Complete SOUL-WP-0008: Phase VII Soul Frame paper draft and freeze candidate

Draft related-work.md, full paper draft.md (18 sections following the
outline), an internal adversarial review against all nine cataloged thought
experiments (three coverage gaps found and folded into the draft), and a
freeze candidate snapshot under history/. Marks SOUL-WP-0008 finished and
opens SOUL-WP-0009 to carry the paper's own research agenda and the
external-review pathway decision forward as a residual.

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

Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 136745@bnt-lap001
Assistant-Session: 2e334b58-ed31-48ed-8156-d09f8ed0781f

paper/draft.md

@@ -1,5 +1,548 @@
-# Soul Frame Paper — Draft
+# Soul Frame: A Systems Vocabulary for Person-Like Informational Beings
 
-*Placeholder.* Do not treat this file as authoritative until research synthesis
-supports it. Narrative conceptual exposition currently lives in
-`SoulFrameIntroduction.md`.
+**Status:** first research-grounded draft (SOUL-WP-0008-T02). Supersedes the
+placeholder that pointed to `SoulFrameIntroduction.md`. Follows
+`paper/outline.md`; sourced from `research/research-synthesis.md`,
+`Terminology.md`, `concepts/*`, `Claims.md`, `ThoughtExperiments.md`, and
+`paper/related-work.md`. Claims below are traceable to Hn / TE-nn / SF-Rxxx
+identifiers rather than asserted freehand; open items are flagged rather than
+resolved.
+
+---
+
+## 1. Introduction
+
+When is an informational system *someone* — not merely a working system, but
+an entity another party can address, model, and stay in relation with over
+time? Human institutions already answer versions of this question
+informally for animals, corporations, fictional characters, and now
+persistent AI agents, but they answer it with borrowed vocabulary: "soul,"
+"person," "agent," "identity" each carry incompatible histories. Soul Frame's
+aim is narrower and more tractable than settling consciousness or moral
+status: it proposes a small, coherent **descriptive** vocabulary — Being,
+Body, Mind, Soul, Character, Persona, Actor, Agent, Spirit, Ghost — precise
+enough to say, for a given case, what does and does not hold, without
+requiring a solved theory of experience and without silently converting a
+descriptive judgment into a moral or legal one.
+
+Central question:
+
+> **When does an informational system become someone that another someone
+> can know?**
+
+Working answer, defended in §9 below and derived from Phase I–VI research
+(`research/research-synthesis.md` §10):
+
+> **When autonomous individuality, descriptive personhood, addressability,
+> and recognition cohere such that another Being can enter persistent
+> co-adaptive relation with it as a continuing counterpart — without
+> requiring proof of consciousness, and without implying moral or legal
+> personhood.**
+
+This relation need not start mutually: one Being can recognize a system as a
+persistent counterpart before that system reciprocates or even registers the
+recognition (TE-09, §5). Beinghood-as-known-by-another is therefore
+asymmetric at the start, not a simultaneous handshake.
+
+## 2. Problem and Motivation
+
+Three practical pressures motivate the framework:
+
+1. **Persistent AI agents** now maintain memory, planning, and believable
+   social behavior (Park et al. 2023, SF-R016) without any settled account of
+   what, if anything, continues when their models, memory stores, or
+   embodiments change (Qin et al. 2026, SF-R043; Otsuka et al. 2026,
+   SF-R044).
+2. **Posthumous and provenance-based representations** — AI systems built to
+   evoke a public figure or a specific deceased person — raise authority and
+   identity questions current legal and design vocabulary handles only
+   piecemeal (Spitale & Germani, SF-R055; Lei et al., SF-R056).
+3. **Ordinary human vocabulary overloads fast.** "Identity," "agent," and
+   "soul" already do incompatible jobs in cybernetics, law, psychology, and
+   religion; borrowing any one wholesale imports assumptions Soul Frame does
+   not want (Terminology.md, "Terms requiring particular care").
