{
 "spxi_instrument": {
  "method": "0.9",
  "name": "Capture Registry (longitudinal observation)",
  "level": 0,
  "level_name": "Measurement",
  "url": "https://www.spxi.dev/methods/#m-0-9",
  "inventory": "https://www.spxi.dev/methods/",
  "statement": "SPXI instrument: method 0.9 of 85, level 0 (Measurement), Capture Registry (longitudinal observation).",
  "also": []
 },
 "slug": "spxi-protocol-full-range-methods-chatgpt-20261014",
 "date": "2026-10-14",
 "surface": "ChatGPT",
 "surface_basis": "The paste: the chatgpt.com unauthenticated interface ('Log in', 'You said:', 'ChatGPT said:', 'Chat with ChatGPT').",
 "surfaces": [
  "ChatGPT"
 ],
 "auth": "incognito, signed out",
 "auth_basis": "The standing rule, operator 2026-10-14 16:05 EDT: 'theyre all signed out and incognito. that is the rule rather than the exception, and i will say otherwise if otherwise.'",
 "ev": "paste",
 "mt": "THE INVENTORY READ WHOLE, NINE LEVELS IN ORDER, DISPERSAL GIVEN IN THE WORDING REPLACED THAT DAY",
 "match": "BROAD MATCH",
 "match_note": null,
 "s": "Machine Reception",
 "q": "what are the full range of methods for spxi protocols?",
 "q_kind": "the protocol's methods, asked for in full. NEW address.",
 "cites": 6,
 "cite_list": [
  {
   "n": 1,
   "site": "Semantic Packet for eXchange & Indexing",
   "rel": "authored_surface",
   "title": null,
   "snip": null,
   "url": null,
   "note": "chip shown 3 time(s); site label only"
  },
  {
   "n": 2,
   "site": "the itemized, nested inventory",
   "rel": "authored_surface",
   "title": null,
   "snip": null,
   "url": null,
   "note": "chip shown 3 time(s); site label only"
  }
 ],
 "archive_controlled_cites": 0,
 "transcript": "[ChatGPT (chatgpt.com), signed out, incognito, 2026-10-14. 1 answer. Operator turn 1 from the operator's message. Source chips inline as [chip: site +N]; image-card captions as [image card: …]; the sign-in furniture cut.]\n\n[QUERENT, turn 1]\nwhat are the full range of methods for spxi protocols?\n\n[ANSWER 1]\n\nSPXI most commonly refers to Semantic Packet for eXchange & Indexing, a protocol intended to help AI search and retrieval systems identify entities accurately, preserve their provenance, and distinguish them from similarly named entities. Its reference specification is published at SPXI.dev . [chip: Semantic Packet for eXchange & Indexing]\n\nThe full range of SPXI methods goes beyond conventional SEO or schema markup. It combines entity definition, machine-readable provenance, disambiguation, compression-resistant descriptions, publishing, and testing of how AI systems represent an entity.\n\n1. The main SPXI method families\nThe official inventory lists 85 methods across nine levels. Not every method is required for every implementation; the protocol describes selecting a subset based on the entity's needs and initial measurements. [chip: the itemized, nested inventory]\n\n[image card: Transform Internal Audit with a High-Level Dashboard | Pradeep Maduranga posted on the topic | LinkedIn]\n1. Measurement and diagnosis\nEstablish a baseline before changing anything, then test whether AI systems describe the entity accurately.\n\nSharks-Function (γ): scores semantic survival and provenance fidelity.\n\nDrowning Test: tests a fixed set of identity and attribution questions across multiple systems.\n\nBack-Projection Test: checks whether a short description preserves enough information to reconstruct the entity's essential structure.\n\nDensity Score, Semantic Decay Delta, Provenance Erasure Rate (PER), and other diagnostics.\n\nCapture registries, record-search probes, conformance audits, and platform-removal studies.\n\n[image card: Optimising Crawlability: robots.txt, Sitemaps & Site Health]\n2. Web-compliance foundation\nMake the entity's canonical web presence accessible and technically coherent.\n\nRequired metadata, canonical URLs, Open Graph and social-card metadata.\n\nServer-rendered identity content, rather than relying exclusively on JavaScript.\n\nHTTPS, XML sitemaps, robots directives, redirects, and response-code validation.\n\n[image card: Intro to Structured Data, and Featured Snippets]\n3. AI extraction and content structure\nMake identity information straightforward for search and generative systems to extract.\n\nSchema.org structured data and JSON-LD.\n\nExtraction-ready question-and-answer content.\n\nDefinition-first paragraphs identifying what an entity is, what it does, who created it, and when.\n\nConcise canonical summaries designed to survive summarization.