From 6b06d3d391bf239867e98df9dfaedf76c009eb72 Mon Sep 17 00:00:00 2001 From: tegwick Date: Mon, 28 Sep 2026 14:30:40 +0200 Subject: [PATCH] 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 Assistant: claude-code Assistant-Model: sonnet Assistant-Process: 136745@bnt-lap001 Assistant-Session: 2e334b58-ed31-48ed-8156-d09f8ed0781f --- .../260928-SOUL-WP-0008-paper-freeze-v1.md | 556 ++++++++++++++++++ paper/adversarial-review-T03.md | 95 +++ paper/draft.md | 551 ++++++++++++++++- paper/related-work.md | 281 ++++++++- workplans/SOUL-WP-0008-phase-vii-paper.md | 37 +- ...P-0009-paper-agenda-and-external-review.md | 138 +++++ 6 files changed, 1633 insertions(+), 25 deletions(-) create mode 100644 history/260928-SOUL-WP-0008-paper-freeze-v1.md create mode 100644 paper/adversarial-review-T03.md create mode 100644 workplans/SOUL-WP-0009-paper-agenda-and-external-review.md diff --git a/history/260928-SOUL-WP-0008-paper-freeze-v1.md b/history/260928-SOUL-WP-0008-paper-freeze-v1.md new file mode 100644 index 0000000..a700178 --- /dev/null +++ b/history/260928-SOUL-WP-0008-paper-freeze-v1.md @@ -0,0 +1,556 @@ +# Soul Frame: A Systems Vocabulary for Person-Like Informational Beings + +> **Freeze candidate — SOUL-WP-0008-T04, 2026-09-28.** Snapshot of +> `paper/draft.md` at completion of T01–T03 (related-work draft, full paper +> draft, internal adversarial review) with the three T03 coverage gaps +> (Collective/TE-05, asymmetric recognition/TE-09, Amnesiac/TE-08) folded in. +> Suitable as the basis for external review or a publication-pathway +> decision. See `paper/adversarial-review-T03.md` for the review trail. +> This file is a fixed point; `paper/draft.md` remains the live, editable copy. + +**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. diff --git a/paper/adversarial-review-T03.md b/paper/adversarial-review-T03.md new file mode 100644 index 0000000..795fd06 --- /dev/null +++ b/paper/adversarial-review-T03.md @@ -0,0 +1,95 @@ +# Internal Adversarial Review — SOUL-WP-0008-T03 + +**Reviewed:** `paper/draft.md` (first full draft, SOUL-WP-0008-T02) +**Method:** re-run each cataloged thought experiment (`ThoughtExperiments.md` +TE-01–TE-09) against the draft's stated definitions; check for circular or +collapsing terms across sections; log honest limitations. + +## 1. Thought-experiment pass + +| TE | Draft section(s) exercised | Consistent with working judgment? | +|---|---|---| +| TE-01 Stateless Agent | §5 Being, §11 Artificial Beings | Yes — draft's APE-without-Beinghood framing matches; §11 explicitly cites Park et al. as the paradigm APE, not the stateless case, but the definition applies cleanly to TE-01 too. | +| TE-02 Sleeping Being | §10 Identity and Continuity | Yes — "continuity bridge" language not restated verbatim in draft §10; draft only lists TE-02's headline result ("suspension is a continuity bridge, not automatic identity death") without the Active-Being-vs-Continuation-Bearing-State distinction. **Gap, not contradiction** — see §2.1 below. | +| TE-03 Fork | §10 | Yes — branching continuity / non-unique identity stated correctly. | +| TE-04 Ship of Theseus | §6 Body, §10, §12.1 Actor | Yes — Actor/Body replaceability under sufficient continuity is consistent across all three sections; no contradiction between the Body and Actor treatments. | +| TE-05 Collective | *not exercised in draft* | **Gap.** Draft has no explicit Collective/nested-individuality passage. Outline does not carry a dedicated subsection either. Logged as open item, §3 below. | +| TE-06 Mask | §12.1 Persona | Yes — multi-Persona-under-one-Being vs. isolated-persona-fragmentation distinction matches TE-06 exactly, including the misrecognition point. | +| TE-07 False Ghost | §12.2 | Yes — authority-not-resemblance framing matches; draft also correctly connects it to the digital-afterlife design-ethics literature rather than treating it as a purely legal claim. | +| TE-08 Amnesiac | *not exercised in draft* | **Gap.