| Local reference consumption | Filter the verified preview by explicit candidate ID, improving forces and responsibilities; emit corpus/packaging citations, force costs and conditional relations; clarify or return no match | [reference_consume.py](scripts/reference_consume.py); deterministic metadata filtering, not natural-language retrieval, applicability or compatibility proof |
| Consumer event preparation | Produce a schema-v1 event with verified release pins, explicit provenance, unknown or evidenced producer outcomes, immutable file and exact collector-index digest | [Consumer instructions](feedback/ConsumerIntegration.md#local-lookup-and-closeout-helper); does not install hooks, enroll sources or independently verify outcome/lineage |
| Current research corpus | Inspect 18 developed candidate hypotheses with evidence profiles and retained source/runtime reviews | [Evolution report](research/evolution/EvolutionReport.md); the additional live candidate is outside frozen 0.1, no canonical admissions |
| Implementation mappings | Locate scoped mechanisms for transactional and offline recovery | [TransactionalRecovery](technologies/TransactionalRecovery.md), [OfflineRecovery](technologies/OfflineRecovery.md); no product supplies a certified complete configuration |
| Metadata and publication checks | Validate contract examples, candidate inventory/hashes, classification, evidence locators and immutable release artifacts | `make schema-test evolution-check classification-check reference-check`; checks establish structural traceability, not source truth |
| Research bench | Plan and execute bounded source investigations, retain failures, screen structure and explicitly replay compatible cached runs | [Bench adapter](research/bench/README.md); paid inference uses llm-connect and its task authorization/budget, not automatic invocation |
| Learning visibility | Read a selected retrospective ledger, prospective protocols, measured/unknown effort, immutable snapshots and comparison readiness | [ComparisonWindows.json](research/evolution/ComparisonWindows.json); 8 prospective cycles in 7 declared groups, none reaches the 3-cycle review trigger |
| Deterministic scheduled reporting | Observe retained natural daily, weekly and October 1 monthly reports from activity-core | [Receipt reconciliation](docs/evidence/2026-10-04-loop-reconciliation.json); zero enrolled consumers, dated owner health snapshot, no admitted pattern-editing executor |
The frozen preview and live research are separate version surfaces. Published candidate
prose is read at its corpus revision; release documents and evidence locators are read
at the packaging revision. Legitimate new research does not rewrite the old preview.
## Evidence limits and unavailable capabilities
The four walkthroughs (VC-01/02/03/06) are synthetic drafts or provisional studies;
six validation cases are planned. The named files under `architectures/` are research
stubs, not developed or validated architecture decompositions. General, content and
collaborative sequences contain provisional scaffolding beyond the two developed core
paths. Vocabulary and catalog names do not constitute additional implemented patterns.
The consumed development pilot scored 18/24 in each presentation condition after
model-review adjudication. It establishes neither a naming benefit nor equivalence.
Independent human scores, fresh-scenario replication and decision-time evidence remain
missing. M1/M2 remain revise/defer, and canonical admission is open. Full canonical graph
export, held-out retrieval evaluation and real-repository applicability studies retain
their recorded prerequisites. Eight disclosed preview navigation cases are development
checks; they are not held-out retrieval results.
Full-contract recurrence, production fitness, accessibility conformance, native crash
and off-device recovery guarantees are not established by the scoped source studies or
authored runtime fixtures. Seven prospective cycles have positive recorded research
time; LEARN-0017's time is unknown. A matching group label is not proof of comparability,
and there is no basis for a diminishing-returns or plateau claim.
The capability entry and hosted-publication preparation exist, but hosted federation
registration and eligible consumer integration lack acceptance evidence. The consumer
roster is empty; eligible-task coverage and usefulness are unknown. Deterministic
collection/reporting is implemented by activity-core, while producer closeout integration,
real use plus linked outcomes, delayed-outcome refresh, admitted bounded investigation,
authenticated publication and automatic rollback remain incomplete. Reporting schedules
are not proof of a closed autonomous improvement loop.
## Boundaries
Research covers framework-independent authority, addressability, projection, mutation,
recovery, interaction, composition and delivery decisions. Additional coverage must
come from useful questions, contrasting contexts and traceable evidence. Authoring,
validation and qualified reference improvements are in scope; canonical admission and
stronger evidence claims require the existing reviews.
Do not turn the deliverable into a framework ranking, component cookbook, general
frontend runtime or universal architecture prescription. Do not infer maturity from
catalog size, fixtures, model agreement or automation definitions. Do not fabricate
human ratings, historical effort, consumer use, complete contract recurrence or
unsupported guarantees. Policy/access/budget changes in the operating loop remain
monthly human decisions; qualified reference work can continue within existing scope.
## Work and assessment ownership
[WP-0009](workplans/FEP-WP-0009-m1-independent-validation.md) owns the independent M1
validation residual of finished WP-0002. [WP-0003](workplans/FEP-WP-0003-contrasting-schools.md)
owns architectural contrasts, broader walkthroughs and M2; [WP-0004](workplans/FEP-WP-0004-reference-surface.md)
owns gated canonical export, held-out retrieval and real-repository evaluation.
