*(Historical record, filed 14 July 2026, before the v2.0 rename: "resolution" herein is the framework term since renamed "cohering", and claim labels are as of v1.6. Preserved unedited.)*

# The Container Problem
**Working note v0.1 · Space Immanence · 14 July 2026**
**Status: pre-theoretical claim, post kill-check. Circulated to be attacked, not admired.**

## The claim

Experience is widely reported and described as happening *inside* something: a mind, a field, a space of awareness that contents are presented to. Call this the container structure. Our claim, at its current size: the container structure of experience-as-such is an unaddressed problem intuition in the consciousness literature, and figure-ground darkening is a candidate mechanism for it.

The mechanism in brief. Any system that models by selective illumination (attention, prediction, salience) produces at every moment an unpresentable remainder: the ground that funds the current figure but cannot itself be shown. The system must model this remainder somehow. We propose that under compression constraints the default encoding of a more-that-cannot-be-shown is a homogeneous, surrounding, empty medium, and that this encoding is read phenomenologically as a container. On this account the container error (already central to Space Immanence v1.5 as diagnosis) acquires a generative mechanism: it is what partial illumination produces by default. Hold the vocabulary as provisional throughout; "darkening" is a placeholder for a formal object we do not yet have.

## What the kill-check established

The broad version of this project is dead and we should say so internally. "Introspection misrepresents its own basis" is the reigning consensus programme, not an opening: Metzinger's phenomenal transparency, Graziano's attention schema, and roughly half of Chalmers's fifteen canvassed solutions to the meta-problem all live there. Additionally, one of our original predictions is already an observed result, not a prediction: the pure-awareness literature (Metzinger's MPE programme, and the MPE-92M questionnaire) already documents the absence of a spatial frame of reference in deep contemplative states. Container collapse at the far end of practice is a consistency check we must pass, not credit we can claim.

What survived: the container shows up everywhere as metaphor and nowhere as derived mechanism. Metzinger's tunnel is a bandwidth story. Graziano's "ethereal essence vaguely localisable in space" is a caricature-schema story. Husserl named the horizon but gave it no generative mechanism and never tied it to the hard problem. And the container intuition does not appear in Chalmers's catalogue of problem intuitions at all. Nobody derives the empty surrounding medium from the unpresentable remainder. That move is unclaimed as of this note.

## The Step 0 finding, and the flip

A first-pass literature check changed the shape of the claim. Two results matter.

First, experimental philosophy (Sytsma and Machery; Sytsma and Ozdemir's "No Problem") provides evidence that ordinary people do not share the philosophers' concept of phenomenal consciousness. Contested, but any claim of the form "the container intuition is universal and compulsory" walks straight into this literature's line of fire.

Second, and more interesting: the adjacent territory has been measured, and what untrained populations report is a point, not a container. Starmans and Bloom found children and adults locate the self at or near the eyes, even for an alien with eyes on its chest; congenitally blind subjects locate the self in the head (Bertossa et al.); a recent large-N study finds people conceptualise consciousness as a spatio-temporally localised process in a confined brain region (the "Cartesian Folk Theater" result). The naive default is a located egocenter.

So the universality claim is out, and a trajectory claim replaces it. Untrained cognition encodes the darkened remainder as a point-observer. Introspective training, which turns attention onto the ground itself, transforms the point into a container. Sustained training collapses the container (the known MPE endpoint). **Point, then container, then collapse.** The darkening mechanism generates this sequence naturally, because the container should only appear once attention begins interrogating the remainder. No rival on the board predicts the full sequence: Graziano's schema has no reason to reshape with contemplative training, embodiment predicts the point but not the transformation, and conceptual metaphor (Lakoff and Johnson's MIND IS A CONTAINER) predicts vocabulary, not a stage-ordered phenomenology ending in collapse. The trajectory is now the discriminating signature.

## Studies, with kill authority stated

**A. MPE-92M reanalysis (reconnaissance only, no kill authority).** Public OSF dataset. Ask whether container-adjacent items (candidates within the published factors: Witness Consciousness; Emptiness and Non-egoic Self-awareness; Sensory Perception in Body and Space; Luminosity) separate from body-boundedness and spatial-frame items, and whether they vary non-monotonically with practice experience. The instrument was built from contemplative vocabulary on trained populations, so neither outcome settles the existence question; cross-sectional practice data also confounds development with survivorship. Useful for item harvesting and curve reconnaissance only.

**B. The residue instrument (kill authority, existence).** Pre-registered survey, swarm-study mould, primary arm non-meditators, stratified by introspective experience from the outset, cross-linguistic where feasible. It must separate three things people conflate: the perceptual spatial frame ("things appear arranged around me"), body-boundedness ("experience feels located in or near my body"), and the non-spatial container ("experiences happen in something they are presented to"). The claim survives only if the third loads separately after controlling for the first two, and only if the loading strengthens with introspective experience in the predicted direction. If container items track a language's metaphor inventory rather than experience strata, the phenomenon is Lakoff's, not ours.

**C. Formalising "cheapest model" (kill authority, mechanism).** Currently the load-bearing assertion. Required: show that for a system modelling its own selection process under stated compression constraints, the optimal encoding of the unpresentable remainder is medium-shaped, deriving all three signatures (homogeneous, surrounding, empty) rather than mere simplification, which would just restate Graziano. Discipline: candidate encoding space and cost function fixed adversarially before running (Fable as red team). Note: probing LLMs for container talk is contamination, not convergence, and proves nothing.

**D. Dissociation experiments (later, lab, after a Ganzfeld literature pass).** Body-model perturbations (rubber hand, full-body illusion) versus figure-ground dissolution (Ganzfeld), with crossed predictions on container-report stability. Predictions are about magnitudes, not just directions, so this needs power analysis, and the Ganzfeld arm only counts as prediction if existing phenomenology reports have not already described container destabilisation.

## Falsification conditions, fixed now

The idea goes in the drawer if any of the following hold: no separable container factor in B after controlling for body and frame; container loading flat or decreasing across introspective-experience strata in B; container reports tracking metaphor inventory across languages rather than experience; or a non-medium-shaped optimum in C under adversarially fixed constraints.

## Attack here first

The strongest surviving objection: the residue may not exist, i.e. the "non-spatial container" may fully reduce to body-anchoring plus perceptual frame plus contemplative vocabulary, leaving nothing for darkening to explain. B is designed to test exactly this and should be attacked at the item level before anything is fielded. Second objection: the trajectory could be an artefact of learning the container *vocabulary* partway through training rather than a phenomenological stage; the cross-linguistic arm and vocabulary-controls in B carry that weight. Third: "cheapest" in C is rigging-prone; the red-team constraint is not optional.

## Key sources

Metzinger, MPE papers and Gamma & Metzinger MPE-92M (PLOS ONE 2021, data on OSF); Graziano, attention schema (2013, 2019); Chalmers, "The Meta-Problem of Consciousness" (JCS 2018); Sytsma & Machery, "Two Conceptions of Subjective Experience" (Phil Studies 2010); Sytsma & Ozdemir (JCS 2019); Starmans & Bloom (Cognition 2012); Bertossa et al., "Point Zero" (2008); "Cartesian Folk Theater" (N≈2,057); Lakoff & Johnson (1980); Kövecses on metaphor universality/variation; Husserl on horizon-consciousness; Okumura, *Realizing Genjōkōan* (provenance of the illumination/darkening framing).