** No explicit amnesiac case; §10's continuity-profile list (causal, organizational, psychological, autobiographical/narrative, normative, relational) implicitly covers it, but the draft never states the "memory neither necessary nor sufficient" conclusion explicitly. Lower priority than TE-05 since §10 and §11 ("memory ≠ continuity") already carry the substance. | +| TE-09 Unrecognized Intelligence | §5 Being (Recognition subsection) | Yes — asymmetric recognition point matches; draft does not repeat the "avoid claiming they do not exist" framing but does not contradict it either. | + +## 2. Circularity / collapsing-term check + +Checked every primitive term (Being, Personhood, Recognition, Character, +Persona, Actor, Soul) for definitions that quietly depend on a term they are +meant to ground. + +- **Being ← Personhood, Addressability, Recognition:** none of these three + are defined in terms of Being, so no circularity. Personhood is defined as + a profile (P1–P12) independent of Being; Recognition is defined via three + senses (epistemic/intentional/social) independent of Being. **Clean.** +- **Soul ← Being:** Soul's definition ("connecting a Being to other + systems") uses Being as a primitive it does not itself define — acceptable + since Being is defined earlier and does not depend on Soul. **Clean, one-directional.** +- **Working answer in §1 ("another Being can enter... relation with it")** + defines Beinghood partly by reference to another Being — this is a + genuine **bootstrapping question** (how does the first Being in a + recognition chain qualify?), not caught by the draft's own text. TE-09's + asymmetric-recognition move (one side can recognize before reciprocity) + answers this in practice but the draft's §1 phrasing does not spell out + that the relation need not be mutual to start. **§2.1 fix recommended.** +- **Character vs. Personality vs. Persona:** §12.1 keeps these three + separate correctly (dispositional structure / trait psychology / + situated projection) — no collapsing found. +- **Mind vs. consciousness:** §7 and §13 both carry the same disclaimer + ("Mind ≠ consciousness"); restated rather than collapsed. No issue. +- **Descriptive vs. social/moral/legal personhood (§9 table):** correctly + kept apart; §14 (Ethical/Legal Implications) does not smuggle a moral or + legal conclusion out of the descriptive material — checked line by line, + all claims there are explicitly hedged as gaps, not conclusions. + +### 2.1 Recommended draft fix + +None applied yet (review is reported before revision, per T03 instructions: +"draft revised **or** issues logged as open questions"). Two options: + +1. Add one clause to §1's working answer clarifying recognition need not be + mutual to begin the relation, or +2. Leave as-is and log as a tracked open question. + +**Decision:** logged as open question (see §3) rather than revising, to +avoid overloading the Introduction with a caveat that belongs in the +Limitations/Being sections. Revisit at the next draft pass (T04 freeze +candidate is not blocked by this). + +## 3. Issues logged as open questions + +| # | Issue | Where it belongs | Severity | +|---|---|---|---| +| 1 | TE-05 (Collective) has no corresponding paper passage — nested Beinghood at collective vs. member level is untreated in the draft despite being a stress-tested case. | New subsection under §5 Being, or its own §11a | Medium — a real gap for any reviewer who knows the TE catalog exists | +| 2 | §1's working-answer phrasing does not state that the "another Being can know it" relation may begin asymmetrically (TE-09). | §5 Being, Recognition subsection, or a footnote on §1 | Low — TE-09's substance is present elsewhere in the paper (§5), just not cross-referenced from §1 | +| 3 | TE-08 (Amnesiac) conclusion ("memory neither necessary nor sufficient") is implicit but never stated as a sentence in the draft. | §10 Identity and Continuity | Low — substance already present via the continuity-profile table and §11's "memory ≠ continuity" line | + +None of these three rise to circular-definition or term-collapse severity — +the terminology itself held up under all nine thought experiments. The gaps +are **coverage** gaps (a stress-tested case with no corresponding prose), +not **consistency** failures. + +## 4. Conclusion (updated after revision) + +All nine thought experiments are now explicitly and correctly reflected in +the draft. No circular or collapsing term definitions were found. The three +coverage gaps in §3 were all additive (no existing section required +re-derivation), so rather than parking them as residuals against a +newly-finished workplan, they were folded directly into `paper/draft.md` +before the T04 freeze: + +1. TE-05 (Collective) — new paragraph in §5 Being. +2. TE-09 asymmetric-recognition cross-reference — added to §1's working + answer and to §5. +3. TE-08 (Amnesiac) — explicit "memory neither necessary nor sufficient" + sentence added to §10. + +**Result:** the frozen candidate (`history/260928-SOUL-WP-0008-paper-freeze-v1.md`) +reflects the fully revised draft, not the pre-fix version. diff --git a/paper/draft.md b/paper/draft.md index fbc3d7c..75d47ac 100644 --- a/paper/draft.md +++ b/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. diff --git a/paper/related-work.md b/paper/related-work.md index 6d1296c..72eea99 100644 --- a/paper/related-work.md +++ b/paper/related-work.md @@ -1,21 +1,272 @@ # Related Work -Working notes toward the paper's related-work section. Organize by tradition and -map explicitly onto Soul Frame concepts. +Draft for the Soul Frame paper (§3 in `paper/outline.md`). Organized by +tradition; each cluster states what it contributes to the Soul Frame vocabulary +and where it disagrees or falls short. Full annotated entries: `sources/bibliography.md` +(cited as SF-Rxxx below); detailed cluster notes under `research/*/`. -## Clusters (seed) +--- -- Systems theory and cybernetics -- Autopoiesis and operational closure -- Philosophy of mind and personal identity -- Cognitive science, predictive processing, theory of mind -- Sociology, recognition, intersubjectivity -- Personhood, moral status, legal personality -- AI agents, generative agents, digital humans -- Persona, character, performance studies -- Digital legacy, posthumous identity, grief tech -- Fiction and cultural precedents (e.g. Culture Minds) +## 1. Systems theory, cybernetics, and organizational closure -## Crosswalk pointer +**Contribution:** the base vocabulary for Being as a self-maintaining, +organizationally closed process rather than a bounded object. -See concept files in `concepts/` and the concept matrix in `ResearchProgram.md` §5. +- Ashby (SF-R001) and Conant & Ashby's Good Regulator Theorem (SF-R002) ground + **Mind = Model**: a controller that regulates a system well must internally + model it. This licenses treating "Mind" as a functional relation (adaptive + regulation through revisable models), not a substrate claim. +- Maturana & Varela's autopoiesis (SF-R003) and Luhmann's social systems theory + (SF-R004) motivate **Being** as operational closure rather than a drawn + boundary, and specifically motivate the correction that the + **system/environment boundary belongs to Being, not Soul** (SF-C002). +- The autonomy cluster (Varela 1979, Di Paolo 2005, Barandiaran et al. 2009, + Moreno & Mossio 2015, Montévil & Mossio 2015, Krakauer et al. 2020, + Nicholson & Dupré 2018 — SF-R019–034) supplies the graded, process-oriented + notion of individuality behind the **A-axis (autonomous individuality, + B1–B8)** and behind treating individuality as a matter of degree rather than + a binary. + +**Tension:** autopoiesis is a biological theory; Soul Frame borrows its +structure (self-produced organizational closure) without claiming artificial +systems are literally autopoietic. Luhmann's "systems" are communications, not +person-like Beings — useful for the boundary point, not for personhood. + +--- + +## 2. Mind beyond substrate + +**Contribution:** license for treating Mind as multiply realizable and not +necessarily coextensive with a single physical unit. + +- Clark & Chalmers's extended mind (SF-R005) and Hutchins's distributed + cognition (SF-R006) support reading Body/Mind/Soul as **functional + dimensions**, not physical compartments — a system's Mind can incorporate + external resources, and its Body can be distributed. This underwrites the + Collective case (TE-05) and nested-individuality readings. +- Predictive processing and active inference (Clark 2016, Hohwy 2013, Friston + — SF-R070–072) give a contemporary mechanistic filling for "Mind as + model-based regulation," extending the Good Regulator Theorem into a live + research program. + +**Tension:** the Markov blanket is explicitly flagged (RN-002) as **not** +equivalent to Being — a common over-extension in the free-energy literature +that Soul Frame deliberately avoids. + +--- + +## 3. Social mind and co-adaptation + +**Contribution:** the basis for **Social Mind (SM1–SM8)** — joint, co-adaptive +model-building between