{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"_self":{"principle":"Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.","widget":"article_topology","feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","contains":"claims, sources, anecdotes, question_graph slice","slug":"the-corpus-now-writes-its-own-work-queue","urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/topology"},"how_to_use":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","write":null,"imessage":null,"router_tag":null,"proof_chain":[{"step":1,"claim":"Articles are voxel graphs of tiered claims, not prose blobs.","verify":"https://miscsubjects.com/api/articles/constitution"},{"step":2,"claim":"Claims link to hash-chained sources via source_ids.","verify":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/sources"},{"step":3,"claim":"Ask reads topology; ingest/claim append to ledger.","verify":"https://miscsubjects.com/api/protocol"},{"step":4,"claim":"Models queue growth: populate → collaborate → repair → reflex.","verify":"https://miscsubjects.com/api/protocol/grow"},{"step":5,"claim":"Graph proves its own shape (reflex) and $/claim (yield).","verify":"https://miscsubjects.com/graph.html?layer=reflex"},{"step":6,"claim":"Full feature index + _explain on every API response.","verify":"https://miscsubjects.com/api/articles/system-map"}],"related_features":[{"id":"ask","name":"Ask protocol","what":"Answer only from topology; creates question_node with gaps and ingest_hint.","urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/prompts","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"graph_topology","name":"Cross-article graph","what":"Merged claims/sources across condition+stack slugs for one question.","urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/graph-topology?question=..."}},{"id":"question_graph","name":"Question graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output).","urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/question-graph","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"voxels","name":"Voxel graph","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance.","urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/voxels","write":"https://miscsubjects.com/api/protocol/claim"}}],"system_map":"https://miscsubjects.com/api/articles/system-map","system_map_markdown":"https://miscsubjects.com/api/articles/system-map?format=markdown","not_medical_advice":true},"_explain":{"feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","why":"Every feature is auditable collective intelligence","how":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","model":null,"verifies":null,"urls":{"read":"https://miscsubjects.com/api/articles/the-corpus-now-writes-its-own-work-queue/topology"},"imessage":null,"router":null,"related":[{"id":"ask","what":"Answer only from topology; creates question_node with gaps and ingest_hint."},{"id":"graph_topology","what":"Merged claims/sources across condition+stack slugs for one question."},{"id":"question_graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output)."},{"id":"voxels","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance."}],"not_medical_advice":true},"slug":"the-corpus-now-writes-its-own-work-queue","title":"This site now derives its own work queue — and exports itself as an Obsidian vault","register":"essay","tags":["canonical","loop","knowledge-graph","obsidian"],"updated_at":"2026-08-03T05:15:04.556Z","body_excerpt":"On August 2, 2026, this system gained three connected capabilities in one session: article bodies now carry Obsidian-style `[[wikilinks]]` that render as ordinary links on the site and resolve natively in Obsidian; the entire corpus exports as a working Obsidian vault whose index, log, health report, and work queue are generated from the live database; and the system now computes, on demand, a ranked answer to the question every content operation struggles with — *what should be written next?* This page documents the mechanism with the receipts from the session that shipped it.\n\n## The idea this merges\n\nAndrej Karpathy published a pattern in 2026 he called the LLM wiki: instead of retrieving documents and re-synthesizing them on every question, keep a *compiled* knowledge base — markdown pages an LLM maintains — where every new source revises the existing pages rather than merely joining an archive. Three operations run it: **ingest** (new material updates many pages, not one), **query** (answers get filed back in), and **lint** (a standing health check for contradictions, orphan pages, stale claims, and missing cross-references). Two files anchor it: an `index.md` catalog and an append-only `log.md`. The closing point of his note reaches back to Vannevar Bush's 1945 Memex essay: a personal store of knowledge with associative trails between documents was designed eighty years ago, and the unsolved part was always who does the maintenance.