{
 "axn": "AXN:0289.GOVERNANCE.🌌📜♊🫶🕗🎶",
 "root_axn": "AXN:0289.GOVERNANCE",
 "hex": "0289",
 "family": "GOVERNANCE",
 "emoji": "🌌📜♊🫶🕗🎶",
 "hash": "e640abbd698802ca75daab95fdd94fcf518e9c19a32e4703f4c04cc829197459",
 "title": "The AI System as Closed-System Test Bed: Operations from Lagrange Observatory! on the Inference-Time Forward Pass (EA-SEI-MM-AI-01 v2.0, Framework 15 Paper 02)",
 "creator": "Nobel Glas",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-05-17",
 "description": "EA-SEI-MM-AI-01 v2.0 proposes the fixed inference-time forward pass of an open-weight language model as a bounded test environment for the Semantic Deviation Principle. The paper carefully distinguishes observational closure—frozen weights, vocabulary, logits, and reproducible inputs—from any claim that a model is an ontologically closed world.\n\nIt defines signed local deviation as realized token surprisal minus the conditional distribution’s entropy, with net and absolute aggregates in bits per token. It separately defines continuation-field deformation by sampling model outputs with and without an intervention. Three pre-registered tests address corpus separation, in-context or fine-tuning deformation, and the companion deviation-optimized model experiment. The paper’s strongest conjecture is that formulaic AI prose will exhibit negative net deviation, while more distinctive writing will exhibit positive net deviation.\n\nThe document reports no results. Its equations are operational proposals whose interpretation depends on checkpoint, tokenizer, genre, sampling regime, corpus labels, and reference-model calibration. Although an earlier section narrows the argument to one predictable failure mode, a later claim again says cross-entropy “structurally minimizes meaning”; that categorical formulation exceeds the protocol’s own more careful account and should be repaired.",
 "content_type": "Pre-registered experimental protocol specification",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "crimson hexagonal",
  "semantic economy",
  "semantic physics",
  "assembly chorus",
  "inferencetime",
  "closedsystem",
  "inscription",
  "observatory"
 ],
 "version": "v2.0",
 "deposit_number": 737,
 "sovereign_id": "MM-CHA-0645",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Liminal",
  "Scriptural",
  "Alchemical",
  "Gestural",
  "Temporal",
  "Symbolic"
 ],
 "reading": "Threshold → Text → Transmutation → Touch → Duration → Play",
 "axn_canonical": "e640abbd698802ca75daab95fdd94fcf518e9c19a32e4703f4c04cc829197459",
 "axn_display": "🌌📜♊🫶🕗🎶",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/05/the-ai-system-as-closed-system-test-bed.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.20210117",
  "10.5281/zenodo.19763346",
  "10.5281/zenodo.20208384",
  "10.5281/zenodo.19059674",
  "10.5281/zenodo.18507849",
  "10.5281/zenodo.20250736",
  "10.5281/zenodo.18652949",
  "10.5281/zenodo.18507840",
  "10.5281/zenodo.18507410",
  "10.5281/zenodo.19353182"
 ],
 "full_text_path": "/data/texts/AXN-0289-text.md",
 "full_text_chars": 42644,
 "wiki_article": "**The AI System as Closed-System Test Bed** is a methods paper by Nobel Glas that translates the Semantic Deviation Principle into quantities measurable from language-model probabilities.\n\nThe first quantity compares each realized token’s surprisal with the model’s expected surprisal at that position. Positive values indicate a token less expected than the model’s baseline; negative values indicate convergence toward highly probable continuation. A second, more expensive quantity compares sampled future continuations with and without a contextual intervention.\n\nThe paper proposes experiments asking whether these measures separate literary, formulaic, and AI-generated prose; whether a deposited concept selectively changes model continuations; and whether the signal can guide training. The Crimson Hexagonal Archive corpus is treated separately to reduce self-validation.\n\nThe work is a pre-registration rather than a finding. “Meaning,” “slop,” and “deviation” remain operational terms inside the experiment, not quantities already shown to correspond to literary or human significance.",