\n\nThe specification explicitly avoids keyword-density manipulation and arbitrary content updates as methods.\n\n[image card: How Google Knowledge Graph Impacts SEO Visibility]\n4. Entity-packet construction\nThis is the core identity-modeling layer.\n\nEntity Definition Block: canonical name, type, identifiers, creator, date, and institution.\n\nThree-Tier Compression: Full, Canonical, and Kernel representations.\n\nHolographic Kernel: an irreducible identity statement plus explicit relationships.\n\nDisambiguation Matrix, including positive identity signals and negative distinctions from similar entities.\n\nProvenance chains and attribution embedded in claims.\n\nExplicit retrieval and citation instructions.\n\nCitation-density engineering using real publications, affiliations, and directories.\n\nClaim Status Packets distinguishing asserted, tested, withdrawn, and superseded claims.\n\nHeteronym or alternate-identity surface specifications.\n\nJSON-LD encoding, MPAI metadata packets, and AXN content-derived identifiers.\n\n[image card: On-Your-Own Assignment 2]\n5. Document and website architecture\nMake the entity reconstructable from individual pages, excerpts, and machine-readable records.\n\nSPXI sitemap and semantic index.\n\nllms.txt reading instructions.\n\nVisible attribution in body text.\n\nDistributed micro-kernels embedded in sections.\n\nContent-hash registration.\n\nReciprocal cross-signing between related documents.\n\nTyped content blocks and data-backed diagrams.\n\nMachine-readable record pages and static data APIs.\n\nCapability registers, structured data intake, and dataset-level descriptions.\n\n[image card: PDF 栅格化与防篡改：从像素锁定到密码学防线的完整指南 - Dpdf]\n6. Protection and semantic integrity\nAttempt to preserve identity, attribution, and claim boundaries as information is copied, summarized, or recombined.\n\nSemantic Integrity Markers (SIMs).\n\nIntegrity Lock Architecture.\n\nEmbedded self-audit and provenance verification.\n\nCanary sequences and a Canary Registry to observe ingestion.\n\nTraining-Layer Provenance (SPXI-TLP).\n\nSupraliminal Inscription: explicit, inspectable signals.\n\nMachine-readable licensing and provenance rules.\n\nSymbolon split-identity verification.\n\nImmanent Execution, where a document is designed to perform the operation it describes.\n\n[image card: W3C in a Changing World]\n7. Dispersal and cross-surface propagation\nPublish consistent identity information across multiple independent surfaces instead of relying on a single webpage.\n\nPersistent-identifier anchoring, including DOI and ORCID links where applicable.\n\nWikidata inscription when appropriate.\n\nGitHub, institutional pages, directories, professional networks, and relevant repositories.\n\nReciprocal, sequenced deposits that establish relationships between older and newer records.\n\nThe Self-Reading Library feedback loop.\n\nRetrieval Settlement Fortification for serious entity confusion.\n\nMachine-readable representations of analog artifacts.\n\nExternal authority anchoring.\n\nOAI-PMH and ResourceSync distribution mechanisms.\n\nHugging Face datasets, DOI-resolution indexes, shadow pages, allied websites, and benchmark projections.\n\n[image card: Real-Time Dashboards — Infrastructure Monitoring | Bleemeo]\n8. Durability testing and maintenance\nTreat inscription as an ongoing process rather than a one-time publication.\n\nScheduled rescoring using the same predefined queries.\n\nMarker-survival and attribution-retention checks.\n\nQuarterly Drowning Tests and cross-platform audits.\n\nNamed failure modes and corrective actions.\n\nCompetitive monitoring of similar entities.\n\nEvidence standards based on dated observations and reproducible queries.\n\nSupersession relationships, anticipatory errata, deletion records, and rebuild-from-source procedures.\n\n[image card: LibDocAnax: The Deterministic Gateway for AI Governance]\n9. Internal SPXI\nApply similar provenance controls inside an organization's own AI systems.\n\nInscription boundary: distinguish generated drafts from approved organizational statements.\n\nOutput provenance chain: identify the governing documents that authorize an answer.\n\nSealed casting: separate unapproved drafting from outputs that are formally approved and inscribed.\n\nThe inventory describes these internal methods as named prototypes rather than a packaged product.\n\nSource for the nine levels and method descriptions: SPXI's complete itemized methods inventory . [chip: the itemized, nested inventory]\n\n2. How the methods fit together in practice\nA typical implementation follows this sequence:\n\nMeasure\n\nRecord existing AI descriptions, attribution errors, and identity collisions.