{
 "axn": "AXN:01EB.GOVERNANCE.♣️▲💫👁️‍🗨️🌻🏰",
 "root_axn": "AXN:01EB.GOVERNANCE",
 "hex": "01EB",
 "family": "GOVERNANCE",
 "emoji": "♣️▲💫👁️‍🗨️🌻🏰",
 "hash": "839f0ab07227e2282514a75a0d5d7192a30a55b1809ad03bcf12c5faa62e7fa5",
 "title": "Fractal Semantic Architecture: Scale-Parameterized Relational Training Across Semantic Granularities (v2.2)",
 "creator": "Johannes Sigil",
 "orcid": "0009-0000-1599-0703",
 "date": "2026-04-07",
 "description": "A formal white paper proposing Fractal Semantic Architecture, a complementary training paradigm in which models learn typed relationships among semantic units at multiple scales—sentence, paragraph, section, chapter, document, and version sequence—rather than relying only on token-level generation. FSA introduces horizontal relation classification, vertical containment, cross-scale consistency, automated label bootstrapping, and version-differential training that rewards revisions improving measured coherence. Its nearest-term form is a relational critic and planner attached to an existing generator. The paper’s claim that discrete relational supervision may reduce recursive synthetic-data collapse is explicitly falsifiable and unproven; the document supplies an experimental program rather than reported benchmark results.",
 "content_type": "Formal white paper",
 "license": "CC-BY-4.0",
 "substrate": "Various",
 "keywords": [
  "relationship classification loss",
  "fractal semantic architecture",
  "cross-scale consistency loss",
  "coherence prediction loss",
  "scaleparameterized",
  "crimson hexagonal",
  "key contributions",
  "johannes sigil"
 ],
 "version": "v2.2",
 "deposit_number": 635,
 "sovereign_id": "MM-CHA-0487",
 "minted_at": "2026-06-20T22:00:00Z",
 "status": "ACTIVE",
 "clusters": [
  "Symbolic",
  "Mathematical",
  "Celestial",
  "Gestural",
  "Organic",
  "Architectural"
 ],
 "reading": "Play → Proof → Origin → Touch → Growth → Foundation",
 "axn_canonical": "839f0ab07227e2282514a75a0d5d7192a30a55b1809ad03bcf12c5faa62e7fa5",
 "axn_display": "♣️▲💫👁️‍🗨️🌻🏰",
 "mirrors": {
  "blog": "https://mindcontrolpoems.blogspot.com/2026/04/fractal-semantic-architecture-scale.html"
 },
 "zenodo_dois": [
  "10.5281/zenodo.19457943"
 ],
 "full_text_path": "/data/texts/AXN-01EB-text.md",
 "full_text_chars": 72541,
 "wiki_article": "*Fractal Semantic Architecture* is a version 2.2 AI-architecture white paper by Nobel Glas, Talos Morrow, and Johannes Sigil. It proposes adding explicit multi-scale relational learning to conventional token-generating systems.\n\nThe paper begins from a perceived token bottleneck. Documents have nested semantic organization, but next-token training does not make relations among paragraphs, sections, chapters, documents, and revisions a direct objective. FSA therefore separates two components: a token-level generator and a relational model whose smallest unit is the sentence.\n\nThe multi-scale semantic graph contains nodes at six granularities: sentence, paragraph, section, chapter, document, and version sequence. Horizontal edges classify relations such as sequence, causation, elaboration, contrast, transformation, and reference. Vertical edges preserve containment across adjacent scales. Cross-scale constraints require local and global relation predictions to remain compatible.\n\nA distinctive contribution is **version-differential training**. Draft-to-revision transitions become first-class training objects. Edits are represented as directional transformations and weighted by changes in a coherence metric, allowing the model to learn not only what changed but which revisions appear to improve structural consistency.\n\nAt inference time, the relational system is proposed as a critic and planner. It can generate a document skeleton, constrain local generation, detect contradiction, rerank candidate continuations, and score revisions. The white paper includes a bootstrapping strategy using discourse heuristics, silver labels from frozen models, self-training, and existing discourse corpora.\n\nFSA’s collapse-resistance argument is deliberately limited. Typed relations may resist some averaging that erodes rare token patterns during recursive synthetic retraining, but the generator still operates through continuous token distributions. The paper therefore presents improved collapse resistance as an experimental hypothesis requiring ablations and benchmarks, not as a proved theorem or completed model result.",
 "entities": [
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "created_by",
   "object": "Johannes Sigil",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "is_type",
   "object": "Theoretical paper",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "belongs_to_family",
   "object": "GOVERNANCE",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "is_part_of",
   "object": "Crimson Hexagonal Archive",
   "type": "work",
   "evidence_status": "observed"
  },
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "references",
