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.

research/law-governance/legal-personhood-precedent-survey.md

@@ -0,0 +1,105 @@
+# Legal Personhood Precedent Survey (Companion Line — Slice 1)
+
+**Workplan:** SOUL-WP-0010-T03, resolved 2026-09-28
+**Charter:** `moral-legal-personhood-charter.md` — this note executes charter
+scope item 1 **only**. Moral status (item 2) and the non-derivation
+statement (item 3) are explicitly **not** attempted here.
+**Extends:** `sp-gh-legal-gap-sketch.md` (§1 mapping row "Being →
+legal person: fit poor/direct").
+**Non-goal:** no derivation of moral or legal status from Soul Frame
+descriptive concepts; no jurisdiction-specific legal advice. Jurisdictional
+variance is tracked, not averaged (charter item 4).
+
+---
+
+## 1. Corporate personhood — the fiat baseline
+
+| Precedent | Jurisdiction | Holding / significance |
+|---|---|---|
+| *Salomon v A Salomon & Co* (1897) | UK | Separate legal personality of the company even with one dominant shareholder; personality as legal construction, not description |
+| *Santa Clara County v Southern Pacific* (1886) | US | Headnote origin of corporate constitutional personhood under the 14th Amendment |
+| *Citizens United v FEC* (2010) | US | Corporate political-speech rights; personality bundle expands by doctrine, not by any change in the entity |
+| *Burwell v Hobby Lobby* (2014) | US | Closely-held corporations exercise religious rights — bundle extends to interests classically "personal" |
+
+**Pattern:** legal personality is a *functional grant* serving legal-system
+purposes (asset partitioning, standing, liability channeling). The bearer
+has essentially **no descriptive personhood profile** (P1–P12 ≈ 0 at the
+corporate level; cf. RN-003 §8 corporate false-positive risk, TE-05) —
+maximal proof that legal personality and descriptive personhood are
+independent axes.
+
+## 2. Animal law — capacities without personality
+
+| Precedent | Jurisdiction | Holding / significance |
+|---|---|---|
+| NhRP *Tommy* / *Kiko* line (2014–2018, NY) | US | Habeas for chimpanzees denied; courts leaned on rights–duties reciprocity ("social contract" reasoning) |
+| *NhRP v Breheny* ("Happy" the elephant, 2022, NY Court of Appeals) | US | Habeas denied 5–2; strong dissents (Wilson, Rivera) arguing personality is a legal conclusion, not a biological fact |
+| *Sandra* orangutan (2015, Buenos Aires) | Argentina | Court language of "non-human subject of rights"; effect largely welfare-based |
+| *Cecilia* chimpanzee (2016, Mendoza) | Argentina | Habeas **granted**; explicitly declared a non-human legal person for the writ's purpose |
+
+**Pattern:** the mirror image of §1 — entities with a **non-trivial
+descriptive profile** (self/other-models, social reciprocity) are mostly
+*denied* legal personality, with courts citing duty-bearing capacity, not
+descriptive capacities. Where granted (Cecilia), the grant is narrow and
+purpose-bound. Confirms: descriptive profile neither necessary (§1) nor
+sufficient (§2) for legal personality.
+
+## 3. Environmental / other non-human grants — personality as governance instrument
+
+| Precedent | Jurisdiction | Holding / significance |
+|---|---|---|
+| Te Awa Tupua Act (2017) | New Zealand | Whanganui River as legal person with statutory human guardians (Te Pou Tupua) |
+| Ganges/Yamuna, Uttarakhand HC (2017) | India | Rivers declared legal persons; **stayed** by the Supreme Court — grants can be revoked/suspended |
+| Rights of Nature, Constitution art. 71 (2008) | Ecuador | Constitutional-level standing for nature |
+
+**Pattern:** legal personality used as a **custodianship/standing
+mechanism** — personality plus mandatory human guardians. Structurally the
+closest existing template to the gap sketch's missing "Gh. custodianship
+instrument" (§1, §3.4 there): a legal person that cannot represent itself,
+represented by appointed authorities with defined scope.
+