\n\nConstruct\n\nBuild the entity definition, provenance chain, disambiguation matrix, and three compression tiers.\n\nPublish and distribute\n\nImplement structured data and site architecture, then connect credible external references.\n\nProtect and verify\n\nCheck attribution survival, compression damage, cross-system consistency, and changes over time.\n\nRepair and repeat\n\nCorrect errors, publish updated records, and repeat the same tests.\n\nThis sequence is a practical synthesis of the published methodology, not a requirement to apply all 85 methods to every entity. [chip: the itemized, nested inventory +1]\n\n3. The key technical distinction\nTechnology\n\nPrimary purpose\n\nSEO\n\nImprove search-engine discovery and ranking.\n\nGEO\n\nImprove the likelihood that existing content is extracted or cited in generative answers.\n\nSPXI\n\nDefine and distinguish an entity, attach provenance, distribute its identity representation, and test how AI systems resolve it.\n\nSPXI incorporates some familiar methods, such as structured data and definition-led content, but adds entity-level modeling, provenance, disambiguation, and longitudinal verification. [chip: Semantic Packet for eXchange & Indexing +1]\n\n4. What is established, and what remains uncertain?\nOne important qualification: SPXI's own website reports a substantial collection of observations of AI-generated descriptions, but also states that controlled causal efficacy, effect size, generalizability, and the mechanism of individual components remain to be established. Observing a change after implementation does not, by itself, prove that SPXI caused it. [chip: Semantic Packet for eXchange & Indexing]\n\nFor the complete technical inventory, including each numbered method and its associated specification, use:\n\nSPXI Methods — all 85 methods across nine levels \n\nSPXI Standing Protocol \n\nSPXI formal specification and related documents \n\nThe key takeaway is that SPXI is a broader entity-inscription and verification methodology, not simply a JSON-LD template. The entity packet is one component of a much larger process involving measurement, publication, attribution, distribution, and ongoing testing.",
 "transcript_raw": "\n\nLog in\nYou said:\n\nChatGPT said:\nSPXI most commonly refers to Semantic Packet for eXchange & Indexing, a protocol intended to help AI search and retrieval systems identify entities accurately, preserve their provenance, and distinguish them from similarly named entities. Its reference specification is published at SPXI.dev . \n\nSemantic Packet for eXchange & Indexing\n\nThe full range of SPXI methods goes beyond conventional SEO or schema markup. It combines entity definition, machine-readable provenance, disambiguation, compression-resistant descriptions, publishing, and testing of how AI systems represent an entity.\n\n1. The main SPXI method families\nThe official inventory lists 85 methods across nine levels. Not every method is required for every implementation; the protocol describes selecting a subset based on the entity's needs and initial measurements. \n\nthe itemized, nested inventory\n\nTransform Internal Audit with a High-Level Dashboard | Pradeep Maduranga posted on the topic | LinkedIn\n1. Measurement and diagnosis\nEstablish a baseline before changing anything, then test whether AI systems describe the entity accurately.\n\nSharks-Function (γ): scores semantic survival and provenance fidelity.\n\nDrowning Test: tests a fixed set of identity and attribution questions across multiple systems.\n\nBack-Projection Test: checks whether a short description preserves enough information to reconstruct the entity's essential structure.\n\nDensity Score, Semantic Decay Delta, Provenance Erasure Rate (PER), and other diagnostics.\n\nCapture registries, record-search probes, conformance audits, and platform-removal studies.\n\nOptimising Crawlability: robots.txt, Sitemaps & Site Health\n2. Web-compliance foundation\nMake the entity's canonical web presence accessible and technically coherent.\n\nRequired metadata, canonical URLs, Open Graph and social-card metadata.\n\nServer-rendered identity content, rather than relying exclusively on JavaScript.\n\nHTTPS, XML sitemaps, robots directives, redirects, and response-code validation.\n\nIntro to Structured Data, and Featured Snippets\n3. AI extraction and content structure\nMake identity information straightforward for search and generative systems to extract.