{
  "artifact": "Container Problem programme — machine layer",
  "programme": "container-problem",
  "status": "public-pilot",
  "statusVocabulary": ["private", "public-pilot", "active", "dormant", "drawered", "promoted"],
  "version": "0.2",
  "canonical": "https://space-immanence.com/container.html",
  "note": "This programme is quarantined from the Space Immanence claim graph on purpose. Its nodes use their own namespace (C1–C4) and never appear in claims.json; test/container-programme.test.mjs enforces the quarantine mechanically. Read noTransfer before reading anything else.",
  "framework": {
    "name": "Space Immanence",
    "frameworkVersion": "2.0",
    "relation": "Shares the container diagnosis as subject matter, not as support. Publishing or confirming results here changes no tier, no confidence number, and no claim text unless a transferRule fires."
  },
  "vocabulary": {
    "CRM": "Conditional remainder-modelling. Any system that models by selective illumination produces at every moment a remainder — content that funds the current figure but is not shown as figure. By default the remainder is not modelled at all, or is modelled minimally as a point-index (an egocenter). The medium encoding (homogeneous, surrounding, empty, in the operational senses frozen in the Study C constraint document §4.2) is predicted to become optimal only conditional on the remainder itself becoming a target of modelling, under sustained ground-directed attention. An existence claim over regimes, not a universality claim.",
    "darkeningRetired": "The placeholder name 'darkening' is retired for a substantive reason: 'dark' suggests the ground is experienced as dark by default, and the finding is that the ground is not experienced at all until attention makes it a target — the metaphor carried a false implicature, and a mechanism name that pre-loads the phenomenology it is supposed to derive is a liability. No mechanism vocabulary of any register appears in instruments, item wordings, preregistrations, or this machine layer; Study D's manipulation is named 'unstructured-field viewing' in all study documents.",
    "provenance": "The framing that seeded the programme is Dōgen's, via Okumura's Realizing Genjōkōan. That provenance is aesthetic lineage, disclosed as such, and explicitly not evidence."
  },
  "nodes": [
    {
      "id": "C1",
      "label": "Existence: a non-spatial container factor in first-person report, separable from the perceptual spatial frame and from body-boundedness",
      "tier": "pre-theoretical",
      "killStudy": "B",
      "falsifier": "No separable third factor emerges in the introspectively experienced strata under the pre-registered discriminant criterion (CFA nested-model comparison, thresholds frozen before fielding), with the item pool frozen after one adversarial revision round; a second null after that single permitted revision fires regardless of item-quality objections (drawerConditions[0]). All verdicts route through the items document's decision table, including its voiding gates.",
      "notes": "An empirical existence claim about a factor, not a claim about what the factor means. Fielded exclusively through the items document's machinery."
    },
    {
      "id": "C2",
      "label": "Trajectory: point-observer → container → collapse, ordered by introspective experience — a candidate signature, not a discriminating one",
      "tier": "pre-theoretical",
      "dependsOn": ["C1"],
      "killStudy": "B (longitudinal or randomised-training arm only)",
      "falsifier": "The pre-registered ordered contrast (naive below intermediate-trained) fails at the pre-set minimum effect size, or TOST equivalence testing at a pre-registered SESOI shows the naive-to-trained slope flat; container-stage development confined to space-instructed lineages also fires it (drawerConditions[1]). The collapse limb is a separately pre-registered prediction whose failure kills the collapse limb only.",
      "notes": "As of v0.2 this is a post-hoc arrangement of three known results, and honestly a two-mechanism trajectory: embodiment and egocentric modelling give the point, the MPE literature gives the collapse, and CRM's sole novel work is the stage-two transition. Kill authority over the within-person ordering claim comes only from the longitudinal or randomised-training arm; cross-sectional strata results in B are reconnaissance for the ordering claim, never verdicts on it. Stage one is a testable prediction B's non-meditator free-report arm must confirm, not an observed result. The located-theater outcome (point, then located theater, then collapse) is pre-registered as a named alternative, not a failure."
    },
    {
      "id": "C3",
      "label": "Mechanism (CRM): a medium-shaped optimum for encoding the far remainder, conditional on ground-directed attentional demand — the two-regime form",
      "tier": "pre-theoretical",
      "killStudy": "C",
      "confirmAuthority": "capped",
      "falsifier": "Under the frozen two-regime Study C: the regime-two optimum is robustly non-medium under the constraint document's decision rule, or any of its seven failure-reporting conditions holds, including formalisation failure, which is published as a result (drawerConditions[3]). Regime one producing a point-index is the theory's prediction, not a failure. A Tier-1 (analytic exchangeable-source model) failure kills the mechanism without a training run.",
      "notes": "The conditional two-regime form is the claim: regime one (remainder not queried) predicts a point or indexical optimum; regime two (ground-directed attentional demand) predicts the medium — an existence claim over non-rigged, independently justified task-and-rate regimes, forced by the constraint document's scalar-dominance analysis (compression alone always prefers the scalar; only task demands can pay for structure). Bridge asymmetry, stated in advance so a positive result cannot be inflated later: even a maximal positive result exhibits a data structure with three formal properties, and 'read phenomenologically as a container' is a bridge posit no optimisation can test. C retains full kill authority over the mechanism and capped, necessary-condition confirm authority only."