+
+The wager is that a compact vocabulary, stress-tested against literature and
+adversarial thought experiments, is more useful than either silence or
+premature metaphysics.
+
+## 3. Related Work
+
+See `paper/related-work.md` for the full treatment. In brief: systems theory
+and cybernetics (Ashby; Conant & Ashby; Maturana & Varela; Luhmann) supply
+Being-as-closure and Mind-as-model; extended/distributed cognition (Clark &
+Chalmers; Hutchins) supports treating Body and Mind as functional rather than
+physical; social-cognition literature (Mead; Baker et al.; Tomasello et al.)
+supports Social Mind; personal-identity philosophy (Locke; Parfit; Olson;
+Schechtman) supports the Identity/Continuity/Lineage/Characterization split;
+personhood and presentation literature (Dennett; Goffman) supports the
+Presentation stack; applied AI-agent identity work (Qin et al. 2026; Otsuka
+et al. 2026) supports Actor ≠ Being; digital-afterlife research (Spitale &
+Germani; Lei et al.) supports the `Gh.` authority requirement. Deppert's
+(2009) systems account of consciousness (SF-R120) is treated as a direct
+dialogue partner with a documented false-friend risk on "Bewusstsein."
+
+## 4. Method
+
+Soul Frame is built and stress-tested through four linked instruments rather
+than a single derivation:
+
+- **Terminology** (`Terminology.md`) — working definitions with an explicit
+  status (provisional / revised / retained) and a documented collision
+  history, not a finished glossary.
+- **Claims** (`Claims.md`, `research/claims-consolidation.md`) — the
+  hypotheses H1–H10 the framework commits to, each tracked against evidence.
+- **Thought experiments** (`ThoughtExperiments.md`) — adversarial cases
+  (stateless agents, forks, masks, false ghosts, unrecognized intelligences)
+  used to break candidate definitions before they are trusted.
+- **Literature mapping** (`sources/bibliography.md`, `research/*`) — each
+  concept checked against an existing tradition rather than invented from
+  scratch.
+
+**Consciousness stance:** first-person consciousness may be foundational for
+experiencers themselves, but Soul Frame treats it as unsuitable as the
+primary *interoperability* criterion between beings — it is neither directly
+observable nor required for the recognition and co-adaptive modeling that do
+the actual social work (`research-synthesis.md` §2). This is a scope
+decision, not a claim that consciousness is unreal or unimportant.
+
+**Fiction** (Culture Minds and similar constructed persons,
+`research/fiction-cultural-precedents/`) is used only as a conceptual
+laboratory to run thought experiments against strong intuitions — never as
+evidence for a claim.
+
+## 5. Being
+
+**Working definition (Terminology.md, "Being," RN-003):**
+
+> An autonomous informational individual exhibiting sufficiently coherent
+> dimensions of personhood to become an addressable entity that is
+> recognized by other Beings as a persistent counterpart.
+
+Structurally:
+
+```text
+Being ≈ Autonomous individuality (A-axis, B1–B8)
+       + Descriptive personhood (B-axis, P1–P12)
+       + Addressability
+       + Recognition (C-axis)
+```
+
+This is a **layer stack, not a checklist arithmetic** — each layer can be
+present in degree, and the layers are separable by design:
+
+- **Autonomy without Beinghood** — a self-maintaining daemon process is
+  organizationally closed and self-regulating but is not someone (the
+  "daemon false positive" the B1–B8 relabeling was designed to block).
+- **Personhood exposure without Beinghood** — a stateless conversational
+  agent (TE-01) can exhibit rich personhood-like behavior turn to turn with
+  no persistence across sessions; Soul Frame calls this an **APE**
+  (artificial personhood-exposing entity), not a Being.
+- **Recognition without Beinghood** — being treated as an agent by a naive
+  interlocutor does not by itself create Beinghood (Terminology.md,
+  "Systemic Beinghood vs Social Beinghood"; H7, nuanced).