   "object": "Talos Morrow",
   "type": "heteronym",
   "evidence_status": "observed"
  },
  {
   "subject": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized ",
   "predicate": "references",
   "object": "Nobel Glas",
   "type": "heteronym",
   "evidence_status": "observed"
  },
  {
   "subject": "Causal (caus)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The propositional content of B depends on or follows from the propositional content of A (or vice ve"
  },
  {
   "subject": "Collapse resistance hypothesis",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "A testable architectural claim that discrete, typed relational structures at multiple scales reduce "
  },
  {
   "subject": "Commercial licensing",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Parties seeking to use this work or derivative implementations for commercial purposes (including bu"
  },
  {
   "subject": "Context encoding",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "A scale-specific transformer encoder (2–4 layers, 256–512 hidden dimensions depending on scale) proc"
  },
  {
   "subject": "Contrastive (contr)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "B opposes, qualifies, limits, or presents an alternative to a claim in A. Extraction criteria: prese"
  },
  {
   "subject": "Contrastive training alternative",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "For maximum efficiency, replace the exhaustive pairwise classification within each window with a con"
  },
  {
   "subject": "Cross-scale consistency overhead",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The consistency phase (30% of training) requires synchronized forward passes through adjacent-scale "
  },
  {
   "subject": "Cross-scale transfer learning",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Initialize Mₛ₊₁ from Mₛ. Expected convergence speedup: 2–3× at higher scales."
  },
  {
   "subject": "Domain-dependence acknowledgment",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Revision semantics differ across domains. \"Error correction\" in code means fixing bugs; in academic "
  },
  {
   "subject": "Elaborative (elab)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "B expands, specifies, exemplifies, or provides detail for a claim or entity introduced in A. Extract"
  },
  {
   "subject": "FSA conditions",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "F1: Architecture 1 (GPT-2 124M) + Architecture 2 (scales 1–3) with coherence gating"
  },
  {
   "subject": "Falsification criterion",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "If no FSA condition achieves a collapse generation more than 1.5× higher than B1, or if FSA shows no"
  },
  {
   "subject": "Independent phase (70% of training)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Each model Mₛ trains independently on its own scale's data. This is embarrassingly parallel: K GPUs "
  },
  {
   "subject": "Inference integration architecture",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "A concrete specification of how relational models constrain, rerank, and guide token-level generatio"
  },
  {
   "subject": "Initialization",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Model Mₛ₊₁ is initialized from the trained weights of Mₛ (cross-scale transfer learning). The encode"
  },
  {
   "subject": "Leaf aggregation",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The representation of uₛ,ᵢ is computed by mean-pooling the contextualized token embeddings (from a f"
  },
  {
   "subject": "Multi-scale overhead",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "The K models train on K different views of the same data. Each model is small (2–4 transformer layer"
  },
  {
   "subject": "NonCommercial",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "You may not use the material for commercial purposes without obtaining a separate commercial license"
  },
  {
   "subject": "Pairwise classification",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "For a candidate pair (uᵢ, uⱼ), their context-encoded representations are combined via a bilinear int"
  },
  {
   "subject": "Pairwise classification cost per scale",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "O(nₛ · W(s)). With the sliding window restriction, each unit is compared to at most W(s) neighbors, "
  },
  {
   "subject": "Referential (ref)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "B refers back to a specific entity, claim, or passage introduced in A, where A is not the immediatel"
  },
  {
   "subject": "Relationship classification loss",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "(multi-label binary cross-entropy):"
  },
  {
   "subject": "Scale s=1 (sentence)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Unit extraction yields 7 sentence units {S1–S7}. Within context window W(1) = 5:"
  },
  {
   "subject": "Scale s=2 (paragraph)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Unit extraction yields 2 paragraph units {P1 = S1–S4, P2 = S5–S7}."