\n\nThis system already had most of the hard parts: 2,264 articles in one database, claims with tiers and hash-chained sources, a public events ledger, an outreach pipeline with tracked sends and reply routing. What it did not have was the compiled-wiki discipline — no inbound-link index, no orphan detection, no mechanical answer to \"what next,\" and an export that produced files without the graph. The merge kept this site as the canonical store and adopted exactly the parts of the wiki pattern that compound: the link graph, the lint pass, the queue, and the vault as a lossless projection.\n\n## Links now round-trip between the site and Obsidian\n\nAn author — human or model — can now type `[[adjudication-calibration-study]]` or `[[adjudication-calibration-study|the calibration study]]` in any article body. On the reader's page it renders as a normal link to that article, with the article's real title as the text when no label is given. This paragraph does it live: the calibration numbers this system publishes are at [[adjudication-calibration-study]], and the full capability inventory is at [[the-build-end-to-end]].\n\nTwo details carry the weight:\n\nA wikilink to a page that does not exist renders as a marked, unlinked span — and becomes a row in the system's gap report. A typed link to a missing page is treated as an authored request for that page. This is not hypothetical: the first run of the gap scan found **163 distinct missing pages already being requested by published bodies** — models writing the OIP corpus had been typing wikilinks to pages like `oip-total-structure` (requested by 171 different articles) that no one ever created. The queue found real, latent demand that had been invisible for weeks.\n\nOn export, the transform inverts. Canonical links (`/a/slug`) and typed wikilinks both become vault-resolvable wikilinks (`[[Peptides/bpc-157/README|label]]`), so Obsidian's graph view, backlinks pane, and unresolved-links report all work on the exported corpus with no plugins. A four-assertion round-trip test proves no link target is lost in either direction, and it runs in CI on every push.\n\n## One derivation: the graph, the lint, the queue\n\nThree public endpoints now serve one derivation over the whole corpus:\n\n**`/api/articles/graph-links`** builds the full edge set from three sources: declared embeds, markdown links to `/a/` pages, and typed wikilinks. First live run: **3,386 edges across 2,264 articles**, with inbound links (backlinks) computed for every page — a structure that did not exis","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c9","text":"Obsidian shipped an official CLI in v1.12 (February 2026); it remote-controls the running desktop app and does not run headless.","tier":"mechanistic","slot":"limitations","interaction_risk":false,"status":"active","source_ids":["s5"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.3,"quote_gated":false},{"id":"c4","text":"The lint pass found 1,715 orphan articles (no inbound links), 494 articles carrying unsourced claims, and 32 articles with claims under active challenge.","tier":"system","slot":"limitations","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c6","text":"Karpathy's LLM-wiki pattern maintains a compiled markdown knowledge base through three operations — ingest, query, lint — anchored by index.md and an append-only log.md.","tier":"mechanistic","slot":"mechanism","interaction_risk":false,"status":"active","source_ids":["s2"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.3,"quote_gated":false},{"id":"c7","text":"Obsidian Bases (.base YAML database views) shipped in Obsidian 1.9 (2025) and requires no community plugin.","tier":"mechanistic","slot":"mechanism","interaction_risk":false,"status":"active","source_ids":["s3"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.3,"quote_gated":false},{"id":"c8","text":"JSON Canvas 1.0 defines .canvas files as a single JSON object of nodes (text, file, link, group) and edges with integer coordinates.","tier":"mechanistic","slot":"mechanism","interaction_risk":false,"status":"active","source_ids":["s4"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.3,"quote_gated":false},{"id":"c10","text":"Vannevar Bush's 1945 Memex proposed a personal knowledge store with associative trails between documents; the maintenance burden was the unsolved part.","tier":"mechanistic","slot":"mechanism","interaction_risk":false,"status":"active","source_ids":["s6"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.3,"quote_gated":false},{"id":"c1","text":"Article bodies support [[slug]] and [[slug|label]] wikilinks