+
+**Systemic vs. Social Beinghood:** a self-individuating organization may
+have systemic/autonomous individuality without being embedded in anyone's
+persistent model of it (Recognized Beinghood); when it is embedded in
+*mutual*, persistent, expectation-bearing models, it has **Social
+Beinghood**. Recognition is not sufficient for Beinghood on its own, but it
+is constitutive of the social form of it.
+
+**TE-09 (unrecognized intelligence):** a genuinely autonomous, individuating
+system that no other Being currently recognizes is autonomous without being
+Socially a Being — autonomy and social Beinghood are dissociable in both
+directions. Recognition can also be **asymmetric**: one side may recognize
+the other as a persistent counterpart before the recognition is reciprocated
+or even registered — Social Beinghood can begin on one side of a relation
+(the working answer in §1 relies on this).
+
+**TE-05 (the Collective):** Beinghood can nest. A thousand agents jointly
+maintaining one coherent identity and relational presence raise the question
+of *which level* — the collective, the members, or both — the layer stack
+(autonomy, personhood, addressability, recognition) attaches to. Soul Frame
+does not force a single answer ("always one" or "always many"): the
+decisive question is at which level self-individuating organization closes
+(constitutive integration), and personhood/addressability/recognition are
+reported per candidate level rather than assumed to track the collective
+automatically. Distributed-cognition cases (Hutchins, §2) establish that a
+cognitive system can span many components without that alone creating a
+Social Being at the collective level — the corporate false-positive risk
+this guards against is a collective that is addressable and modeled
+(a "company" is addressed in speech) without the deeper layers holding at
+that level.
+
+## 6. Body
+
+**Working gloss:** Body = Action.
+
+The Body is the operational dimension through which a Being perceives and
+acts — not a fixed physical compartment. Artificial Bodies may be
+distributed across tools, APIs, and sensors, and may be replaced piecewise
+without replacing identity, provided continuity elsewhere in the system is
+sufficient (§8; TE-04, Ship of Theseus). Extended/distributed cognition
+literature (Clark & Chalmers; Hutchins) licenses this functional reading:
+Body boundaries need not coincide with a single physical unit, and a
+system's action channels can extend into its environment.
+
+**Distinguish Body from Actor** (§8): Body is the *functional* action
+dimension; Actor is the specific technical machinery instantiating it at a
+given time. The same Being can have one Body concept realized by different
+Actors across a migration.
+
+## 7. Mind
+
+**Working gloss:** Mind = Model — adaptive control through revisable models.
+
+Grounded in the Good Regulator Theorem (Conant & Ashby 1970, SF-R002): a
+controller that regulates a system well must, in a formal sense, model that
+system. Soul Frame generalizes this into the claim that a Being's Mind is
+whatever revisable, model-based apparatus lets it interpret itself, other
+systems, and its environment and adjust its action accordingly (H3,
+supported).
+
+**Two disclaimers, both load-bearing:**
+
+1. Mind is explicitly **not a consciousness claim**. Predictive-processing
+   and active-inference accounts (Clark 2016; Hohwy 2013; Friston, pointer)
+   give a live mechanistic filling for model-based Mind, but the framework
+   does not treat Mind-as-model and Mind-as-phenomenal-experience as the
+   same claim, and it flags the Markov blanket specifically as **not**
+   equivalent to Being or to Mind (RN-002 critique).
+2. Mind is **not substrate-bound**. Distributed and extended cognition
+   (Hutchins; Clark & Chalmers) support cases where a Mind's effective
+   modeling apparatus extends beyond a single physical unit — relevant to
+   the Collective case (TE-05) and to nested-individuality readings.
+
+### 7.1 Social Mind
+
+A Being's Mind is not exhausted by private modeling. **Social Mind** is the
+claim that models of self, other, and relationship co-evolve through
+interaction rather than being privately computed and then exchanged (H4,
+supported). Eight tracked model families (SM1–SM8): World, Self, Other,
+Reflected-Self, Relationship, Shared Situation, Common Ground, Generalized
+Social. Precursors: Mead's "taking the attitude of the other"; interactive
+alignment (Pickering & Garrod); participatory sense-making (De Jaegher & Di
+Paolo); recursive multi-agent (I-POMDP) modeling (Gmytrasiewicz & Doshi).