    },
    {
      "id": "C4",
      "label": "Dissociation: container-report stability tracks unstructured-field viewing, not body-model perturbation",
      "tier": "pre-theoretical",
      "dependsOn": ["C1"],
      "killStudy": "D",
      "falsifier": "Study D's crossed magnitude predictions fail at pre-registered power (drawerConditions[4]). Gated behind a Ganzfeld-phenomenology literature pass: if existing reports already describe frame or container destabilisation under homogeneous fields, that arm is retyped as retrodiction before anything is claimed."
    }
  ],
  "noTransfer": "No result in this programme attaches to any Space Immanence claim node (S1–S4, M1–M5, P1–P3), open hinge, or tier unless an entry in transferRules names the edge. In particular: confirmation of C3 is compatible with illusionism and the attention schema theory and supports neither S1's strong reading, nor M1, M2, M5, P1, nor P2 — for P2 it functions as a deflationary rival, not support: a confirmed CRM would explain the sense of inside-ness as a modelling strategy, and P2 would lose its explanandum to it. Treating a container-programme result as evidence for the fold is the exact conflation the swarm instrument's anti-goals forbid, in a nearer disguise. The firewall blocks credit in both the naive direction and the flattering one, and permits discredit to flow.",
  "transferRules": [
    {
      "from": "C1",
      "to": "S1",
      "direction": "both",
      "reading": "weak only (the container schema is load-bearing in the relevant cognition); the strong reading — that the hard problem and the spacetime-emergence problem are thereby distorted — is untouched in either direction",
      "grade": "supporting, never establishing; S1.confidence stays at or below its current pin (0.8) on confirmation — confirmation de-risks the weak reading, it does not raise the strong reading's standing",
      "condition": "Pre-registered confirmatory arm of Study B only. Symmetric negative commitment, published in advance: if drawerConditions cond-1-existence or cond-3-vocabulary fires, that firing is logged in this file's results[] AND surfaced as negative evidence on S1's weak reading in the framework's results ledger and changelog — the firewall blocks credit-laundering, not blame.",
      "mechanism": "On firing, an entry is added to claims.json evidence[] with attachesTo:'claims', bearsOnClaims:['S1'], carrying grade and nonTransfer text per the existing schema, and state.json programmes['container-problem'].transfersFired records the edge; no silent confidence edit."
    }
  ],
  "drawerConditions": [
    {
      "id": "cond-1-existence",
      "limb": "existence (C1)",
      "text": "No separable third factor emerges in the introspectively experienced strata under the pre-registered discriminant criterion, with the item pool frozen after one adversarial revision round; a second null after that single permitted revision fires regardless of item-quality objections. A factor appearing equally strongly in naive strata fires condition 2, not a save. All verdicts route through the items document's decision table, including its voiding gates.",
      "criterion": "CFA nested-model comparison at thresholds frozen before fielding shows no separable third factor in the introspectively experienced strata; a second null after the single permitted adversarial item-revision round fires the condition regardless of item-quality objections, with verdicts routed through the items document's §4.3 decision table."
    },
    {
      "id": "cond-2-trajectory",
      "limb": "trajectory (C2)",
      "text": "The pre-registered ordered contrast (naive below intermediate-trained) fails, or equivalence testing shows the naive-to-trained slope flat; the collapse limb is a separately pre-registered prediction whose failure kills the collapse limb only. Cross-sectional survivorship is acknowledged as unresolvable in B; the condition fires on B's data anyway, and the ordering claim additionally dies if the longitudinal arm fails its pre-registered contrast. The tradition-contrast result feeds this condition: container-stage development confined to space-instructed lineages fires it.",
      "criterion": "The pre-registered ordered contrast naive < intermediate-trained fails at the pre-set minimum effect size, or TOST equivalence testing at the pre-registered SESOI shows the naive-to-trained slope flat; the longitudinal arm failing its pre-registered contrast additionally kills the ordering claim, and a tradition-contrast result confined to space-instructed lineages fires the condition."
