NSTD.7:5 - Archetypal Grounding

NSTD.7:5.1 - Generated-narrative pipeline: graph-to-text case

An AI agent receives a concept graph and produces a polished explanation. The author compares the needed dependency and example relations with the draft, evaluates consequential losses and repairs the account. The optional record below supports repetition of that comparison.

GeneratedNarrativeUseNote@GraphToTextTeaching:
  sourceMaterialRef: concept graph with dependency, example, counterexample and evidence links
  requiredRelationsOrConstraints: prerequisite chain, contrast pairs, evidence-return points
  generationMethodRef: LLM-assisted graph-to-text workflow
  contentPlanRef: selected nodes and relations
  discourseOrEventPlanRef: didactic dependency order with a contrast reveal
  generatedDraftRef: prose candidate
  sourceComparison: required relations compared with their sentences
  evaluationRef: relevant NSTD.6 questions and results
  useDecisionOrRepair: repair any missing prerequisite before the learner uses that inference
  revisitCondition: source graph, generator behavior or reader result changes

Pipeline steps:

Select the nodes, relations and returns the learner needs.
Choose an order through NSTD.2, then generate a short draft.
Compare the draft with the graph. If it says “B occurs because A” but the graph supports only “A precedes B”, replace the causal claim or obtain the missing causal account.
Use NSTD.6 to assess the repaired version for the intended reading. The draft need not have been accepted before this assessment.
Keep the adequate result. For repeated improvement, use E.23 with the version, changed part, protected characteristics and comparison basis.

NSTD.7:5.2 - Probe suite for generated narrative

Probe	Question	Pass condition	Failure repair
Source perturbation	If one source relation changes, does the generated narrative change at the right place?	The affected sentence, order marker, or source-return link changes.	Recover source plan; do not rely on prompt fluency.
Structure recovery	Can a reader reconstruct selected source structure from the output?	Reader recovers nodes and relations needed for declared use and knows lost relations.	Add source-return markers or narrow declared use.
Responsibility	Who decides the consequential use and can correct it?	The applicable assignment or decision authority is recoverable.	Resolve that authority question; apply evidence or assurance checks only when those claims are made.
Schema use	Does the result satisfy the constraints that matter to its use?	Required fields and their semantic constraints are satisfied.	Repair the generator or result; use executable validation when it can test those constraints.
Improvement evidence	Is the new variant better under the relevant `NSTD.6` characteristics?	Re-evaluation supports the claimed change without losing protected results. A sufficient one-off comparison can finish here.	Keep an unsupported variant as a candidate. Use `E.22` if the question needs framing, or `E.23` for repeated improvement.

NSTD.7:5.3 - Before and after repair: generated seminar outline

Before:

The generated outline sounds coherent and covers all important ideas, so it can be used as a DPF learning route.

Failure: neither the needed source relations nor the learner’s task is identified. “Covers all important ideas” has no comparison basis.

After:

The outline selects EntityOfConcern, forces, solution, neighboring-pattern exits and the improvement loop, ordered by their teaching prerequisites. Compare those relations with the source and try the intended reconstruction task through NSTD.8 and NSTD.6. A worked design estimate can support a provisional lesson; a claim about what learners actually recover requires a reading or teaching trial. C.35 becomes relevant only if the generated result is being used to inform architecture work.

NSTD.7:5.4 - Generated-storycraft boundary

For a franchise continuation, compare the generated scene with the selected continuity, premise and character-motivation constraints. A surprising event is acceptable when those relations support it; if it relies on a contradiction, repair the event or change the stated premise. Source perturbation can test a recurring generator problem. A private critique and a publication have different permissions questions. NSTD.6 can evaluate the candidate before either use is accepted.

NSTD.7:5.5 - Calibration for generated narrative

Illustrative condition	Consequence for use
Fluent output contradicts a required source relation.	Repair that relation or narrow the proposed use.
Needed source relations are present, but a consequential reading remains ambiguous.	Use a targeted recovery probe or clarify the wording.
The inspected result supports the intended use at an acceptable cost.	Use it; no separate generation dossier is required.
A method improvement is claimed.	Compare versions under the same relevant conditions, including protected characteristics. Repeated or heterogeneous probes support only the generality they actually test.

