soul-frame/history/260928-scope-intent-gap-assessment.md
tegwick 5a8a5a2d2d Update SCOPE to actual repo state; add scope-vs-intent gap assessment; open SOUL-WP-0011
- SCOPE.md now reflects Phases I-IX complete, paper draft with decided
  pathway, companion line, and metrics groundwork; current work surface
  and sharpened out-of-scope table
- history/260928-scope-intent-gap-assessment.md assesses state against
  INTENT's six determinations and success criterion; gap register G1-G7,
  ranking G1 (sufficiency/weighting), G2 (coverage matrix), G3 (Soul
  packaging) as most relevant addressable gaps
- SOUL-WP-0011 opened to address G1-G3 (three tasks)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 234768@bnt-lap001
Assistant-Session: 91cdb0c1-a203-431c-b542-cf192b3930a6
2026-09-28 20:38:53 +02:00

68 lines
5.1 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Scope vs. Intent — Gap Assessment (2026-09-28)
**Context:** SCOPE.md updated the same day to reflect actual repo state
(Phases I–IX complete, SOUL-WP-0001…0010 finished). This note assesses that
state against `INTENT.md`'s standing purpose, six determinations, and
success criterion, and ranks the gaps.
---
## 1. Assessment against INTENT's six determinations
| # | INTENT: "determine…" | State | Verdict |
|---|---|---|---|
| 1 | what is already well established | 13 workstream literature maps, SF-R### ledger, five phase syntheses | **Met** for the traversed fields; fiction set and some WS depth (WS11, WS13) remain thin |
| 2 | what Soul Frame recombines usefully | `research/concept-crosswalk.md`, related-work §, phase syntheses | **Met** |
| 3 | what concepts require refinement | H1–H10 all phase-reviewed; RQ1–RQ8 carry working answers with explicit residuals | **Met as process**; residuals live in OpenQuestions |
| 4 | where terminology conflicts with usage | Terminology standard; RQ4 Soul retention decided with disclaimer policy; Deppert false-friend flagged | **Met** |
| 5 | what genuinely new propositions emerge | B1–B8 / P1–P12 profiles, three-axis independence, Sp./Gh. as provenance descriptors, recognition test, continuity channel set | **Met**, but propositions are profile-shaped with **no aggregation/threshold principle** (→ G1) |
| 6a | can these support a rigorous theory | Paper draft exists, adversarially reviewed | **Partially met** — rigor currently rests on per-dimension analysis; sufficiency questions ("how much personhood is *enough* for Beinghood v0.2") are open everywhere they matter (→ G1) |
| 6b | …and eventually a practical architecture | Deliberately downstream (INTENT itself: "downstream of conceptual clarity") | **Out of repo scope** — not a gap to close here |
## 2. Assessment against the success criterion
INTENT's success criterion: one coherent vocabulary describing **nine
reference entity types** (human, animal, short-lived AI agent, persistent
autonomous Agent-being, Einstein `Sp.`, authorized `Gh.`, original
artificial companion, distributed AI, radically non-human system) *while
still making meaningful distinctions among them*.
**Finding: this test has never been run as such.** The closest artifacts
cover fragments — `personhood-dimensions-map.md` §3 profiles five entities
on three coarse axes; thought experiments each stress one entity class.
No document applies the full vocabulary (B1–B8, P1–P12, continuity
channels, addressability/recognition, Agent/Sp./Gh. descriptors) across
all nine and checks that the distinctions survive. The program's own
success criterion is currently **asserted, not exercised** (→ G2).
## 3. Gap register
| ID | Gap | Source | Addressable now? |
|---|---|---|---|
| **G1** | No principled weighting/sufficiency scheme for the B-, P-, and continuity profiles; "sufficient personhood," "enough closure," and continuity thresholds are undefined wherever they are load-bearing | RQ1, RQ2, RQ5 (OQ-043); paper §17 item 2 | **Yes** — conceptual work, no dependency |
| **G2** | Success-criterion coverage matrix (nine entity types × full vocabulary) never produced | INTENT success criterion | **Yes** — synthesis of existing material |
| **G3** | Soul packaging unresolved: relations vs consequences vs both; Cluster D formal depth | RQ4 remainder, flagged **paper-critical** | **Yes** — bounded concept work |
| G4 | Metrics instruments scoped but not built (B3, psychological continuity) | WP-0010 residual | **Gated** — open decision `0401cf28`; do not start without resolution |
| G5 | Companion line items 2–4 (moral status survey, non-derivation statement, jurisdictional tracking) | Charter | **Gated** — charter's own next-step rule; slice-by-slice |
| G6 | Paper not yet circulated; internal-review stage depends on coulomb-research being operational | WP-0009-T06 decision | **Blocked externally** — facility still being set up |
| G7 | Thin coverage: WS11 (death/persistence depth), WS13 fiction set breadth, hybrid display conventions, eval harnesses | §17 item 6; RQ7/RQ8 residuals | Yes, but low urgency — none is load-bearing for the paper |
## 4. Ranking — most relevant gaps
**G1, G2, G3**, in that order, are the gaps worth addressing now:
- **G1** is the deepest structural debt: every profile the framework
introduces ends in "weighting and thresholds open." Determination 6a
cannot be claimed while the framework has no stated position on
aggregation — even a principled *refusal* to weight (context-of-claim
relativity) would be a position; silence is not.
- **G2** is the cheapest high-value item: it directly exercises the
success criterion, likely surfaces vocabulary strain exactly where
INTENT predicts it (distributed AI, radically non-human), and produces
the paper's strongest possible exhibit.
- **G3** is the only remaining item OpenQuestions marks paper-critical.
- G4–G6 are gated or blocked by design; G7 is real but not urgent.
**Disposition:** G1–G3 are picked up by **SOUL-WP-0011** (created with this
assessment). G4–G6 stay with their existing gates. G7 remains in
OpenQuestions/§17 as agenda, not debt.