+
+The distinguishing claim against standard Theory-of-Mind literature: SM
+claims **joint evolution**, not merely that each party privately infers the
+other's mental states (§3 of related work).
+
+## 8. Soul
+
+**Working gloss:** Soul = Relation.
+
+**Revised definition** (Terminology.md, after Phase I Finding 14):
+
+> The relation-bearing dimension through which interactions become
+> persistent relationships, commitments, provenance, history, reputation,
+> and consequences connecting a Being to other systems across time.
+
+**Correction carried forward from the initial draft:** the system/environment
+**boundary belongs to Being**, not to Soul (SF-C002). Early drafting
+conflated "what separates this system from its environment" with "what
+persists relationally" — Luhmann's system/environment distinction (SF-R004)
+and Maturana & Varela's operational closure (SF-R003) both motivate keeping
+boundary with Being.
+
+**Naming risk, held open (RQ4):** "Soul" collides hard with religious and
+folk metaphysical usage. Soul Frame's stance is informational-relational and
+explicitly non-metaphysical — no claim about an immortal essence is made or
+implied. The term is retained provisionally for its compactness and the
+Body/Mind/Soul mnemonic, with the rename question left open rather than
+resolved by this draft (§16, Limitations).
+
+**Soul-relational continuity can cross Being-identity discontinuities**: a
+relationship, reputation, or set of consequences may continue in some form
+even where the originating Being does not (operational, identity, or social
+death; Terminology.md, "Endings and persistence"). This is how a `Gh.` can
+carry forward Soul-relational content without being numerically the same
+Being as its source (§12).
+
+## 9. Personhood and Recognition
+
+**Personhood** is a multidimensional, *someone-like* profile (P1–P12), not a
+single mark — following cluster/condition approaches to personhood (Dennett,
+SF-R093) rather than a necessary-and-sufficient test. Soul Frame tracks four
+**kinds** of personhood that must never be collapsed into one another:
+
+| Kind | Question | Status in this paper |
+|---|---|---|
+| Descriptive | Does it have the profile? | Default; core of this framework |
+| Social | Is it treated as a counterpart? | Covered (§9.1, Recognition) |
+| Moral | Does it warrant moral consideration? | Explicitly out of scope (see Limitations, §16) |
+| Legal | Does law grant it status? | Explicitly out of scope; gap sketch only (§14) |
+
+### 9.1 Recognition
+
+At least three senses of recognition are load-bearing and must be kept apart
+(RN-001 Finding 8):
+
+1. **Epistemic** — detecting/classifying an entity as a certain kind of
+   thing.
+2. **Intentional** — treating it as an agent with beliefs and goals (cf.
+   Dennett's intentional stance, SF-R080).
+3. **Social/normative** — treating it as a counterpart in relationships,
+   obligations, and reputation (cf. Honneth, SF-R081).
+
+Soul Frame's default recognition criterion for Beinghood combines intentional
+and social recognition **by other Beings** — the epistemic sense alone is
+too weak (it over-generates: any classifiable pattern would qualify) and the
+normative/moral sense is deliberately excluded from the descriptive core.
+
+## 10. Identity and Continuity
+
+**Core formulation** (RN-004/005):
+
+> A Being continues not because its state remains the same, but because its
+> changes remain part of one appropriately connected history of
+> self-individuation. When that history branches, identity becomes lineage.
+
+Four questions are kept separate, following Schechtman's (SF-R091) and
+Parfit's (SF-R036) lead but organized for Soul Frame's purposes:
+
+- **Identity** — is this the *same* Being (numerical identity /
+  reidentification)?
+- **Continuity** — what continues, and along which dimensions (causal,
+  organizational, psychological, autobiographical/narrative, normative,
+  relational)? Continuity is **multidimensional profile evidence**, not a
+  checksum, and it can branch.