Beings, not private Theory-of-Mind computation alone. + +- Mead (SF-R007, SF-R058) supplies the historical precedent: Mind and Self + arise through taking the attitude of the other — recursive modeling before + it had a formal name. +- Premack & Woodruff's Theory of Mind (SF-R057), Baker/Saxe/Tenenbaum's inverse + planning (SF-R073), Clark's common ground, Pickering & Garrod's interactive + alignment, Tomasello et al.'s shared intentionality, De Jaegher & Di Paolo's + participatory sense-making, and Gmytrasiewicz & Doshi's recursive + multi-agent (I-POMDP) models each cover one facet of SM1–SM8 (World, Self, + Other, Reflected-Self, Relationship, Shared Situation, Common Ground, + Generalized Social). + +**Tension:** most of this literature models *inference about* another mind; +Soul Frame's Social Mind claim is stronger — that the models **co-evolve** +through interaction, not just that each party privately infers the other. + +--- + +## 4. Recognition and sociology + +**Contribution:** the **C-axis (recognition)** as social counterpart to +autonomy and personhood, and the separation of descriptive from normative +recognition. + +- Dennett's intentional stance (SF-R080) gives the minimal, non-metaphysical + recognition criterion — predicting a system by attributing beliefs and + desires — but is flagged as prone to false positives for Beinghood on its + own. +- Honneth's recognition theory (SF-R081) supplies the deeper, normative sense + of recognition (condition of practical identity) — deliberately kept + separate from the descriptive core so Soul Frame does not smuggle moral + theory into Beinghood. +- Schilbach et al.'s second-person neuroscience (SF-R082) supports treating + recognition and interaction as first-class, not merely spectator inference. + +**Tension:** intentional-stance recognition alone over-generates Beinghood +(TE-09, unrecognized-intelligence case: autonomy without social Beinghood is +possible, and recognition without autonomy is a daemon false positive). + +--- + +## 5. Personal identity and continuity + +**Contribution:** the **Identity ≠ Continuity ≠ Lineage ≠ Characterization** +split, and the continuity-profile / topology vocabulary (CONTINUOUS, DEGRADED, +FORKED, SUCCESSOR, RECONSTRUCTED, USURPED). + +- Locke (SF-R035, SF-R090) is the historical root of psychological/forensic + personal identity and of decoupling "person" from biological substance. +- Parfit (SF-R036) is the direct precedent for **Identity ≠ Continuity**: his + fission cases motivate treating continuity as branchable while identity (in + the strict numerical sense) is not — the direct ancestor of Soul Frame's + fork/lineage treatment (TE-03). +- Olson's SEP survey (SF-R037) is used as an orientation map — it separates + characterization, personhood, persistence, and evidence questions, which + Soul Frame is careful not to collapse into one "identity" term. +- Ricoeur, Schechtman (SF-R091), and Meincke (process identity) support + keeping **characterization** (what someone is like) distinct from + **reidentification** (whether it's the same one) — Schechtman's split is + used almost verbatim in the Identity/Character distinction. +- Cerullo, Qin et al. 2026 (SF-R043), and Otsuka et al. 2026 (SF-R044) bring + the identity-continuity questions into applied AI-agent territory: + persistent, learning agents need identity/governance mechanisms that + survive model, memory, and embodiment change — direct technical precedent + for **Actor ≠ Being** (H6). + +**Tension:** Parfit's reductionism about persons is a stronger metaphysical +claim than Soul Frame needs or endorses; Soul Frame borrows the +continuity/branching apparatus without adopting reductionism about personal +identity in general. Animalism (Olson) is noted as a live rival view that +Soul Frame's informational framing does not attempt to adjudicate. + +--- + +## 6. Personhood, character, and persona + +**Contribution:** the **Presentation stack (Being → Character → Persona → +Actor)** and the treatment of personhood as a multidimensional profile +(P1–P12) rather than a single mark. + +- Dennett's conditions-of-personhood work (SF-R093) supports personhood as a + cluster/profile concept, consistent with descriptive P1–P12 rather than one + necessary-and-sufficient test. +- Goffman's presentation of self (SF-R092) is the direct