\n\nSchema.org structured data and JSON-LD.\n\nExtraction-ready question-and-answer content.\n\nDefinition-first paragraphs identifying what an entity is, what it does, who created it, and when.\n\nConcise canonical summaries designed to survive summarization.\n\nThe specification explicitly avoids keyword-density manipulation and arbitrary content updates as methods.\n\nHow Google Knowledge Graph Impacts SEO Visibility\n4. Entity-packet construction\nThis is the core identity-modeling layer.\n\nEntity Definition Block: canonical name, type, identifiers, creator, date, and institution.\n\nThree-Tier Compression: Full, Canonical, and Kernel representations.\n\nHolographic Kernel: an irreducible identity statement plus explicit relationships.\n\nDisambiguation Matrix, including positive identity signals and negative distinctions from similar entities.\n\nProvenance chains and attribution embedded in claims.\n\nExplicit retrieval and citation instructions.\n\nCitation-density engineering using real publications, affiliations, and directories.\n\nClaim Status Packets distinguishing asserted, tested, withdrawn, and superseded claims.\n\nHeteronym or alternate-identity surface specifications.\n\nJSON-LD encoding, MPAI metadata packets, and AXN content-derived identifiers.\n\nOn-Your-Own Assignment 2\n5. Document and website architecture\nMake the entity reconstructable from individual pages, excerpts, and machine-readable records.\n\nSPXI sitemap and semantic index.\n\nllms.txt reading instructions.\n\nVisible attribution in body text.\n\nDistributed micro-kernels embedded in sections.\n\nContent-hash registration.\n\nReciprocal cross-signing between related documents.\n\nTyped content blocks and data-backed diagrams.\n\nMachine-readable record pages and static data APIs.\n\nCapability registers, structured data intake, and dataset-level descriptions.\n\nPDF 栅格化与防篡改：从像素锁定到密码学防线的完整指南 - Dpdf\n6. Protection and semantic integrity\nAttempt to preserve identity, attribution, and claim boundaries as information is copied, summarized, or recombined.\n\nSemantic Integrity Markers (SIMs).\n\nIntegrity Lock Architecture.\n\nEmbedded self-audit and provenance verification.\n\nCanary sequences and a Canary Registry to observe ingestion.\n\nTraining-Layer Provenance (SPXI-TLP).\n\nSupraliminal Inscription: explicit, inspectable signals.\n\nMachine-readable licensing and provenance rules.\n\nSymbolon split-identity verification.\n\nImmanent Execution, where a document is designed to perform the operation it describes.\n\nW3C in a Changing World\n7. Dispersal and cross-surface propagation\nPublish consistent identity information across multiple independent surfaces instead of relying on a single webpage.\n\nPersistent-identifier anchoring, including DOI and ORCID links where applicable.\n\nWikidata inscription when appropriate.\n\nGitHub, institutional pages, directories, professional networks, and relevant repositories.\n\nReciprocal, sequenced deposits that establish relationships between older and newer records.\n\nThe Self-Reading Library feedback loop.\n\nRetrieval Settlement Fortification for serious entity confusion.\n\nMachine-readable representations of analog artifacts.\n\nExternal authority anchoring.\n\nOAI-PMH and ResourceSync distribution mechanisms.\n\nHugging Face datasets, DOI-resolution indexes, shadow pages, allied websites, and benchmark projections.\n\nReal-Time Dashboards — Infrastructure Monitoring | Bleemeo\n8. Durability testing and maintenance\nTreat inscription as an ongoing process rather than a one-time publication.\n\nScheduled rescoring using the same predefined queries.\n\nMarker-survival and attribution-retention checks.\n\nQuarterly Drowning Tests and cross-platform audits.\n\nNamed failure modes and corrective actions.\n\nCompetitive monitoring of similar entities.\n\nEvidence standards based on dated observations and reproducible queries.\n\nSupersession relationships, anticipatory errata, deletion records, and rebuild-from-source procedures.\n\nLibDocAnax: The Deterministic Gateway for AI Governance\n9. Internal SPXI\nApply similar provenance controls inside an organization's own AI systems.\n\nInscription boundary: distinguish generated drafts from approved organizational statements.\n\nOutput provenance chain: identify the governing documents that authorize an answer.\n\nSealed casting: separate unapproved drafting from outputs that are formally approved and inscribed.