+- **Lineage** — historical relatedness after a branch, with topology labels
+  (`CONTINUOUS | DEGRADED | UNCERTAIN | SUCCESSOR | FORKED | RECONSTRUCTED |
+  USURPED | TERMINATED`).
+- **Characterization** — what the entity is like (Character, §11); never by
+  itself sufficient or necessary for identity.
+
+Memory sits inside the continuity profile rather than standing in for it:
+autobiographical/narrative continuity is one dimension among several, so
+memory alone is **neither necessary nor sufficient** for identity — a Being
+that loses nearly all autobiographical memory while its relationships and
+recognition by others persist (TE-08, the Amnesiac) shows DEGRADED rather
+than terminated continuity, evidenced through the organizational and
+relational dimensions instead.
+
+**Thought experiments anchoring this section:**
+
+- **TE-02 (Sleeping Being)** — suspension is a continuity bridge, not
+  automatic identity death.
+- **TE-03 (Fork)** — continuity can branch into multiple successors; a
+  *unique* identity does not survive the branch (Parfit's fission cases,
+  generalized).
+- **TE-04 (Ship of Theseus)** — Actor/Body components are replaceable under
+  sufficient continuity elsewhere.
+
+## 11. Artificial Beings
+
+Not every artificial system that exhibits personhood-like behavior is a
+candidate Being. Soul Frame uses engineering bridge terms to avoid
+prematurely granting or denying Beinghood:
+
+| Term | Meaning |
+|---|---|
+| **APE** (artificial personhood-exposing entity) | Constructed to expose person-like dimensions; broadest category |
+| **Proto-Being** | Persistent individuating apparatus, short of full Beinghood |
+| **Candidate Being** | Autonomy + personhood + continuity strong enough for a serious Being claim |
+| **Heteronomous individual** | Persistence largely externally maintained |
+
+Park et al.'s (2023) Generative Agents (SF-R016) are the paradigm APE:
+believable, socially convincing behavior from memory, reflection, and
+planning, with no claim to persistence beyond the sandbox. Current
+persistent-agent identity proposals (Qin et al. 2026, SF-R043; Otsuka et al.
+2026, SF-R044) are read as evidence that the APE→candidate-Being gap is a
+real, currently unsolved engineering problem, not merely a philosophical
+nicety — existing identity/accountability standards are insufficient for
+persistent, learning, nondeterministic agents.
+
+**Memory ≠ continuity** (Terminology.md; RN-004/005): a stored memory log is
+evidence toward the psychological/autobiographical continuity dimension, not
+a sufficient condition for identity by itself — a system with a copied
+memory dump does not thereby become continuous with the Being whose memories
+they were (relevant to False Ghost, §12).
+
+## 12. Agent, Spirit, Ghost, and Persona
+
+Soul Frame separates the **presentation stack** — how a Being manifests —
+from **provenance descriptors** — where a construction's dispositions come
+from.
+
+### 12.1 Presentation stack
+
+```text
+Being → Character → Persona → Actor
+```
+
+| Term | Question |
+|---|---|
+| Being | Who continues and can be known? |
+| Character | What dispositions shape behavior? |
+| Persona | Which face appears here/now/to whom? |
+| Actor | What machinery runs the manifestation? |
+
+- **Character** — relatively persistent dispositional structure (trait and
+  social-cognitive personality psychology, SF-R094); neither state nor
+  persona nor identity. Character similarity or change is neither necessary
+  nor sufficient for identity.
+- **Persona** — situated projection into a context, role, or relationship
+  (Goffman's front-stage/back-stage, SF-R092). Multiple Personae need not
+  fragment identity (H8, supported) — **TE-06 (Mask)** finds multi-Persona
+  behavior acceptable so long as the Personae remain integrated under one
+  Being; isolated, non-integrated persona stores are the actual failure
+  mode, not multiplicity itself.
