-to-end acceptance closure and may make the strong result circular/contaminated. #404's candidate freeze, exposure roles, independent evaluation and append-only lifecycle remain unchanged; #405 owns this cross-layer composition constraint.
Depth 8C cross-layer handoff — PACT remains intact
CONCORDAT-MS generalizes PACT's transfer rule across the full Machine Spirit federation boundary:
A foreign LAC now crosses through an explicit directional federation contract carrying semantic/profile mapping, provenance disclosure, source trust-root generation and target appraisal policy. It still lands as
foreign_candidate|evidence_only|quarantinedaccording to target policy; source admission cannot become target admission by signature/bridge composition.This does not reopen Depth 7. It is a Depth 8 composition constraint feeding #405D conformance.