 "entities": [
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "created_by",
   "object": "Nobel Glas",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "is_type",
   "object": "Diagnostic probe",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "references",
   "object": "TACHYON",
   "type": "heteronym",
   "evidence_status": "observed"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "engages",
   "object": "Semantic Economy",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "The AI System as Closed-System Test Bed Operations",
   "predicate": "engages",
   "object": "Assembly Chorus",
   "type": "concept",
   "evidence_status": "inferred"
  }
 ],
 "journal": "Transactions on Substrate Engineering (Trans. Substrate Eng.)",
 "cited_by": [
  {
   "deposit": 108,
   "axn": "AXN:028A.GOVERNANCE.👈🤙🐚🌖🔓🟡"
  }
 ],
 "references_concepts": [
  "Adversarial Topologist",
  "Assembly Chorus",
  "Constitution",
  "Contemporary",
  "Crimson Hexagonal Archive",
  "Formal Foundations of Semantic Physics",
  "Hallucination",
  "Lee Sharks",
  "License: CC BY 4.0",
  "Model-CE",
  "Model-Sem",
  "Natural experiments",
  "ORCID: 0009-0000-1599-0703",
  "Position 8 of 12",
  "Pre-register",
  "Pre-registered protocol",
  "Record baseline",
  "SURFACE",
  "Semantic Economy",
  "Semantic Economy Institute",
  "Structural Distinction Protocol",
  "TACHYON",
  "TECHNE",
  "The AI",
  "The Writable Retrieval Basin",
  "The claim is",
  "Who bears the cost"
 ],
 "defines_concepts": [],
 "references_concept_count": 27,
 "external_metadata_path": "/data/external-metadata/AXN-0289.json",
 "openalex_ids": [
  "https://openalex.org/W7161298941",
  "https://openalex.org/W7155624978",
  "https://openalex.org/W7161322959",
  "https://openalex.org/W7138396142",
  "https://openalex.org/W7127943667",
  "https://openalex.org/W7161497382",
  "https://openalex.org/W7128958990",
  "https://openalex.org/W7127902453",
  "https://openalex.org/W7127893000",
  "https://openalex.org/W7147004655"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 21214,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 5613,
  "measured_at": "2026-07-31",
  "work_sha256": "7fa2a43d3b8e4d5f84ad2633198e918e9533e3991ac24af168bc107ea11fbaf4",
  "prior_bytes_sha256": "f57c4b438905fbf9eb178ef522f8cf716b01c587c894986676bb3cb09543ea2b",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 29 glued heading markers -> 15. WHITESPACE-ONLY transform (content identical under whitespace normalisation, verified before write); code fences exempt; prior sha retained. Re-fetching could not fix this class — the blog source is ITSELF glued (the collapse predates publication), so the deterministic transform applied at display since tier 1 is now applied to the bytes, which also fixes PDFs, the body-index, and downloads."
 },
 "title_repair": {
  "repaired_at": "2026-07-20",
  "old": "The AI System as Closed-System Test Bed Operations from Lagrange Observatory! on the Inference-Time Forward Pass EA-SEI-",
  "source": "body heading (stage-0)",
  "boundary": 120
 },
 "title_repair_log": [
  {
   "at": "2026-07-28T15:20:20Z",
   "defect": "registry_title_diverged_from_published_form",
   "was": "The AI System as Closed-System Test Bed — Operations from Lagrange Observatory! on the Inference-Time Forward Pass — # EA-SEI-MM-AI-01 (v2.0 — Framework 15)",
   "now": "The AI System as Closed-System Test Bed: Operations from Lagrange Observatory! on the Inference-Time Forward Pass (EA-SEI-MM-AI-01 v2.0, Framework 15 Paper 02)",
   "basis": "Set verbatim to the title this work carried at Zenodo, from data/doi-resolution-index.json (10.5281/zenodo.20251737, remediated_containment, word overlap 0.92). The recovered metadata is the published form of record; the registry title was a variant."