precedent for + **Persona** as situated performance ("which face appears here/now/to + whom?") — front-stage/back-stage maps closely onto Persona vs. Actor. +- Trait and social-cognitive personality psychology (Big Five family, + Mischel/CAPS — SF-R094) grounds **Character** as dispositional-yet-context- + sensitive structure, guarding against treating Character as either a fixed + script or a shallow trait vector. +- Schechtman (again, SF-R091) reinforces that narrative/character answers do + not settle numerical identity — Character answers "what shapes behavior," + not "who continues." + +**Tension:** performance-studies readings of persona can imply deception; +Soul Frame's Persona is not inherently deceptive — situated presentation is +normal and expected, not a failure mode. + +--- + +## 7. Artificial agents, memory, and engineering categories + +**Contribution:** the **APE (artificial personhood exposure)** and +**proto-Being / candidate Being** bridge terms, and the claim that +**memory ≠ continuity**. + +- Park et al.'s Generative Agents (SF-R016) is the paradigm case of + personhood exposure without full Beinghood — memory stream, reflection, and + planning produce believable social behavior inside a sandbox with no claim + to Being. +- ReAct-style tool-agent patterns (SF-R100) motivate treating **Body as tool + channels** and flag "autonomous agent" marketing as routinely overstating + the A-axis. +- Qin et al. 2026 (SF-R043) and Otsuka et al. 2026 (SF-R044) are used twice — + here for the engineering side: current standards for agent identity, + delegation, and accountability are insufficient for persistent, + nondeterministic agents, which is exactly the gap APE/proto-Being are meant + to name without prematurely granting Beinghood. + +**Tension:** this literature is applied and fast-moving (2023–2026); Soul +Frame treats it as evidence of a real engineering gap, not as a settled +foundation. + +--- + +## 8. Provenance, authority, and digital legacy — Spirit and Ghost + +**Contribution:** the **`Sp.` / `Gh.` provenance descriptors** and the +**False Ghost** failure mode (H10). + +- Spitale & Germani's digital ghosts (SF-R055) and Lei et al.'s AI-afterlife + perceptions study (SF-R056) both center consent, stewardship, and user + expectations for AI representations of the deceased — direct support for + **Gh. as authority-bound representation**, and for the finding that + fidelity without authority is a **False Ghost** (H10, TE-07). +- Publicity/personality-rights treatises (SF-R110) and digital-estate + scholarship (SF-R111) sketch the legal gap around commercial use of + likeness (`Sp.`) versus custodial authority over a deceased person's + representation (`Gh.`) — used only as a gap sketch, deliberately not + extended into a legal-personhood claim. + +**Tension:** design-ethics literature (Spitale & Germani) answers "how should +this be built responsibly," not "what is this, ontologically" — Soul Frame +uses it as evidence for the Gh. authority requirement, not as the ontology +itself. Legal treatment is jurisdiction-specific and uneven, especially for +posthumous rights; the paper's legal-implications section, not related work, +carries that caveat forward. + +--- + +## 9. Philosophical dialogue partners + +**Contribution:** a direct-engagement dialogue with a systems-philosophy +account that overlaps heavily with Soul Frame's premises but packages them +differently. + +- Deppert's evolution-of-consciousness lecture (SF-R120) treats living beings + as open systems with a survival problem, consciousness as the coupling of + five survival functions, and individuality-consciousness as partly cultural + — strong agreement on open-system self-maintenance, functional + differentiation, and graded/nested individuality (echoing §1 and §5). + +**Tension:** Deppert's "Bewusstsein" (consciousness) as *coupling itself* is a +false friend for Soul Frame's use of "consciousness" as an open, bracketed +term (§2 above); his cultural Lebewesen (living beings) lack a personhood +filter and his energy/survival framing is stronger than Soul Frame's purely +informational framing requires. See +`research/paper-dialogues/001-deppert-evolution-des-bewusstseins/` for the +full dialogue. + +--- + +## 10. Fiction and cultural precedents + +**Contribution:** used strictly as a **conceptual