Elamur GroupantsโŒ•
โ˜ฐ

prag-silver-prompt

The groupant beside prag/src/silver.rs in the Mova repository: what the code computes, what it never does, how to go back from its outputs, its invariants, cost and checks.

Facts

Implementation material. A Mova code model describes this code at one source revision: partial models, finite checks and their stated scope. It is not a reviewed general exposition, and its labels are shown as written, never raised.

Components

componentlabelwhere
approximantpartial source modelforward
astpartial../syntax.json
compositionpartial source modelcomposition
costpartial source modelcost
descriptantpartial source modelepoch-memory
invariantpartial source modelinvariant
testspartial source modelchecks

Obernants

The typed relations around the forward model: the behaviour complement (what the code never does), the reverse reconstruction (every input compatible with an output) and specialised views.

idtypelabelwhere
prag-silver-prompt-behavior-complementbehavior_complementpartial source modelbehavior-complement
prag-silver-prompt-reverse-reconstructionreverse_reconstructionpartial source modelreverse-reconstruction
prag-silver-prompt-specializationsilver_prompt_projectionpartial source modelspecialization

Model text

model

prag-silver-prompt

forward

RULES then Sentences; Tale/Gum pos=0 emits paragraph header and ctx unless immediately preceding supplied Item shares src/doc and checked successor paragraph. Tatoeba header emitted once. Every input item gets sequential number/text.

invariant

checked_add prevents MAX->MIN overflow/wrap. Predecessor is previous item, not corpus search; pos!=0 emits no context/header. Valid same-source adjacent paragraphs preserve original rendering.

cost

O(N+B) time/output; O(1) predecessor state.

behavior-complement

Missing ctx after cross-source collision and panic/wrap at i64::MAX are excluded after repair. Inserting ctx before every sentence is also outside relation. Universe: bounded supplied inputs and candidate observable outputs at this source revision. Partial source-derived inner exclusions with finite witness evidence; unsampled semantics remain unknown.

reverse-reconstruction

key,batch,ord,plen and suppressed ctx are lost. Multiple Item sequences yield identical prompts; no unique inverse. Target is all x in the stated domain with F(x)=y, without unique recovery or an implemented complete solver.

specialization

Old code failed source-scoped Tale1/Gum2 context count and MAX/MIN adjacency witness. Equality on src plus checked successor repairs both with no teacher invocation.

composition

Children share source identity. Preserve frame indices through alignment/link mapping and batch references through prompt/gate numbering. Independent marginal inverses can lose shared correlations; overlap costs are counted once.

checks

Six fbench and five silver wave16_models tests: finite canonical role oracle, independent ten-role counts, old-code witnesses and compiled controls. See receipts at file root.

epoch-memory

2026-10-30: prospective inspection predicted predecessor defects and duplicate-edge recall inflation. Three old-code witnesses confirm these. Valid adjacency and unique links retain semantics. No score assertions or deduplication introduced. Historical metrics retain original semantics.

limitations

Partial syntax is not expanded semantic AST; macros opaque. Scoped models and finite observations, not full-file verification or proof. No live parser, teacher, corpus, filesystem aggregate, GPU, full course, speed or approximation-cap claim. External effects and resource-extreme malformed inputs remain unexecuted.

evidence

Evidence scope

See root receipts.md for source and raw-log hashes. Pure supplied fixtures only; effects are source inspected.

This page in Markdown โ†’ https://md.groupants.elamur.ai/free/en/mova/prag/src/silver.rs.groupant/prompt.groupant/