+## 4. AI legal personality — proposals, not precedent
+
+| Item | Status |
+|---|---|
+| Solum, "Legal Personhood for Artificial Intelligences" (1992, NC L Rev) | Foundational scholarly framing: personality as bundle; capacity objections answerable case-by-case |
+| EU Parliament resolution on Civil Law Rules on Robotics (2017/2103(INL)) | Proposed exploring "electronic personhood" for sophisticated autonomous robots |
+| Open letter from AI/robotics/law experts (2018) | Opposed electronic personhood as liability-shielding; influential in the retreat |
+| EP resolution 2020/2014(INL) on AI civil liability | Retreat: liability routed to existing persons (operator/producer); no electronic person |
+| Bryson, Diamantis & Grant, "Of, for, and by the people" (2017, AI & Law) | "Synthetic persons" legally possible but a policy mistake: personality without effective sanctionability creates a liability lacuna |
+
+**Pattern:** the live AI debate is **not** about descriptive capacities but
+about *liability engineering* — who absorbs harm costs. The strongest
+objection (Bryson et al.) is that personality without punishability
+decouples rights from accountability: in Soul Frame terms, the law cares
+about something like P8/P11 (commitments, responsibility-tracking)
+*enforceability*, not about the descriptive profile as such.
+
+---
+
+## 5. Cross-cutting findings (for the companion line, not the descriptive core)
+
+1. **Fiat and functional.** Every grant surveyed serves a legal-system
+   purpose; none tracks a descriptive threshold. The gap sketch's "fit:
+   poor/direct" for Being → legal person is confirmed across all four
+   clusters.
+2. **Personality is a divisible bundle.** Partial, purpose-bound grants
+   (Cecilia's habeas-only personhood, river guardianship) are normal —
+   "legal person" names a family of bundles, not one status.
+3. **Double decoupling.** No-profile entities hold rich bundles (§1);
+   rich-profile entities are denied them (§2). Any future Soul Frame
+   moral/legal mapping must treat legal personality as an independent
+   variable, never a derivable one.
+4. **Guardianship is the load-bearing template.** For Sp./Gh. governance
+   questions, §3's guardian-plus-person construction is the precedent
+   family to develop further, not §1's self-directed corporate model.
+5. **Jurisdictional variance is severe** — common-law habeas strategies,
+   civil-law subject-of-rights language, statutory grants, and
+   constitutional provisions behave differently; per charter item 4 this
+   table tracks, and must not average, them.
+
+## 6. Residual (explicitly not opened here)
+
+Charter items 2 (moral status survey) and 3 (non-derivation statement)
+remain future slices of the companion line, gated per the charter's own
+next-step rule.

research/law-governance/moral-legal-personhood-charter.md

@@ -22,7 +22,9 @@ core to get there — by defining a companion line with its own scope.
 
 ## Scope (what the companion line would cover)
 
-1. **Legal personhood precedent survey** — corporate personhood, animal
+1. **Legal personhood precedent survey** — ✅ first slice executed as
+   `legal-personhood-precedent-survey.md` (SOUL-WP-0010-T03, 2026-09-28) —
+   corporate personhood, animal
    welfare/rights law, AI legal-personality proposals (e.g. EU robot-
    personhood debate), personality/publicity rights (`SF-R110`), digital
    estates (`SF-R111`) — building outward from the existing gap sketch in
@@ -77,3 +79,7 @@ scoped narrowly enough (e.g. "legal personhood precedent survey only" as a
 first slice) to avoid re-opening the whole moral/legal question at once.
 Not opened now — SOUL-WP-0009-T05's done condition is this charter existing,
 not the companion line's work starting.
+
+**Update 2026-09-28:** the first slice was picked up exactly as scoped —
+SOUL-WP-0010-T03 produced `legal-personhood-precedent-survey.md` (item 1
+only). Items 2–4 remain unstarted future slices.