Implement SOUL-WP-0010: P1-P12 itemization, instrument scoping, legal precedent survey

- T01: itemize P1-P12 in concepts/personhood.md with per-code defining
  questions and anchors (Dennett cluster SF-R093, trait/social-cognitive
  personality psychology SF-R094), matching B1-B8 specificity
- T02: research/instrument-scoping-b3-psychological-continuity.md scopes
  candidate instruments for constitutive integration (B3) and
  psychological continuity
- T03: research/law-governance/legal-personhood-precedent-survey.md,
  charter scope item 1 only, cross-referenced from the charter
- Workplan finished; residual (instrument build gate) recorded as open
  hub decision 0401cf28; stale "left proposed" prose corrected

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

research/instrument-scoping-b3-psychological-continuity.md

@@ -0,0 +1,95 @@
+# Instrument Scoping — Constitutive Integration (B3) and Psychological Continuity
+
+**Workplan:** SOUL-WP-0010-T02, resolved 2026-09-28
+**Follows:** `research/metrics-scoping-note.md` (SOUL-WP-0009-T04)
+**Purpose:** scope — not build — candidate operational approaches for the two
+dimensions the metrics note marked **No existing instrument** while carrying
+the most argumentative weight across the thought-experiment catalog
+(TE-02, TE-04, TE-05, TE-08).
+
+Scoping, in this note's sense: name a candidate operational approach, say
+what it would measure and what it would miss, and judge whether it is
+viable enough to justify a build effort — or state explicitly that none is.
+
+---
+
+## 1. B3 — Constitutive integration
+
+**Target claim to operationalize:** the system is one *integrated
+organization*, not loosely coupled components (decisive in TE-05 The
+Collective: "at which level does self-individuating organization close?";
+load-bearing in TE-04 for what survives gradual replacement).
+
+### Candidate approaches
+
+| # | Approach | What it measures | What it misses |
+|---|---|---|---|
+| 1 | **Constraint-closure ratio** (operationalizing Montévil & Mossio 2015): over a dependency graph of the system's processes and the constraints acting on them, the fraction of constraints that are themselves produced/maintained by processes inside the candidate boundary | Degree of organizational closure at a chosen boundary; directly comparable across candidate levels (member vs. collective — exactly TE-05's question) | Graph construction is modeler-dependent; no canonical granularity for "a process" |
+| 2 | **Integration/segregation measures from network science** (participation coefficient, modularity Q, global efficiency) applied to the component-interaction graph | Whether interaction structure is one integrated module or several weakly coupled ones | Measures topology, not constitution — a message bus scores "integrated" without any self-maintenance |
+| 3 | **Perturbation-propagation profiling**: ablate or degrade one component; measure how widely and how fast compensatory adjustment propagates | Functional (not just topological) integration; cheap to run on artificial systems | Conflates integration with fragility unless compensation is distinguished from cascade failure |
+| 4 | IIT-style integrated-information approximations (Φ proxies) | Principled "more than the sum of parts" formalization | Computationally intractable beyond toy systems; imports contested consciousness commitments Soul Frame deliberately avoids (P7 boundary) |
+
+### Judgment
+
+**Viable candidate exists.** The recommended composite is **1 + 3**:
+constraint-closure ratio as the structural instrument, validated against
+perturbation-propagation profiling as the behavioral check (a genuinely
+integrated organization should show closure *and* distributed
+compensation). Approach 2 is a cheap screening proxy only; approach 4 is
+**rejected** for Soul Frame use — cost and consciousness entanglement.
+
+For artificial systems the raw material (dependency graphs, service
+telemetry, chaos-engineering-style perturbation runs) already exists in
+production tooling; the invention needed is the mapping and the closure
+criterion, not the data collection. This parallels the metrics note's B4
+finding ("needs mapping, not invention") more closely than its flat "No"
+suggested — B3 is *buildable*, not measurable-today.
+
+---
+
+## 2. Psychological continuity
+
+**Target claim to operationalize:** "the same adaptive/modeling process"
+persists over time — as distinct from *similar outputs* (the metrics
+note's explicit objection to output-based proxies). Load-bearing in TE-02
+(is the restored process the same one?), TE-04 (H6 channel under gradual
+replacement), TE-08 (degraded continuity when the autobiographical channel
+fails).
+
+### Candidate approaches
+
+| # | Approach | What it measures | What it misses |
+|---|---|---|---|
+| 1 | **Representational continuity**: compare internal state-space *structure* across time slices (representational similarity analysis between model snapshots — geometry of the representation space, not I/O behavior) | Whether the modeling process itself evolved continuously vs. was swapped for a behavioral look-alike; directly answers the "same process, not similar outputs" requirement | Requires white-box access; no established threshold for "continuous enough"; substrate-specific (embedding spaces vs. neural recordings don't compare) |
+| 2 | **Overlapping-chains connectedness** (Parfitian chains operationalized): connectedness of the retrieval graph over the autobiographical store — do current states causally draw on states that drew on earlier states, in overlapping spans? | Graded continuity that degrades the way TE-08 needs (severe amnesia → sparse graph → DEGRADED, not binary death) | Measures the memory channel only (C4/C5-adjacent); a process could stay "the same" while its store is pruned |
+| 3 | **Longitudinal disposition profiling**: repeated CAPS-style if-then situation×response probes (SF-R094), tracking profile drift over time | Behavioral-level continuity of character/valuation (P4, P12) without white-box access | It is exactly an output-similarity measure — the thing the metrics note warns is *adjacent to*, not identical with, process continuity |
+
+### Judgment
+
+**Viable candidate exists, with a caveat.** **Approach 1** is the only
+candidate that measures the continuity claim itself rather than a
+correlate; it should be primary. Approach 2 is a complementary channel
+instrument (autobiographical continuity specifically), and approach 3 is
+**admissible only as corroborating evidence**, never as the operational
+definition — otherwise the instrument re-imports the output-similarity
+error the metrics note flagged.
+
+Caveat: approach 1 is currently substrate-specific. A cross-substrate
+psychological-continuity metric remains out of reach; what is scoped here
+is an instrument *for artificial systems with inspectable internals*.
+
+---
+
+## 3. Overall conclusion
+
+Both dimensions clear the scoping bar set by SOUL-WP-0010-T02's done
+condition: at least one candidate operational approach each —
+**constraint-closure ratio + perturbation profiling** for B3;
+**representational continuity** (with overlapping-chains as channel
+instrument) for psychological continuity. Neither is viable *today* as a
+validated metric; both are viable *build targets* with no missing
+theoretical prerequisite.
+
+Whether to actually build/pilot either instrument is a founder-gated
+prioritization question, recorded as a hub decision (origin: residual,
+SOUL-WP-0010) rather than opened as a workplan here.