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
This commit is contained in:
tegwick 2026-09-28 20:33:09 +02:00
parent d82d9ddd3f
commit b2ca47db97
5 changed files with 265 additions and 24 deletions

View file

@ -1,6 +1,6 @@
# Personhood
**Status:** revised (Phase III, 2026-08-12)
**Status:** revised (Phase IX, 2026-09-28 — P1–P12 itemized, SOUL-WP-0010-T01)
**See also:** H2, RQ2, APE, RN-003, `research/personhood/personhood-dimensions-map.md`
## Working definition
@ -22,22 +22,31 @@ legal status.
## Descriptive profile (P1–P12)
| ID | Dimension |
|---|---|
| P1 | Self-model |
| P2 | Other-model |
| P3 | Relationship model |
| P4 | Character |
| P5 | Intentional organization |
| P6 | Autobiographical integration |
| P7 | Perspective (entity-relative; not solved consciousness) |
| P8 | Commitments |
| P9 | Social reciprocity |
| P10 | Communicative competence |
| P11 | Responsibility-tracking |
| P12 | Value / preference structure |
Itemized to the same specificity as B1–B8 (`concepts/being.md`), per
SOUL-WP-0010-T01. P1–P9 from RN-003; P10–P12 added in Phase III. Full map:
`research/personhood/personhood-dimensions-map.md`. Literature basis:
Dennett cluster conditions (SF-R093); trait and social-cognitive
personality psychology (SF-R094).
Profile, not binary checklist.
| ID | Dimension | Defining question | Anchors |
|---|---|---|---|
| P1 | Self-model | Does it maintain a model of itself as a distinct, continuing entity? | SM2; identity; Dennett self-representation condition |
| P2 | Other-model | Does it hold differentiated models of particular others (not just user classes)? | SM3; social cognition / theory-of-mind tradition |
| P3 | Relationship model | Does it track histories and states of specific relationships? | SM5; Soul (relation) |
| P4 | Character | Does it show persistent dispositions across contexts — stable yet situation-sensitive (trait × situation, CAPS-style), not a fixed script? | Character; SF-R094 Big Five / Mischel |
| P5 | Intentional organization | Is its behavior intelligible via extended intentions and plans, beyond single-step stimulus–response? | Mind; agency; Dennett intentional-system condition (SF-R080/R093) |
| P6 | Autobiographical integration | Does it integrate past events as *its own* history? | continuity C4/C5; Schechtman characterization question |
| P7 | Perspective | Does it operate from an entity-relative informational perspective? (First-person indexicality; explicitly **not** solved phenomenal consciousness.) | RN-003; design boundary |
| P8 | Commitments | Do its present acts bind its future manifestations (promises, stances, obligations)? | normative continuity |
| P9 | Social reciprocity | Does it recursively co-adapt with others who model it (mutual modeling, not one-way output)? | H4; Social Mind; Dennett reciprocity condition |
| P10 | Communicative competence | Can it participate in shared symbol systems and maintain common ground? | language; Dennett verbal-communication condition |
| P11 | Responsibility-tracking | Can attributions of credit/blame stick to it diachronically? | identity + commitments (P1, P8) |
| P12 | Value / preference structure | Does it exhibit stable cares, preferences, and an evaluative stance? | character; intentional organization; Frankfurt second-order volitions |
Profile, not binary checklist — score per code; entities can be high on P10
and low on P4/P6 (stateless chatbot), or high on B1–B8 and low across
P1–P12 (daemon). Per-code enumeration is the prerequisite for per-code
metric scoping (`research/metrics-scoping-note.md`).
## Three axes

View file

@ -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.

View file

@ -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.

View file

@ -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.

View file

@ -4,7 +4,7 @@ type: workplan
title: "Phase IX — P-axis enumeration, metrics instruments, and moral/legal companion line (slice 1)"
domain: agents
repo: soul-frame
status: active
status: finished
flavor: residual
origin: residual
origin_ref: SOUL-WP-0009
@ -33,9 +33,8 @@ and should not sit only as prose in their source notes:
first narrow slice ("legal personhood precedent survey only") rather than
opening the whole moral/legal question at once.
This workplan bundles both as a first slice. **Left `proposed`** — not
reviewed against current repo state or started; needs Bernd's go-ahead
before promotion to `ready`/`active`, same as SOUL-WP-0009 was.
This workplan bundles both as a first slice. Activated 2026-09-28 with
Bernd's go-ahead; all three tasks resolved the same day.
## Depends on
@ -47,7 +46,7 @@ before promotion to `ready`/`active`, same as SOUL-WP-0009 was.
```task
id: SOUL-WP-0010-T01
status: todo
status: done
priority: medium
state_hub_task_id: "598c52c1-5902-541f-bff0-78a8700ce4ed"
```
@ -67,7 +66,7 @@ specificity.
```task
id: SOUL-WP-0010-T02
status: todo
status: done
priority: low
state_hub_task_id: "1ae4434f-8603-5c71-aa59-add71bff24aa"
```
@ -86,7 +85,7 @@ approach per dimension, or explicitly states none is currently viable.
```task
id: SOUL-WP-0010-T03
status: todo
status: done
priority: low
state_hub_task_id: "f29ae5a5-0ede-57c2-9963-50580f5cf6db"
```
@ -99,3 +98,30 @@ status or the non-derivation statement (charter items 2–3) in this slice.
**Done when:** a precedent survey note exists, explicitly scoped to legal
personhood only, cross-referenced from the charter.
---
## Outcome (2026-09-28)
- **T01** — `concepts/personhood.md` now carries an itemized P1–P12 table
(defining question + anchors per code), sourced from the Phase III
dimensions map, SF-R093 (Dennett cluster) and SF-R094 (trait /
social-cognitive personality psychology). Unblocks per-code metric
scoping.
- **T02** — `research/instrument-scoping-b3-psychological-continuity.md`:
viable build targets named for both dimensions (B3: constraint-closure
ratio + perturbation profiling; psychological continuity:
representational continuity, white-box systems only). Neither viable as
a validated metric today.
- **T03** — `research/law-governance/legal-personhood-precedent-survey.md`:
four precedent clusters (corporate, animal, environmental, AI
proposals), legal-personhood-only per charter item 1; cross-referenced
from the charter. Key finding: double decoupling of legal personality
from descriptive profile; guardianship grants (§3) are the template
relevant to Gh. custodianship.
**Residual:** whether to build/pilot the two scoped instruments is
founder-gated — recorded as open hub decision
`0401cf28-48bb-4486-87cc-b1dfd6903d0d` (origin: residual, origin_ref:
SOUL-WP-0010-T02). Charter items 2–4 stay future companion-line slices
gated by the charter itself, not residuals of this workplan.