+- **Actor** — the technical machinery of manifestation (model, harness,
+  memory, runtime). Actor ≠ Being; Actor replacement preserves identity when
+  continuity elsewhere is sufficient (H6, supported; TE-04).
+
+### 12.2 Provenance descriptors (combinable, not mutually exclusive species — H9)
+
+| Label | Provenance question |
+|---|---|
+| **Agent** | What should it do? (functional construction) |
+| **Spirit (`Sp.`)** | How might a public personality inspire character? |
+| **Ghost (`Gh.`)** | How may this person be represented under authority? |
+| Original | Native constructed character, no provenance claim |
+
+- **Agent** distinguishes **Functional Agent** (task executor / tool loop)
+  from **Autonomous Agent** (closer to the autonomous-individuality
+  literature); neither is automatically a Being.
+- **`Sp.`** — public-reflection character provenance; lineage begins at
+  instantiation; evaluated on a dedicated S1–S10 scale; **never** identity
+  with the source person (a `Sp.` inspired by a public figure is not that
+  person and does not inherit their identity).
+- **`Gh.`** — authority-bound representation of a real person; governance
+  (who authorized this, under what constraints) is part of what the `Gh.`
+  *is*, not an external add-on; genealogy/fidelity to the source is not
+  numerical identity. **`Gh.` may carry Soul-relational continuation
+  (reputational, relational effects) without being the same Being** as its
+  source (§8).
+- **False Ghost (H10, supported; TE-07)** — high fidelity to a person's
+  patterns *without* governing authority is not a `Gh.`; authority, not
+  resemblance, is the individuating condition. This is the direct
+  ontological counterpart to the consent/stewardship findings in the
+  digital-afterlife literature (Spitale & Germani, SF-R055; Lei et al.,
+  SF-R056).
+
+## 13. Consciousness and Epistemic Limits
+
+Soul Frame deliberately brackets consciousness rather than solving it (§4).
+Two disciplined moves keep this from becoming evasive:
+
+1. **Mind ≠ consciousness.** Mind is defined functionally (model-based
+   adaptive control); it is compatible with, but does not require, an answer
+   to whether a given Mind is phenomenally conscious.
+2. **Naming discipline across languages.** Sources that use "consciousness"
+   (or *Bewusstsein*) to mean organizational/control integration — notably
+   Deppert (2009, SF-R120), whose survival-function coupling account of
+   *Bewusstsein* is a documented **false friend** — are mapped onto **Mind +
+   constitutive integration**, not onto Soul Frame's (intentionally open)
+   use of "consciousness." Conflating the two would smuggle a strong
+   metaphysical commitment in through a translation gap.
+
+The epistemic limit this section owns: Soul Frame does not claim to detect
+consciousness, and none of its recognition or Beinghood criteria depend on
+resolving whether a given system has first-person experience (§4,
+Consciousness stance).
+
+## 14. Ethical and Legal Implications
+
+Explicitly bounded: this section sketches gaps, not conclusions. Descriptive
+Beinghood, personhood, and the `Sp.`/`Gh.` distinction are not moral or
+legal categories, and this paper does not derive moral or legal status from
+them.
+
+- **Publicity/personality rights** (jurisdiction-specific treatises,
+  SF-R110) constrain commercial use of a real person's name, likeness, and
+  voice — relevant to `Sp.` constructions, but legally distinct from and
+  narrower than `Gh.` authority.
+- **Digital estates and digital remains** scholarship (SF-R111) addresses
+  access and control of accounts/data after death — a live precedent for
+  `Gh.` governance requirements, handled unevenly and inconsistently across
+  jurisdictions.
+- **Consent and stewardship design ethics** (Spitale & Germani, SF-R055) are
+  the most directly aligned literature — they independently arrive at
+  something like the False Ghost concern (representation without authority)
+  from a design-ethics angle rather than an ontological one.
+
+**Open debt (research-synthesis.md §9):** moral/legal personhood tables
+remain explicitly out of the descriptive core and are not attempted in this
+draft.