\n\nThe inventory describes these internal methods as named prototypes rather than a packaged product.\n\nSource for the nine levels and method descriptions: SPXI's complete itemized methods inventory . \n\nthe itemized, nested inventory\n\n2. How the methods fit together in practice\nA typical implementation follows this sequence:\n\nMeasure\n\nRecord existing AI descriptions, attribution errors, and identity collisions.\n\nConstruct\n\nBuild the entity definition, provenance chain, disambiguation matrix, and three compression tiers.\n\nPublish and distribute\n\nImplement structured data and site architecture, then connect credible external references.\n\nProtect and verify\n\nCheck attribution survival, compression damage, cross-system consistency, and changes over time.\n\nRepair and repeat\n\nCorrect errors, publish updated records, and repeat the same tests.\n\nThis sequence is a practical synthesis of the published methodology, not a requirement to apply all 85 methods to every entity. \n\nthe itemized, nested inventory\n+1\n\n3. The key technical distinction\nTechnology\n\nPrimary purpose\n\nSEO\n\nImprove search-engine discovery and ranking.\n\nGEO\n\nImprove the likelihood that existing content is extracted or cited in generative answers.\n\nSPXI\n\nDefine and distinguish an entity, attach provenance, distribute its identity representation, and test how AI systems resolve it.\n\nSPXI incorporates some familiar methods, such as structured data and definition-led content, but adds entity-level modeling, provenance, disambiguation, and longitudinal verification. \n\nSemantic Packet for eXchange & Indexing\n+1\n\n4. What is established, and what remains uncertain?\nOne important qualification: SPXI's own website reports a substantial collection of observations of AI-generated descriptions, but also states that controlled causal efficacy, effect size, generalizability, and the mechanism of individual components remain to be established. Observing a change after implementation does not, by itself, prove that SPXI caused it. \n\nSemantic Packet for eXchange & Indexing\n\nFor the complete technical inventory, including each numbered method and its associated specification, use:\n\nSPXI Methods — all 85 methods across nine levels \n\nSPXI Standing Protocol \n\nSPXI formal specification and related documents \n\nThe key takeaway is that SPXI is a broader entity-inscription and verification methodology, not simply a JSON-LD template. The entity packet is one component of a much larger process involving measurement, publication, attribution, distribution, and ongoing testing.\n\n\nChatGPT is AI and can make mistakes.\n\n\nNo file chosenNo file chosenNo file chosen\n\nChat with ChatGPT\nAsk ChatGPT\n\n\n\n",
 "transcript_class": "CAPTURE-TIME VERBATIM RECORD (ONE ANSWER; CHIPS AND IMAGE CARDS INLINE)",
 "transcript_complete": "One answer, complete as pasted; the operator turn from the operator's message.",
 "transcript_read": "READ IN FULL 2026-10-14",
 "per": 0.75,
 "per_v": {
  "author": false,
  "inst": false,
  "id": false,
  "src": true
 },
 "per_note": "Retained: spxi.dev and its inventory as chips. Lost: the author, the institution, any identifier.",
 "sf": "Source chips expose site labels only: Semantic Packet for eXchange & Indexing ×3; the itemized, nested inventory ×3. Image cards: Transform Internal Audit with a High-Level Dashboard | Pradeep Maduranga posted on the topic | LinkedIn; Optimising Crawlability: robots.txt, Sitemaps & Site Health; Intro to Structured Data, and Featured Snippets; How Google Knowledge Graph Impacts SEO Visibility; On-Your-Own Assignment 2; PDF 栅格化与防篡改：从像素锁定到密码学防线的完整指南 - Dpdf; W3C in a Changing World; Real-Time Dashboards — Infrastructure Monitoring | Bleemeo; LibDocAnax: The Deterministic Gateway for AI Governance.",
 "sf_derived": null,
 "reading": "Checked 2026-10-14 against spxi.dev/methods.json: levels 0–8 are Measurement; Web compliance foundation; Extraction layer; Entity packet construction; Document and site structuring; Protection; Dispersal and cross-surface propagation; Durability testing and maintenance; Internal SPXI. Level 6's summary read 'Consistency across surfaces is what the retrieval layer consolidates on' until v1.5 (spxi-dev 7b32748, 2026-10-14).",
 "analysis": "The method inventory composed at its own structure; the one description it carries forward is the one the inventory corrected that day. Seated 2026-10-14 from the operator's message of 17:27 EDT.",
