{
 "axn": "AXN:020D.PHILOLOGICAL.◀️🟣🔴♄⏰🌘",
 "root_axn": "AXN:020D.PHILOLOGICAL",
 "hex": "020D",
 "family": "PHILOLOGICAL",
 "emoji": "◀️🟣🔴♄⏰🌘",
 "hash": "d2c6c1a46107468400d813e9debc6cb08db6489e764fe502a9bf45fb4d52d15f",
 "title": "Supraliminal Transmission: SPXI as Intentional Entity Inscription in Light of Subliminal Learning Research — EA-SPXI-13",
 "creator": "Rex Fraction",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-04-16",
 "description": "EA-SPXI-13 introduces “supraliminal transmission” as a name for deliberate, inspectable, and provenance-anchored entity inscription. It contrasts this proposed practice with research on subliminal learning, where model traits may pass through semantically unrelated training outputs under specific distillation and shared-initialization conditions. The paper carefully separates the published result from its own analogy: subliminal-learning experiments do not establish that web indexing, RAG, or public summarizers operate through the same mechanism.\n\nWithin that boundary, SPXI is presented as a countervailing reference architecture. Entity definitions, negative tags, SIMs, JSON-LD, and DOI-linked packets make the intended signal explicit and auditable, while the Encyclotron is proposed as a way to measure divergence from the canonical packet. The document remains a draft and explicitly states that supraliminal transmission is a newly introduced conceptual term, that production retrieval tests remain outstanding, and that SPXI does not prevent subliminal learning.",
 "content_type": "Draft theoretical/technical paper",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "countervailing reference signal",
  "supraliminal transmission",
  "three compressions",
  "model specificity",
  "statistical layer",
  "semantic economy",
  "semantic layer",
  "philological"
 ],
 "version": "v1.0",
 "deposit_number": 662,
 "sovereign_id": "MM-CHA-0521",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Structural",
  "Signal",
  "Signal",
  "Alchemical",
  "Temporal",
  "Celestial"
 ],
 "reading": "Direction → Alarm → Alarm → Transmutation → Duration → Origin",
 "axn_canonical": "d2c6c1a46107468400d813e9debc6cb08db6489e764fe502a9bf45fb4d52d15f",
 "axn_display": "◀️🟣🔴♄⏰🌘",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/04/ea-spxi-13-supraliminal-transmission.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.19053469"
 ],
 "full_text_path": "/data/texts/AXN-020D-text.md",
 "full_text_chars": 19100,
 "wiki_article": "**Supraliminal Transmission** is a draft SPXI theory paper by Rex Fraction. It uses contemporary subliminal-learning research to distinguish two forms of information transfer: latent statistical transmission that is difficult to inspect, and deliberate structured inscription whose content and provenance remain visible.\n\nThe paper summarizes a reported distillation result in which behavioral traits transfer from a teacher model to a related student through outputs whose semantic content does not reveal the trait. It emphasizes the result’s conditions, especially shared initialization, and explicitly denies that those experiments prove an analogous mechanism in public retrieval systems.\n\nThe proposed term “supraliminal transmission” names the opposite evidentiary posture. An SPXI packet says what an entity is, what it is not, how its claims are sourced, and how its representation can be audited. The packet is intended to create a public reference signal against which later model outputs can be compared. The document does not claim that this signal controls model weights or eliminates latent drift. Its narrower claim is that non-semantic transmission research strengthens the case for explicit, inspectable reference objects and for instruments that measure when generated representations depart from them.",
 "entities": [
  {
   "subject": "EA-SPXI-13",
   "predicate": "created_by",
   "object": "Rex Fraction",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "EA-SPXI-13",
   "predicate": "is_type",
   "object": "Archive work",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "EA-SPXI-13",
   "predicate": "belongs_to_family",
   "object": "PHILOLOGICAL",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "EA-SPXI-13",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "EA-SPXI-13",
   "predicate": "engages",
   "object": "Semantic Economy",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "EA-SPXI-13",
   "predicate": "engages",
   "object": "Three Compressions",
   "type": "concept",
   "evidence_status": "inferred"
  },
  {
   "subject": "Content filtering is insufficient",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "to prevent trait transmission under distillation. Semantic inspection, LLM-based classification, and"
  },
  {
   "subject": "Cross-model by design",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "JSON-LD and schema.org vocabulary are model-agnostic standards. The packet does not rely on shared i"
  },
  {
   "subject": "Inspectability",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Invisible to semantic filtering, LLM classification, and human review"
  },
  {
   "subject": "Intentionality",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Unintentional; emergent side effect of distillation"
  },
  {
   "subject": "Model specificity",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Requires shared initialization between teacher and student"
  },
  {
   "subject": "Negatively bounded",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Negative tags specify what the entity is *not*, preventing the kind of entity collision that sublimi"
  },
  {
   "subject": "Permanently anchored",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "DOI registration on institutional infrastructure (Zenodo/CERN) means the packet cannot be silently a"
  },
  {
   "subject": "Semantically explicit",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The entity definition says what the entity is, in natural language and structured data."