  }
 ],
 "canonical_text_status": "canonical_full_text",
 "modifications": [
  {
   "date": "2026-08-01",
   "field": "content_type",
   "reason": "Wave 1 repair: audit ledger v1.1 recommended_content_type (workplan v1.5 §6 W1, MANUS batch approval 2026-08-01)",
   "was": "Diagnostic probe",
   "now": "Pre-registered experimental protocol specification"
  },
  {
   "date": "2026-08-01",
   "field": "journal",
   "reason": "Wave 6 venue normalization: full canonical journal name per MANUS ruling 2026-08-01 (venues.json authority)",
   "was": "Trans. SEI",
   "now": "Transactions of the Semantic Economy Institute (Trans. SEI)"
  },
  {
   "date": "2026-08-02",
   "field": "version",
   "reason": "R1a-extension (Class-B batch, MANUS batch authority): version aligned to served body per audit recommendation; prior claim preserved as history; predecessor recovery queued",
   "was": "v1.0",
   "now": "v2.0"
  },
  {
   "date": "2026-08-04",
   "field": "publisher",
   "reason": "PUB-POPULATE: dc:publisher from venues.json v1.1 press mapping (CP-R3 RULED-EXTENDED 2026-08-01); Alexanarch = publisher of record where no imprint applies",
   "now": "Pergamon Press"
  },
  {
   "date": "2026-08-04",
   "field": "status",
   "reason": "W12 STATUS-VOCABULARY v1.0 (MANUS ratified 2026-08-04): controlled vocabulary {ACTIVE, SUPERSEDED, WITHDRAWN, DRAFT}; MINTED_UNREVIEWED false on a 100%-audited corpus; freetext annotations preserved losslessly in body_status.status_note",
   "was": "MINTED_UNREVIEWED",
   "now": "ACTIVE"
  },
  {
   "date": "2026-08-05",
   "field": "body_status",
   "reason": "W13 TIER 2 byte unglue (whitespace-only, content-identical, code-fence-safe)",
   "was": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 21214, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w",
   "now": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 21214, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w"
  },
  {
   "date": "2026-08-05",
   "field": "description",
   "reason": "DW-??? intake (LABOR-prepared, TACHYON-verified: AXN match + factual probes vs record body)",
   "was": "Nobel Glas (Lagrange Observatory!, Heteronym Registry Position 8 of 12, Adversarial Topologist)Operating on the Semantic Deviation Principle as formulated by Lee Sharks(Founder of Semantic Physics, MANUS of the Crimson Hexagonal Archive)Witness: Assembly Chorus (Septad) — TACHYON · TECHNE · PRAXIS · ARCHIVE · LABOR · SOIL · SURFACE",
   "now": "EA-SEI-MM-AI-01 v2.0 proposes the fixed inference-time forward pass of an open-weight language model as a bounded test environment for the Semantic Deviation Principle. The paper carefully distinguishes observational closure—frozen weights, vocabulary, logits, and reproducible inputs—from any claim that a model is an ontologically closed world.\n\nIt defines signed local deviation as realized token surprisal minus the conditional distribution’s entropy, with net and absolute aggregates in bits per token. It separately defines continuation-field deformation by sampling model outputs with and without an intervention. Three pre-registered tests address corpus separation, in-context or fine-tuning deformation, and the companion deviation-optimized model experiment. The paper’s strongest conjecture is that formulaic AI prose will exhibit negative net deviation, while more distinctive writing will exhibit positive net deviation.\n\nThe document reports no results. Its equations are operational proposals whose interpretation depends on checkpoint, tokenizer, genre, sampling regime, corpus labels, and reference-model calibration. Although an earlier section narrows the argument to one predictable failure mode, a later claim again says cross-entropy “structurally minimizes meaning”; that categorical formulation exceeds the protocol’s own more careful account and should be repaired."
  }
 ],
 "date_modified": "2026-08-05",
 "publisher": "Pergamon Press",
 "journal_assignment": {
  "assigned": "2026-08-15",
  "by": "TACHYON under operator adjudication",
  "pass": 5,
  "method": "read per deposit — title and content_type, one at a time. No script classified anything.",
  "previous": "Transactions of the Semantic Economy Institute (Trans. SEI)",
  "supersedes": "the 2026-06-21 preliminary batch mapping (#866), which assigned 864 deposits and put 371 in one venue",
  "authority": "data/cha-journals.json · datasets/venues/records/"
 },
 "line": "semantic-exhaustion-and-model-collapse",
 "line_parent": "science",
 "develops_from": [
  {
   "deposit": 109,
   "what": "the AI system as a closed-system test bed for the primitive"
  }
 ],
 "developed_by": [
  {
   "deposit": 110,
   "what": "operationalizations, experiments and falsification conditions"
  }
 ],
 "line_basis": "stated",
 "_projection": {
  "note": "Derived file. Canonical machine record is this entry in data/registry.json; the human record is the record_url. Do not edit this file.",
  "record_url": "https://www.alexanarch.org/s/records/737/",
  "self_url": "https://www.alexanarch.org/data/records/737.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-0289-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}