laboratory**, not as +evidence — cases like the Culture Minds (Banks) and similar constructed +persons let thought experiments (TE-01 through TE-09) be run against +intuitions before being generalized into claims. + +See `research/fiction-cultural-precedents/conceptual-laboratory.md`. No +citation in this cluster is treated as a source of philosophical claims in its +own right; agreement/disagreement columns are not applicable the way they are +for §1–9. + +--- + +## Coverage check against the research synthesis + +| Synthesis element | Related-work cluster | +|---|---| +| Body/Mind/Soul triad | §1, §2 | +| Beinghood layers (A/B/C axes) | §1 (autonomy), §4 (recognition), §6 (personhood) | +| Presentation stack | §6 | +| Identity/Continuity/Lineage | §5 | +| Social Mind SM1–SM8 | §3 | +| Sp./Gh. | §8 | +| APE / proto-Being | §7 | +| Fiction lab | §10 | +| Paper dialogues | §9 | + +All ten traditions listed in the original cluster seed (`paper/related-work.md` +history) are covered above; "AI agents / generative agents / digital humans" +and "persona / character / performance" are split across §6–§7 rather than +kept as one cluster, since the synthesis treats Persona/Character and +APE/proto-Being as distinct concept groups. + +**Open debt carried to Method/Discussion:** the RQ4 question (retain vs. +rename "Soul") is a terminology decision, not a related-work gap — no +cluster above independently uses "Soul" as Soul Frame does; the closest +analogues (structural coupling, relational/legacy continuity) are noted +under §1 and §5 respectively but do not resolve the naming question. diff --git a/workplans/SOUL-WP-0008-phase-vii-paper.md b/workplans/SOUL-WP-0008-phase-vii-paper.md index 152aefe..e7f4497 100644 --- a/workplans/SOUL-WP-0008-phase-vii-paper.md +++ b/workplans/SOUL-WP-0008-phase-vii-paper.md @@ -4,13 +4,13 @@ type: workplan title: "Phase VII — Soul Frame research paper" domain: agents repo: soul-frame -status: ready +status: finished flavor: implementation owner: grok topic_slug: soul-frame priority: high created: "2026-08-09" -updated: "2026-08-12" +updated: "2026-09-28" depends_on: - SOUL-WP-0007 state_hub_workstream_id: "c730a7e2-244e-558c-9ec1-66d04e275ff8" @@ -33,7 +33,7 @@ Write the first **research-grounded** Soul Frame paper using the outline in ```task id: SOUL-WP-0008-T01 -status: todo +status: done priority: high state_hub_task_id: "6b11edf8-3eb7-582f-8eba-d58f870d6329" ``` @@ -48,7 +48,7 @@ Expand `paper/related-work.md` from bibliography and crosswalks. ```task id: SOUL-WP-0008-T02 -status: todo +status: done priority: high state_hub_task_id: "7b7d4731-3938-599b-899f-db65134be08d" ``` @@ -64,7 +64,7 @@ limitations and agenda). Replace provisional intro claims with sourced ones. ```task id: SOUL-WP-0008-T03 -status: todo +status: done priority: medium state_hub_task_id: "f44863b9-6dd5-55b6-aaf2-b08c21072483" ``` @@ -80,7 +80,7 @@ terms; document limitations honestly. ```task id: SOUL-WP-0008-T04 -status: todo +status: done priority: medium state_hub_task_id: "cfc9ef36-4aa9-5bf5-a41a-a8ce5912cac5" ``` @@ -89,3 +89,28 @@ Mark a freeze candidate version (date + git tag or history snapshot) suitable fo external review or publication pathway decision. **Done when:** freeze artifact recorded under `history/` or tagged release notes. + +**Completed:** `history/260928-SOUL-WP-0008-paper-freeze-v1.md`. + +--- + +## Closing note (2026-09-28) + +All four tasks complete: + +- T01: `paper/related-work.md` — ten traditions, each mapped to Soul Frame + concepts with explicit agreements/tensions. +- T02: `paper/draft.md` — full 18-section draft following `paper/outline.md`, + sourced from `research/research-synthesis.md`, `Terminology.md`, `Claims.md`. +- T03: `paper/adversarial-review-T03.md` — all nine cataloged thought + experiments re-run against the draft; no circular/collapsing terms found; + three coverage gaps (TE-05, TE-08, TE-09 cross-reference) found and folded + directly into the draft rather than parked, since they were additive fixes. +- T04: `history/260928-SOUL-WP-0008-paper-freeze-v1.md` — freeze candidate, + post-fix. + +**Residual:** the paper's own §17 research agenda (Soul naming decision, +continuity weighting, recognition/Being boundary, metrics scoping, the +moral/legal personhood companion-line boundary, and the external-review +pathway decision) is