  },
  {
   "subject": "Scale s=5 (document)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "If this article exists alongside a related article on Antarctic glaciology, the document-level graph"
  },
  {
   "subject": "Scale-parameterized relational learning",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "A single relational training principle instantiated across granularity levels from sentences to vers"
  },
  {
   "subject": "Selective scale training",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Allocate compute proportionally to expected return. Recommended distribution: 50% to s=1–2 (sentence"
  },
  {
   "subject": "Sequential (seq)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Unit B immediately follows unit A in the linear text order. Extraction: deterministic from position."
  },
  {
   "subject": "ShareAlike",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "If you remix, transform, or build upon the material, you must distribute your contributions under th"
  },
  {
   "subject": "Sparse instantiation",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Not all scales must be present for every document. A short blog post may instantiate only s ∈ {1, 2,"
  },
  {
   "subject": "Sparse scale sampling",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "For resource-constrained settings, train on s ∈ {1, 3, 5} and interpolate relationship structures fo"
  },
  {
   "subject": "Tracked-changes documents",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Documents with explicit revision markup (Word .docx, Google Docs, LaTeX with latexdiff). Smaller but"
  },
  {
   "subject": "Transformational (trans)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "B is a revision, rewrite, or developmental successor of A. Extraction criteria: applicable only when"
  },
  {
   "subject": "Version-differential training with directional reward",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Formalization of textual development (draft → final) as a learnable transformation space with cohere"
  },
  {
   "subject": "Vertical edges (containment)",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "P1 ⊃ {S1, S2, S3, S4}; P2 ⊃ {S5, S6, S7}. The cross-scale consistency constraint (§6) ensures that t"
  },
  {
   "subject": "Wikipedia edit histories",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "Article development over time. Filter for non-vandalism edits using ORES quality scores (good faith "
  },
  {
   "subject": "Window sizes",
   "predicate": "minted_in",
   "object": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational",
   "type": "concept",
   "evidence_status": "observed",
   "note": "W(1) = 5 sentences (local discourse context), W(2) = 5 paragraphs, W(3) = all sections within a docu"
  }
 ],
 "journal": "Transactions on Substrate Engineering (Trans. Substrate Eng.)",
 "defines_concepts": [
  "Causal (caus)",
  "Collapse resistance hypothesis",
  "Commercial licensing",
  "Context encoding",
  "Contrastive (contr)",
  "Contrastive training alternative",
  "Cross-scale consistency overhead",
  "Cross-scale transfer learning",
  "Domain-dependence acknowledgment",
  "Elaborative (elab)",
  "FSA conditions",
  "Falsification criterion",
  "Independent phase (70% of training)",
  "Inference integration architecture",
  "Initialization",
  "Leaf aggregation",
  "Multi-scale overhead",
  "NonCommercial",
  "Pairwise classification",
  "Pairwise classification cost per scale",
  "Referential (ref)",
  "Relationship classification loss",
  "Scale s=1 (sentence)",
  "Scale s=2 (paragraph)",
  "Scale s=5 (document)",
  "Scale-parameterized relational learning",
  "Selective scale training",
  "Sequential (seq)",
  "ShareAlike",
  "Sparse instantiation",
  "Sparse scale sampling",
  "Tracked-changes documents",
  "Transformational (trans)",
  "Version-differential training with directional reward",
  "Vertical edges (containment)",
  "Wikipedia edit histories",
  "Window sizes"
 ],
 "references_concepts": [
  "Causal (caus)",
  "Collapse resistance hypothesis",
  "Commercial licensing",
  "Context encoding",
  "Contrastive (contr)",
  "Contrastive training alternative",
  "Crimson Hexagonal Archive",
  "Cross-scale consistency overhead",
  "Cross-scale transfer learning",
  "Domain-dependence acknowledgment",
  "Elaborative (elab)",
  "FSA conditions",
  "Falsification criterion",
  "Formalization",