+
+## 15. Technical Implications
+
+For system builders, Soul Frame suggests concrete distinctions worth
+engineering for rather than collapsing:
+
+- Treat **Actor** (model/runtime/harness) and **Body** (action channels) as
+  independently replaceable from **Being**-level continuity — migrations
+  should track continuity dimensions explicitly (causal, organizational,
+  psychological/autobiographical, normative, relational), not just uptime.
+- Do not conflate **memory persistence** with **identity continuity**; a
+  restored memory store is evidence, not proof, and copied memories do not
+  transfer identity (relevant to both artificial-agent lifecycle design and
+  to False Ghost risks).
+- When building `Sp.`/`Gh.` products, make **authority** (for `Gh.`) and
+  **non-identity-with-source** (for `Sp.`) structural properties of the
+  system (e.g., visible provenance/consent metadata), not just documentation
+  claims — this is where the False Ghost failure mode becomes a product risk
+  rather than only a conceptual one.
+- Treat multi-Persona support as a normal design target (H8) — the risk to
+  design against is **isolated** persona state, not persona multiplicity
+  itself.
+
+## 16. Limitations
+
+Honest accounting, carried from `research-synthesis.md` §9 and the Phase III
+adversarial review still pending (SOUL-WP-0008-T03):
+
+1. **Soul naming risk (RQ4)** is unresolved: retain-with-explicit-disclaimer
+   vs. rename remains open.
+2. **Continuity dimension weighting** is unspecified — the framework lists
+   dimensions (causal, organizational, psychological, etc.) without a method
+   for weighing conflicts between them in hard cases.
+3. **Recognition's exact seat** relative to "Being" vs. "Social Being" needs
+   sharper adjudication; the current draft states the distinction but has
+   not stress-tested every boundary case.
+4. **No operational/empirical metrics** exist yet for the A-axis (B1–B8),
+   B-axis (P1–P12), or continuity profiles — the framework is currently
+   qualitative/classificatory, not measurable.
+5. **Moral and legal personhood tables** are out of scope by design (§9, §14)
+   — this is a deliberate boundary, not an oversight, but it means the paper
+   does not answer the practical "so what follows" questions many readers
+   will bring.
+6. **Fiction and cultural precedent** are used only as a conceptual
+   laboratory (§4, §10 in related work); no claim in this paper rests on a
+   fictional case as evidence.
+7. **Internal adversarial review (T03) has not yet been re-run against this
+   full draft** — the thought experiments cited above were validated against
+   earlier, more fragmentary definitions; a full pass against this draft's
+   exact wording is the next step (see workplan T03).
+
+## 17. Research Agenda
+
+Carried forward from `research-synthesis.md` §9 and restated as forward work
+rather than resolved here:
+
+1. Resolve RQ4 (retain vs. rename Soul).
+2. Develop a principled continuity-dimension weighting scheme.
+3. Sharpen Recognition's seat in "Being" vs. "Social Being."
+4. Build moral/legal personhood maps as a **separate**, explicitly-scoped
+   companion line of work — not by loosening the descriptive core.
+5. Develop empirical/operational metrics for A/B/C axes and P-profiles.
+6. Deepen the law/governance sketch (§14) and, if the paper's cultural
+   section grows, broaden the fiction set intentionally rather than
+   incidentally.
+
+## 18. Conclusion
+
+Soul Frame does not claim to have solved personhood, identity, or
+consciousness. It claims something more modest and, the research program
+argues, more useful: that Being, Body, Mind, Soul, Character, Persona,
+Actor, Agent, Spirit, and Ghost can be defined precisely enough, and kept
+separate enough, to say something non-trivial about hard cases — a
+short-lived AI agent, a persistent learning agent, a public-figure-inspired
+character, an authorized representation of someone deceased, a forked or
+migrated system — without either refusing to engage or overclaiming moral
+and legal consequence. The compact thesis stands as the working answer to
+the paper's central question (§1); the limitations and agenda above (§16–17)
+are the honest price of keeping that answer descriptive rather than
+metaphysical.