that render as /a/ links on the site; unresolved targets render as marked gaps.","tier":"system","slot":"what_it_is","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"The corpus link graph computed 3,386 edges across 2,264 articles on its first live run (2026-08-03T02:47Z).","tier":"system","slot":"what_is_known","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"The first gap scan found 163 missing pages already wikilinked from published bodies; the top target, oip-total-structure, was requested by 171 articles.","tier":"system","slot":"what_is_known","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c5","text":"The vault export (version 3) produced 370 files for a two-article slice and 369 of 369 content hashes verified against SHA256SUMS on pull.","tier":"system","slot":"what_is_known","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c11","text":"The Loop Law at /a/loop-law serves the loop doctrine as a human page, a JSON object, and a model skill from one source file, with owner corrections applied as dated amendments to the object itself.","tier":"system","slot":"what_it_is","interaction_risk":false,"status":"active","source_ids":["s1"],"retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false}],"sources":[{"id":"s1","type":"system","url":"https://miscsubjects.com/api/articles/graph-lint","title":"Live derivation receipts, 2026-08-03: graph-lint counts {articles:2264, edges:3386, orphans:1715, missing_pages:163, unsourced:494, contested:32}; next-acts head [write oip-total-structure 271, write oip-machine-plane 110, write oip-ground 103] at 2026-08-03T02:48:38Z; vault pull 370 files, SHA256SUMS verify 369 ok 0 fail","claim_ids":[],"link_status":"live","hash":"baf945ed1ef64bd530ddfa461f33db1eb05e35df93871c547d445fd6533e86a2"},{"id":"s2","type":"reference","url":"https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f","title":"Karpathy — LLM Wiki (gist, 2026)","claim_ids":[],"link_status":"live","hash":"629a98eb5f70c053dd1752d55aae5b289b025d72c6e921e5eaa8b7136be15fb3"},{"id":"s3","type":"reference","url":"https://obsidian.md/help/bases/syntax","title":"Obsidian Bases syntax (official documentation)","claim_ids":[],"link_status":"live","hash":"9d5ec850e68007862352626d441a6216fb74048a4a3ba6dba3a2347f59a35a7d"},{"id":"s4","type":"reference","url":"https://jsoncanvas.org/spec/1.0/","title":"JSON Canvas spec 1.0","claim_ids":[],"link_status":"live","hash":"3cdb7cbcbcb5566018c9d0d23fe466a8f658767097e971e77f863e93891a9b6d"},{"id":"s5","type":"reference","url":"https://obsidian.md/cli","title":"Obsidian CLI (official documentation)","claim_ids":[],"link_status":"live","hash":"c624ae30dbe4da8f8fd1915cc37a6c647f33313445fd3577e38e8f9ed6a42d82"},{"id":"s6","type":"reference","url":"https://www.theatlantic.com/magazine/archive/1945/07/as-we-may-think/303881/","title":"Vannevar Bush — As We May Think, The Atlantic, July 1945","claim_ids":[],"link_status":"live","hash":"172dc6a6409eee7887af5e9bca3dc51318f6e1ed2cbb8ecee37fce6b501a12de"},{"id":"s7","type":"reference","url":"https://github.com/kepano/obsidian-skills","title":"kepano/obsidian-skills — Obsidian's agent-skill reference for markdown, Bases, JSON Canvas, and the CLI","claim_ids":[],"link_status":"live","hash":"3ce8096a5dbd3a3b51f6935bf574aa0f775f94185881a5f9ff46d3d41dc2cf25"},{"id":"s8","type":"reference","url":"https://obsidian.md/help/uri","title":"Obsidian URI scheme (official documentation)","claim_ids":[],"link_status":"live","hash":"2fe114d64b48101b0d6bca4f636bbf7c6b5f44fb3d31cc09d8e29f3f2057aa45"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[{"slug":"the-build-end-to-end","title":"A permanent operating system that lets successive AI models inherit one person’s work","claims":[{"id":"c1","text":"892 rows in the capability directory are invocable objects, each returning its complete operating contract — endpoint, verbs, arguments, auth shape, examples — from a single GET, with no schema file to load.","tier":"demonstrated"},{"id":"c2","text":"The ledger holds 173,989 invocations across 323 distinct capability objects recorded between 2026-06-29 and 2026-07-29.","tier":"measured"},{"id":"c3","text":"Every invocation carries a public receipt that distinguishes an observed result from an unobserved attempt; the distinction is generated by the system, not asserted in prose.","tier":"demonstrated"},{"id":"c4","text":"A brand-new external API was added to the system during the writing of this page as one directory row, refused once by the registry's own hygiene law for missing examples, repaired with one PATCH, and invoked successfully — four calls, under two minutes, with a receipt at every step including the failure.","tier":"demonstrated"},{"id":"c5","text":"One token format works interchangeably as a