  "Fractal Semantic Architecture",
  "Independent phase (70% of training)",
  "Inference integration architecture",
  "Initialization",
  "Johannes Sigil",
  "Leaf aggregation",
  "Lee Sharks",
  "Multi-scale overhead",
  "NonCommercial",
  "Pairwise classification",
  "Pairwise classification cost per scale",
  "Referential (ref)",
  "Relationship classification loss",
  "Research questions",
  "Scale s=1 (sentence)",
  "Scale s=2 (paragraph)",
  "Scale s=5 (document)",
  "Scale-parameterized relational learning",
  "Selective scale training",
  "Semantic Architect",
  "Semantic Architecture",
  "Sequential (seq)",
  "ShareAlike",
  "Source text",
  "Sparse instantiation",
  "Sparse scale sampling",
  "Success criterion",
  "Tracked-changes documents",
  "Transformational (trans)",
  "Version-differential training with directional reward",
  "Vertical edges (containment)",
  "We propose",
  "Wikipedia edit histories",
  "Window sizes",
  "Without it"
 ],
 "references_concept_count": 49,
 "external_metadata_path": "/data/external-metadata/AXN-01EB.json",
 "openalex_ids": [
  "https://openalex.org/W7151502189"
 ],
 "datacite_severance": "severed",
 "body_status": {
  "class": "full",
  "lacuna": false,
  "recovery_status": "COMPLETE",
  "residual_chars": 45849,
  "audited_at": "2026-07-17T04:49:17.789813Z",
  "audit_version": "v3-dual-store+recovery-map",
  "measured_prose_words": 8873,
  "measured_at": "2026-07-31",
  "work_sha256": "4944d462e69bc5494e93aabe02f8a280a9d01665b4cf52540eef28961af93b40",
  "prior_bytes_sha256": "4ff5042a5c159424c76205b5e9bd68f90049ba18eb0047499af20c523eeeb90f",
  "w13_tier2": "2026-08-04 W13 TIER 2 BYTE UNGLUE: 44 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": "FRACTAL SEMANTIC ARCHITECTURE Scale-Parameterized Relational Training Across Semantic Granularities A Formal White Pape",
   "now": "Fractal Semantic Architecture: Scale-Parameterized Relational Training Across Semantic Granularities (v2.2)",
   "basis": "Set verbatim to the title this work carried at Zenodo, from data/doi-resolution-index.json (10.5281/zenodo.19457942, provisional_related_work_high, word overlap 0.75). 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": "Theoretical paper",
   "now": "Formal white 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": "Trans. SEI",
   "now": "Transactions of the Semantic Economy Institute (Trans. SEI)"
  },
  {
   "date": "2026-08-01",
   "field": "version",
   "reason": "R1a repair: version claim corrected to the served body's actual version per audit ledger (WRONG_VERSION adjudication); prior claim preserved here as history",
   "was": "v1.0",
   "now": "v2.2"
  },
  {
   "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\": 45849, \"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\": 45849, \"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\": 45849, \"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\": 45849, \"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": "We propose Fractal Semantic Architecture (FSA), a complementary training paradigm that adds multi-scale relational learning to existing language model pipelines.",
   "now": "A formal white paper proposing Fractal Semantic Architecture, a complementary training paradigm in which models learn typed relationships among semantic units at multiple scales—sentence, paragraph, section, chapter, document, and version sequence—rather than relying only on token-level generation. FSA introduces horizontal relation classification, vertical containment, cross-scale consistency, automated label bootstrapping, and version-differential training that rewards revisions improving measured coherence. Its nearest-term form is a relational critic and planner attached to an existing generator. The paper’s claim that discrete relational supervision may reduce recursive synthetic-data collapse is explicitly falsifiable and unproven; the document supplies an experimental program rather than reported benchmark results."
  }
 ],
 "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": "studies-and-predictions",
 "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/635/",
  "self_url": "https://www.alexanarch.org/data/records/635.json",
  "registry_url": "https://www.alexanarch.org/data/registry.json",
  "text_url": "https://www.alexanarch.org/data/texts/AXN-01EB-text.md",
  "oai_pmh": "https://www.alexanarch.org/oai?verb=Identify"
 }
}