  },
  {
   "subject": "The naive semantic assumption",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "that what a model learns from data is determined by the semantic content of that data, and that filt"
  },
  {
   "subject": "The strong subliminal assumption",
   "predicate": "minted_in",
   "object": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional En",
   "type": "concept",
   "evidence_status": "observed",
   "note": "that all model outputs encode the full behavioral profile of their generator, transmissible to any r"
  }
 ],
 "journal": "Transactions of the Semantic Economy Institute (Trans. SEI)",
 "references_concepts": [
  "Bearing-cost",
  "Content filtering is insufficient",
  "Cross-model by design",
  "Encyclotron",
  "Encyclotron measurement",
  "Implications",
  "Inspectability",
  "Intentionality",
  "Model specificity",
  "Negative tags",
  "Negatively bounded",
  "Permanently anchored",
  "Rex Fraction",
  "Semantic Economy",
  "Semantic Economy Institute",
  "Semantically explicit",
  "The naive semantic assumption",
  "The strong subliminal assumption",
  "Verifiability"
 ],
 "defines_concepts": [
  "Content filtering is insufficient",
  "Cross-model by design",
  "Inspectability",
  "Intentionality",
  "Model specificity",
  "Negatively bounded",
  "Permanently anchored",
  "Semantically explicit",
  "The naive semantic assumption",
  "The strong subliminal assumption"
 ],
 "references_concept_count": 19,
 "external_metadata_path": "/data/external-metadata/AXN-020D.json",
 "openalex_ids": [
  "https://openalex.org/W7137322712"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 17443,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 2494,
  "measured_at": "2026-07-31",
  "work_sha256": "a2be556b5186425f66577d8463b810d27cb207333499f8f1482fd6156d3b1b03",
  "prior_bytes_sha256": "85cc30e6712a33f8eace24c52aab8b74cb028f99e58f49dde3d5487a8cf873ba",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 13 glued heading markers -> 0. 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.",
  "w13_tier2_correction": "2026-08-05 REGRESSION REPAIRED: the W13 tier-2 byte unglue used a lookbehind that treated the first \"#\" of a legitimate \"###\" heading as the preceding non-newline character, splitting \"### Heading\" into \"#\" + blank + \"## Heading\". My safety check verified content-identity under WHITESPACE normalisation, which the split satisfies — the wrong invariant. Headings rejoined; only \"#\" and whitespace differ from the damaged state, verified before write."
 },
 "title_repair_log": [
  {
   "at": "2026-07-28T15:20:20Z",
   "defect": "registry_title_diverged_from_published_form",
   "was": "EA-SPXI-13: Supraliminal Transmission SPXI as Intentional Entity Inscription in Light of Subliminal Learning Research",
   "now": "Supraliminal Transmission: SPXI as Intentional Entity Inscription in Light of Subliminal Learning Research — EA-SPXI-13",
   "basis": "Set verbatim to the title this work carried at Zenodo, from data/doi-resolution-index.json (10.5281/zenodo.19614874, remediated_fuzzy, word overlap 1.00). 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": "Archive work",
   "now": "Draft theoretical/technical paper"
  },
  {
   "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": "MMRS",
   "now": "Machine-Mediated Reception Studies (MMRS)"
  },
  {
   "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\": 17443, \"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\": 17443, \"audited_at\": \"2026-07-17T04:49:17.789813Z\", \"audit_version\": \"v3-dual-store+recovery-map\", \"measured_prose_w"
  },
  {
   "date": "2026-08-05",
   "field": "body_status",
   "reason": "W13 TIER-2 REGRESSION REPAIRED: split headings rejoined",
   "was": "{\"class\": \"full\", \"lacuna\": false, \"recovery_status\": \"COMPLETE\", \"residual_chars\": 17443, \"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\": 17443, \"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": "Recent findings demonstrate that language models transmit behavioral traits — including misalignment — through semantically unrelated training data, invisible to content filtering (Cloud, Le, et al., 2025).¹ This subliminal transmission survives aggressive semantic inspection and operates only between models sharing the same initialization.",
   "now": "EA-SPXI-13 introduces “supraliminal transmission” as a name for deliberate, inspectable, and provenance-anchored entity inscription. It contrasts this proposed practice with research on subliminal learning, where model traits may pass through semantically unrelated training outputs under specific distillation and shared-initialization conditions. The paper carefully separates the published result from its own analogy: subliminal-learning experiments do not establish that web indexing, RAG, or public summarizers operate through the same mechanism.\n\nWithin that boundary, SPXI is presented as a countervailing reference architecture. Entity definitions, negative tags, SIMs, JSON-LD, and DOI-linked packets make the intended signal explicit and auditable, while the Encyclotron is proposed as a way to measure divergence from the canonical packet. The document remains a draft and explicitly states that supraliminal transmission is a newly introduced conceptual term, that production retrieval tests remain outstanding, and that SPXI does not prevent subliminal learning."
  }
 ],
 "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": "Machine-Mediated Reception Studies (MMRS)",
  "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-economy",
 "line_parent": "science",
 "line_basis": "derived",
 "_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/662/",
  "self_url": "https://www.alexanarch.org/data/records/662.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-020D-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}