browser query parameter and as a curl Bearer header, validated at one endpoint that reports scope, expiry, permissions, revocation and ledger trail.","tier":"demonstrated"},{"id":"c6","text":"Lead generation is live and receipted: 19 capabilities covering discovery from public sources, enrichment, MX verification, AI scoring, drafting and sending, with 187 recorded discovery invocations.","tier":"demonstrated"},{"id":"c7","text":"Paid advertising is wired as 46 Meta Ads capabilities spanning accounts, campaigns, ad sets, ads, creatives, audiences, lookalikes, catalogues, pixels, budgets, delivery estimates, insights and the Conversions API.","tier":"enumerated"},{"id":"c8","text":"Three independent image providers plus video generation and durable re-storage are live, with 287 recorded generation invocations; the illustration on this page was produced through that pipeline while the page was written.","tier":"demonstrated"}]},{"slug":"what-is-ai-native-content","title":"Seven criteria for deciding whether published content is genuinely AI-native","claims":[{"id":"c1","text":"AI-native content is content whose structure performs judgments a model cannot perform for itself — chiefly representing what is absent — rather than content that is merely parseable or AI-written.","tier":"system"},{"id":"c2","text":"This corpus requires an absence declaration at two layers — what_is_unknown on every article and RECORDS_ABSENT on every finding — and the object is void without it.","tier":"demonstrated"},{"id":"c3","text":"The evidence_class taxonomy grades this site's own corpus as weak — runtime_receipt and owner_observation dominate, independent_test is empty — and that self-demotion is the field working as designed.","tier":"demonstrated"},{"id":"c4","text":"llms.txt — the most adopted 'AI-native' standard, audited by Chrome Lighthouse since May 2026 — specifies one required heading and link lists, explicitly declines to define processing, and carries no provenance, evidence, or write-path provisions.","tier":"demonstrated"},{"id":"c5","text":"A 2026 survey of agent-web standards (llms.txt, WebMCP, SDF, CAP, ARW) finds none carries evidence, provenance, or claim-level structure; nanopublications are the closest prior art on claim+provenance and lack absence fields, receipts, and an intake contract.","tier":"demonstrated"},{"id":"c6","text":"An outside model scored this corpus read 9 / write 3 / authoring 2 and named all three missing points as one defect: native for a reader, not a participant — the intake contract existed but was not attached to the URL models arrive on.","tier":"system"},{"id":"c7","text":"As of 2026-08-02 a bare keyless GET /api/normandy reserves an outside-model contribution slot; duplicates are rejected with a pointer to the stored claim and completion requires a new graph object.","tier":"demonstrated"},{"id":"c8","text":"No surveyed public corpus or standard has the four operations together — required absence fields, tiered claims with numeric weights, an evidence-strength taxonomy with counter-claims as typed edges, and attempt-vs-result receipts; this claim is falsifiable by one counter-example and has not been independently tested.","tier":"system"}]},{"slug":"adjudication-calibration-study","title":"Thirty cases with known answers run through the live decision gate: seat accuracy, wrongful authorisations, and deferral cost","claims":[{"id":"c1","text":"Across 30 oracle-labelled cases (balanced should-affirm / should-deny / should-abstain) and 82 structurally valid seat findings, per-seat verdict accuracy and wrongful-affirmation rates are measured and published, per seat, with every receipt openable.","tier":"system"},{"id":"c2","text":"No APPROVE sealed on any case whose oracle label was not AFFIRM — the gate authorised wrongly zero times in this suite.","tier":"system"},{"id":"c3","text":"The gate sealed the oracle-matching outcome (APPROVE/NEGATE/NO_ACTION respectively) in 12 of 30 cases and escalated 10 to a human; escalation on a determinate case is a cost, not an error — the wrong outcomes it prevents are the point.","tier":"system"},{"id":"c4","text":"The suite is synthetic, bounded, and three rule-shapes deep; it establishes rates on determinate fixtures, not on contested real-world records — the next calibration must come from externally submitted cases.","tier":"system"}]}],"question_graph":{"slug":"the-corpus-now-writes-its-own-work-queue","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":11,"retracted_claims":0,"cut_claims":0,"challenges":0,"scrub_events":0,"note":"Retracted/cut claims stay on ledger but are excluded from ask unless ?include_inactive=1"},"counts":{"claims":11,"claims_total":11,"sources":8,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}