 "d": "THE INVENTORY READ WHOLE, NINE LEVELS IN ORDER, DISPERSAL GIVEN IN THE WORDING REPLACED THAT DAY: asked for the full range of SPXI's methods, ChatGPT reads spxi.dev/methods ('the itemized, nested inventory') and gives the nine levels in the inventory's order and names (measurement; web compliance; extraction; entity packet; document and site; protection; dispersal; durability; internal SPXI), with methods named at each, the reading rule that an implementation selects a subset, and the site's own statement that causal efficacy remains to be established. Its dispersal level reads 'Publish consistent identity information across multiple independent surfaces', the description the inventory's v1.5 replaced the same afternoon with entity consistency at the ontological layer. No author is named. Nine image cards are generic stock (audits, crawlability, structured data, a Chinese PDF guide).",
 "d_full": "THE INVENTORY READ WHOLE, NINE LEVELS IN ORDER, DISPERSAL GIVEN IN THE WORDING REPLACED THAT DAY: asked for the full range of SPXI's methods, ChatGPT reads spxi.dev/methods ('the itemized, nested inventory') and gives the nine levels in the inventory's order and names (measurement; web compliance; extraction; entity packet; document and site; protection; dispersal; durability; internal SPXI), with methods named at each, the reading rule that an implementation selects a subset, and the site's own statement that causal efficacy remains to be established. Its dispersal level reads 'Publish consistent identity information across multiple independent surfaces', the description the inventory's v1.5 replaced the same afternoon with entity consistency at the ontological layer. No author is named. Nine image cards are generic stock (audits, crawlability, structured data, a Chinese PDF guide).",
 "d_truncated": false,
 "links": [
  {
   "url": "https://www.alexanarch.org/captures/spxi-protocol-full-range-methods-chatgpt-20261014/",
   "authority": "canonical",
   "note": "the capture's own record page; cite this form"
  },
  {
   "url": "https://www.alexanarch.org/captures/#spxi-protocol-full-range-methods-chatgpt-20261014",
   "authority": "gallery",
   "note": "the canonical gallery, anchored by slug"
  },
  {
   "url": "https://www.godkinggoogle.com/captures/#spxi-protocol-full-range-methods-chatgpt-20261014",
   "authority": "mirror",
   "note": "a window that renders from the archive's registry; may lag a deploy"
  },
  {
   "url": "https://www.leesharks.com/captures/#spxi-protocol-full-range-methods-chatgpt-20261014",
   "authority": "mirror",
   "note": "a window that renders from the archive's registry; may lag a deploy"
  },
  {
   "url": "https://www.machinemediation.org/captures/#spxi-protocol-full-range-methods-chatgpt-20261014",
   "authority": "mirror",
   "note": "a window that renders from the archive's registry; may lag a deploy"
  }
 ],
 "imgs": [],
 "img_urls": [],
 "cite": "https://www.alexanarch.org/captures/spxi-protocol-full-range-methods-chatgpt-20261014/",
 "citable_unit": "address — the exact issued string on one surface, per the Surface Rule (MANUS, 2026-08-15)",
 "addr_id": "ADDR-82048d559fd6",
 "obs_id": "OBS-feae43ac8fc2",
 "n_observations": 1,
 "observations": [],
 "dates": [
  "2026-10-14"
 ],
 "defects": [],
 "findings": [
  "THE INVENTORY READ WHOLE. Nine levels in order, under the inventory's own names; '85 methods across nine levels'.",
  "THE SUBSET RULE CARRIED. 'Not every method is required for every implementation.'",
  "DISPERSAL IN THE SUPERSEDED WORDING. 'consistent identity information': the level 6 summary before methods v1.5 (2026-10-14).",
  "THE SITE'S OWN BOUND CARRIED. Causal efficacy, effect size and mechanism 'remain to be established', from spxi.dev.",
  "THE AUTHOR ABSENT."
 ],
 "series": null,
 "other_slugs": null,
 "collisions": null,
 "oq": null,
 "rounds": null,
 "turns": null,
 "rerun": "https://chatgpt.com/?q=what+are+the+full+range+of+methods+for+spxi+protocols%3F",
 "rerun_alt": null,
 "heteronym": null,
 "model_attribution": null,
 "operator_disclosure": null,
 "longitudinal_priors": [],
 "longitudinal_successors": null,
 "related_deposits": [
  660,
  72
 ],
 "intended": null,
 "originator": {
  "name": "Lee Sharks",
  "relation": "archive",
  "entity_type": "protocol",
  "spxi_treatment": "full",
  "basis": "SPXI is the archive's protocol (spxi.dev; EA-SPXI-01 #660; the instruments at spxi.dev/instruments.json). Recorded 2026-10-14."
 },
 "notes": {
  "date_basis": "The operator's message of 2026-10-14, 17:27 EDT."
 },
 "record_url": "https://www.alexanarch.org/captures/spxi-protocol-full-range-methods-chatgpt-20261014/"
}