NSTD.7:5.6 - FPF owner teaching

NSTD.7 connects content planning, realization and evaluation. A generated account has claims expressed through a publication form; its fluency alone does not establish those claims. Use C.2.8 for reader recovery, A.10 for evidence claims and B.3 for assurance claims when they arise. C.35 is restricted to generated or discovered results intended to inform architecture work. Source changes and changed generator behavior can reopen an earlier comparison.

An LLM drafts an explanation of FPF pattern use from notes. Compare its selected relations, order and returns with those notes and the applicable pattern content. NSTD.6 can assess the candidate immediately; if the necessary subject basis is missing, it leaves that amount unassigned while retaining independently supported defect findings. An absent generation journal does not erase visible product qualities or defects.

A graph-to-text system turns an event graph into a match recap. The event graph, source timestamp, uncertainty markers, and official-result refresh route are admitted source basis for this rendering. The generated recap is a carrier. If the system adds causal explanations not in the graph, those claims are not admitted by graph-to-text success. Repair by lowering causal language, adding source return, or opening the evidence owner.

A game story-planning pipeline generates a branching scene. The schema may require objective, location, actors, traits, constraints, and available actions. NSTD.7 treats those fields as method and source-plan support, not as proof of playable, coherent, or ethically acceptable narrative. Structural, semantic, executable, and human probes remain separate from fluency.

An LLM proposes themes from interview notes for qualitative narrative analysis. The generated theme list is not the researcher’s interpretation by default. Human interpretive agency remains live: the researcher checks source excerpts, reflexive stance, alternative readings, and admissible use before any narrative rendering or report uses the generated material.

Use these examples to distinguish evaluation from acceptance:

Generated account	Current evaluation or use decision	Reason
A fluent summary with an unknown source.	Assess visible narrative defects; leave source fidelity unresolved.	The source relation cannot yet be compared.
A graph-to-text candidate with event IDs and a stated order.	Evaluate through `NSTD.6`, then use or repair it.	Its needed relations and losses can be inspected without prior acceptance.
A schema-valid RPG scene contradicting a selected continuity constraint.	Unsuitable for that source-faithful use until repaired.	Field validity does not establish continuity.
An FPF seminar outline with source references and reconstruction tasks.	Evaluate its teaching route through `NSTD.8` and `NSTD.6`.	Product quality and actual learning-effect claims use different evidence.
A homotopy metaphor with an unstated analogy limit.	Diagnose the missing condition and clarify it.	An intuitive explanation can be evaluated before it is fit for proof-related reliance.

When automated repair is used, preserve version identity. “Regenerate until better” destroys improvement evidence. Record the previous carrier, changed prompt or method, selected changed slice, expected value movement, protected trade-offs, and re-evaluation route. A generated variant can be more fluent and still worse on epiplexity, source return, or agency discipline.

Pipeline variants by source type:

Source type	Content plan	Discourse or story plan	Admission danger	Evaluation focus
Knowledge graph or event graph	Select nodes, edges, event ids, uncertainty, and omissions.	Choose traversal, grouping, and return links.	Treating graph coverage as semantic truth.	Epiplexity, ordering recoverability, relation strength.
Architecture source pack	Select structures, candidate trade-offs, decisions, telemetry, and residual exceptions.	Use decision-memory or trade-off route.	Treating generated explanation as architecture decision or assurance.	Structural-information capture, correspondence, source return.
Fictional canon or source pack	Select canon constraints, premise, agency, continuity, and non-use boundary.	Use causal plot plus reveal order.	Treating private generated scene as authorized continuation.	Continuity, character agency, causal support, rights boundary.
Teaching source spine	Select concepts, dependencies, examples, counterexamples, tasks.	Use didactic prerequisite route with repeated anchors.	Treating generated outline as source framework.	Reconstruction tasks, learning-route quality, source-return readiness.
Qualitative notes or interviews	Select excerpts, themes, alternative readings, reflexive stance.	Use analysis narrative with traceable source excerpts.	Treating generated theme as researcher judgment.	Human interpretive agency, source traceability, ethical boundary.

If a pipeline variant requires a source type not covered by the current source pack, mark the case as a source-refresh trigger rather than silently generalizing. A graph-to-text claim, for example, may require a more specific graph-to-text source than a general NLG survey. A game narrative pipeline may need executable or playability probes that a plain text-generation source does not supply.