soul-frame/paper/related-work.md
tegwick 6b06d3d391 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
2026-09-28 14:30:40 +02:00

272 lines
13 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Related Work
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/*/`.
---
## 1. Systems theory, cybernetics, and organizational closure
**Contribution:** the base vocabulary for Being as a self-maintaining,
organizationally closed process rather than a bounded object.
- 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.