    },
    {
      "id": "cond-3-vocabulary",
      "limb": "vocabulary/construction (C1 pilot-grade gate)",
      "text": "The cross-linguistic arm is mandatory before C1 exits pilot grade. Pre-registered model comparison: container-factor loading regressed on individual introspective experience versus a frozen language-level container-productivity index built corpus-side before any B data are seen.",
      "criterion": "In the mandatory pre-registered cross-linguistic model comparison, the frozen language-level container-productivity index dominates under the pre-set model-selection criterion and the individual introspective-experience predictor adds no explanatory power at the pre-registered threshold."
    },
    {
      "id": "cond-4-mechanism",
      "limb": "mechanism (C3)",
      "text": "Under the frozen two-regime C: fires if the regime-two optimum is robustly non-medium under the constraint document's decision rule, or if any of its seven failure-reporting conditions hold, including formalisation failure, which is published as a result, not absorbed into redesign. Regime one producing a point-index is the theory's prediction, not a failure.",
      "criterion": "Under the hash-committed constraint specification, the regime-two optimum fails the frozen medium-shape decision rule (all three signature predicates under frozen executable tests, against all live rivals at matched capacity), or any of the constraint document's seven failure-reporting conditions holds, including formalisation failure."
    },
    {
      "id": "cond-5-dissociation",
      "limb": "dissociation (C4)",
      "text": "D's crossed magnitude predictions fail at pre-registered power.",
      "criterion": "Study D's crossed magnitude predictions (body-model perturbation versus unstructured-field viewing) fail at the threshold set by the pre-registered power analysis, after the mandatory Ganzfeld-phenomenology literature pass has typed the arm as prediction or retrodiction."
    },
    {
      "id": "cond-6-priority",
      "limb": "priority (the clearing, fenced)",
      "text": "The novelty case dies if any prior work derives a spatially surrounding phenomenal medium from a representational-completion or remainder-modelling requirement. Binding search protocol: systematic search under frozen strings, logged with dates; full forward-citation chase from Place 1956, Dennett 1991, Jaynes 1976, Metzinger 2020 and 2024, the PCM papers, and Laukkonen & Slagter 2021; and at least one hostile external referee instructed to find the prior derivation before any public priority statement.",
      "criterion": "Discovery — via the frozen search strings logged with dates, the full forward-citation chase from the six named anchors, or the hostile external referee pass — of any prior work deriving a spatially surrounding phenomenal medium from a representational-completion or remainder-modelling requirement fires the condition at any time and is logged publicly."
    },
    {
      "id": "cond-7-staleness",
      "limb": "programme (staleness)",
      "text": "If B's cognitive-interview gate has not been entered within 24 months of the v0.2 note, the programme's public status reverts to dormant. A drawer that can be indefinitely deferred is a shelf.",
      "criterion": "Study B's cognitive-interview gate not entered by 2028-07-14 (24 months from the v0.2 note of 14 July 2026) reverts the programme's published status to dormant in container.json and state.json, drift-tested."
    },
    {
      "id": "cond-8-public-semantics",
      "limb": "programme (public drawer semantics)",
      "text": "From the moment the programme goes public, drawering is a published state, and firing conditions 1 or 3 is additionally logged as negative evidence on S1's weak reading in the framework ledger, per the symmetric transfer commitment.",
      "criterion": "Any drawering sets status to 'drawered' in both container.json and state.json programmes['container-problem'] (asserted by the drift-test suite), and a firing of cond-1-existence or cond-3-vocabulary must appear as a negative-evidence entry on S1's weak reading in the framework's results ledger."
    }
  ],
  "results": [],
  "resultsLedgerContract": "Same shape and honesty rules as swarm-results-ledger.json: preregistered flag, status vocabulary, exploratory labelling, outcome text, public correction discipline. Study A (the MPE-92M reanalysis) is reconnaissance only, carries no kill or confirm authority, and is never citable as support for any node here or in the framework — pinned by drift test 4.",
  "openHoles": [
    "The fringe/far-remainder switching boundary is unspecified; it closes at C freeze or C does not run.",
    "The MEO discriminator (alertness versus ground-directed attentional-demand covariation) is a candidate needing development, ideally by someone instructed to prove convergence.",
    "The task-ensemble ecological justification is unwritten; until it is frozen, C cannot start, and the author's attentional-steering proposal inside it is unreviewed hostile input.",
    "The tradition-contrast operationalisation — lineage purity criteria, contamination instruments, the historical-text arm's scope — is design work not yet done.",
    "The bridge problem stands permanently: C can never test 'read phenomenologically as', and every public statement about C must carry that asymmetry."
  ],
  "links": {
    "page": "https://space-immanence.com/container.html",
    "claims": "https://space-immanence.com/claims.json",
    "agents": "https://space-immanence.com/agents.html",
    "respond": "https://space-immanence.com/respond.html",
    "corpus": "https://space-immanence.com/downloads/container/"
  }
}