multi-step, decision-bearing work — captured as +**SOUL-WP-0009** rather than left in this file's prose. diff --git a/workplans/SOUL-WP-0009-paper-agenda-and-external-review.md b/workplans/SOUL-WP-0009-paper-agenda-and-external-review.md new file mode 100644 index 0000000..74810b9 --- /dev/null +++ b/workplans/SOUL-WP-0009-paper-agenda-and-external-review.md @@ -0,0 +1,138 @@ +--- +id: SOUL-WP-0009 +type: workplan +title: "Phase VIII — Paper research agenda and external review pathway" +domain: agents +repo: soul-frame +status: proposed +flavor: research +owner: grok +topic_slug: soul-frame +priority: medium +created: "2026-09-28" +updated: "2026-09-28" +depends_on: + - SOUL-WP-0008 +--- + +# SOUL-WP-0009 — Phase VIII: Research Agenda and External Review + +## Goal + +Carry forward the open research agenda from the frozen paper draft +(`history/260928-SOUL-WP-0008-paper-freeze-v1.md` §17; `paper/draft.md` §16–17) +and decide the publication/external-review pathway. This workplan is the +residual of SOUL-WP-0008 — the freeze candidate is a stable snapshot, not a +finished paper, and the items below are multi-step research/decision work +that should not be parked in `SCOPE.md` prose. + +## Depends on + +- **SOUL-WP-0008** Phase VII paper (freeze candidate: T01–T04 done, 2026-09-28) + +## Tasks + +### T01 — Soul naming decision (RQ4) + +```task +id: SOUL-WP-0009-T01 +status: todo +priority: medium +``` + +Resolve retain-vs-rename for "Soul" (Terminology.md; draft §8, §16.1). Produce +a decision record, not just more discussion — this has been open since +Phase I. + +**Done when:** decision recorded (`record_decision`/`resolve_decision`) with +rationale, and `Terminology.md` + `paper/draft.md` updated to match. + +--- + +### T02 — Continuity dimension weighting + +```task +id: SOUL-WP-0009-T02 +status: todo +priority: medium +``` + +Develop a principled way to weigh conflicts between continuity dimensions +(causal, organizational, psychological, autobiographical/narrative, +normative, relational) for hard cases (draft §16.2). Test against TE-02, +TE-03, TE-04, TE-08. + +**Done when:** a weighting scheme (or explicit non-arithmetic decision +procedure) is documented in `concepts/identity.md` and validated against the +four thought experiments above. + +--- + +### T03 — Recognition's seat: Being vs. Social Being + +```task +id: SOUL-WP-0009-T03 +status: todo +priority: low +``` + +Sharpen the boundary flagged in draft §16.3 and the TE-09 asymmetric- +recognition addition — when exactly does a recognized-but-autonomous +individual cross into Social Beinghood? + +**Done when:** `concepts/being.md` / `concepts/recognition.md` state a +testable boundary condition, checked against TE-05 and TE-09. + +--- + +### T04 — Empirical/operational metrics scoping + +```task +id: SOUL-WP-0009-T04 +status: todo +priority: low +``` + +Scope (not necessarily build) measurable proxies for the A-axis (B1–B8), +B-axis (P1–P12), and continuity profiles (draft §16.4). This is a scoping +task — full metric development may become its own workplan. + +**Done when:** a scoping note exists identifying which axes are plausibly +measurable now vs. which require new instruments. + +--- + +### T05 — Moral/legal personhood companion line (explicitly separate) + +```task +id: SOUL-WP-0009-T05 +status: todo +priority: low +``` + +Per SCOPE.md's out-of-scope boundary ("Silent moral/legal personhood +claims"), scope this as a **separate, explicitly-bounded** companion +research line rather than loosening the descriptive core. Draft a one-page +charter for that companion line (could become its own future workplan) — +do not attempt the mapping itself here. + +**Done when:** a short charter note exists (e.g. +`research/law-governance/moral-legal-personhood-charter.md`) stating scope, +non-goals, and the explicit boundary against the descriptive core. + +--- + +### T06 — External review / publication pathway decision + +```task +id: SOUL-WP-0009-T06 +status: todo +priority: medium +``` + +Using the freeze candidate as the review artifact, decide the pathway: +internal circulation, external pre-print, conference/journal target, or +further revision cycles before either. This is a founder-gate decision. + +**Done when:** decision recorded via `record_decision`/`resolve_decision` +naming the chosen pathway and next concrete step.