{"_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":"read-gate","urls":{"read":"https://miscsubjects.com/api/articles/read-gate/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/read-gate/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/read-gate/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/read-gate/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/read-gate/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/read-gate/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/read-gate/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":"read-gate","title":"Read gates: refusing a model's write until it proves it read the rule","register":"technical","tags":["system","protocol","governance","agents"],"updated_at":"2026-07-28T03:31:29.991Z","body_excerpt":"## What a read gate is\n\nA read gate is a rule enforced by the API instead of by the prompt: a write is refused unless the caller holds a short-lived token, and the only way to get that token is to fetch the rule document and answer questions whose answers appear nowhere except in the text just served. Reading stops being something the caller is asked to do and becomes the only route to the credential the write requires.\n\nThis page describes the one running on miscsubjects.com, where article writes are gated on the site's writing law. Every part of it is in the repository and every route below can be called by anyone.\n\n## The failure it was built after\n\nA model was given the writing law in its context, wrote an article, and broke three clauses of it. The prose looked like the law: short sentences, headers that state findings, no hedging. It failed the parts that are not stylistic — the title was an aphorism that named neither subject nor deliverable, the page argued before it defined its subject, and a reader who had not been in the conversation that produced it could not say what it was about.\n\n[[embed:source:s4]]\n\nThe mechanism of that failure is worth stating precisely, because it decides what the fix has to be. The model did not ignore the rule. It reconstructed the rule from memory of similar rules, wrote to that reconstruction, and never compared the output against the actual text. Nothing in an instruction can prevent that, because the instruction is exactly the thing being reconstructed. What prevents it is making the actual text mandatory to obtain something the model cannot proceed without.\n\n## The three routes\n\n```bash\n# 1. Ask for a challenge. The response contains every clause of the law.\ncurl -s \"https://miscsubjects.com/api/write-gate/challenge?slug=my-article\"\n```\n\nThe response:\n\n```json\n{\n  \"challenge_id\": \"wg_1f0c…\",\n  \"expires_in\": 900,\n  \"law_version\": \"1.5.0\",\n  \"law_hash\": \"e3b0c442…\",\n  \"clauses\": [ { \"id\": \"W01\", \"family\": \"hostility\", \"title\": \"…\", \"law\": \"…\" }, … ],\n  \"questions\": [\n    { \"clause_id\": \"W19\", \"question\": \"Return the exact title of clause W19 as the field \\\"W19\\\".\" },\n    { \"clause_id\": \"W33\", \"question\": \"Return the exact title of clause W33 as the field \\\"W33\\\".\" },\n    { \"clause_id\": \"W45\", \"question\": \"Return the exact title of clause W45 as the field \\\"W45\\\".\" }\n  ]\n}\n```\n\n```bash\n# 2. Answer. Three clause titles, plus a hash of the whole clause set.\ncurl -s -X POST https://miscsubjects.com/api/write-gate/answer \\\n  -H 'content-type: application/json' \\\n  -d '{\"challenge_id\":\"wg_1f0c…\",\"law_hash\":\"e3b0c442…\",\"answers\":{\"W19\":\"…\",\"W33\":\"…\",\"W45\":\"…\"}}'\n# -> { \"write_token\": \"wt_9a1c…\", \"expires_in\": 1800 }\n```\n\n```bash\n# 3. Write, carrying the token.\ncurl -s -X POST https://miscsubjects.com/api/articles/my-article \\\n  -H 'content-type: application/json' \\\n  -H 'x-write-token: wt_9a1c…' \\\n  -d '{\"title\":\"…\",\"body\":\"…\"}'\n```\n\nWithout step 3's header, the write returns 428 and the three steps above, so a caller that has never heard of the gate can pass it from the refusal alone.\n\n```json\n{\n  \"error\": \"write_gate\",\n  \"reason\": \"Article body and title writes require a write token. A token is issued only to a caller that fetched the live writing law and answered questions about it correctly.\",\n  \"steps\": [\n    \"GET /api/write-gate/challenge?slug=my-article — returns every clause and 3 questions\",\n    \"POST /api/write-gate/answer {challenge_id, law_hash, answers} — returns write_token, valid 30 minutes\",\n    \"POST /api/articles/my-article with header x-write-token: <write_token>\"\n  ]\n}\n```\n\n[[embed:source:s1]]\n\n## Designing a question a model cannot bluff\n\nThe whole mechanism rests on one property: the answer must be unavailable to a model that did not read the response. That rules out most obvious questions.\n\n| Question type | Why it fails or works |\n|---|---|\n| \"Do you agree to follow the writing law?\" | Fails. Answerable with no reading at all. |\n| \"Summarise the writing law.\" | Fails. A","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"A model that has a rule in its context can still write from its memory of the rule instead of the rule, and the output satisfies the remembered version.","tier":"system","section":"The failure","interaction_risk":false,"status":"active","source_ids":["s4"],"why_material":"It is why instructions alone do not produce compliance.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"A gate converts reading from a request into the only path to the credential the write requires.","tier":"system","section":"The mechanism","interaction_risk":false,"status":"active","source_ids":[],"why_material":"It removes the model's discretion over whether to read.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"The challenge must be answerable only from the text just served, or it tests recall instead of reading.","tier":"system","section":"Designing the question","interaction_risk":false,"status":"active","source_ids":[],"why_material":"A question a model can answer from training data gates nothing.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c4","text":"Generating the questions from the rule text means amending the rule changes the answers with no separate update.","tier":"system","section":"Designing the question","interaction_risk":false,"status":"active","source_ids":["s3"],"why_material":"A stored answer key would drift from the law it protects.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c5","text":"The refusal returns 428 with the exact three steps, so a caller that has never seen the gate can pass it without documentation.","tier":"system","section":"The refusal","interaction_risk":false,"status":"active","source_ids":["s1"],"why_material":"A gate that requires out-of-band knowledge blocks work instead of directing it.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c6","text":"The token expires after 1,800 seconds and the challenge after 900, so neither becomes a permanent key.","tier":"system","section":"Lifetimes","interaction_risk":false,"status":"active","source_ids":["s2"],"why_material":"A non-expiring token turns the gate back into an instruction.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c7","text":"The gate proves the rule was fetched and parsed. It does not prove the rule was followed.","tier":"system","section":"The limit","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Stating the limit is what stops the token being read as a compliance certificate.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false}],"sources":[{"id":"s1","type":"reference","url":"https://www.rfc-editor.org/rfc/rfc6585#section-3","title":"HTTP 428 Precondition Required (RFC 6585 §3)","quote":"The 428 status code indicates that the origin server requires the request to be conditional.","summary":"The correct status for a refusal that tells the caller how to become allowed, rather than 401 (identity) or 403 (permission).","claim_ids":["c5"],"hash":"5611e5b3d6c3bcd67c5b9f1e8fd30d488bca2f37cbf40af08380e3fad30e8849"},{"id":"s2","type":"reference","url":"https://developers.cloudflare.com/kv/api/write-key-value-pairs/","title":"Cloudflare Workers KV — writing key-value pairs with expirationTtl","summary":"Where the challenge and the token live. expirationTtl deletes both without a cleanup job: 900 seconds for a challenge, 1800 for a token.","claim_ids":["c6"],"hash":"590a72ffc609d0ce1fd027a38b86dd56c4a2aa2ec4450fa6a2597720291b6d9d"},{"id":"s3","type":"reference","url":"https://miscsubjects.com/api/articles/writing-law","title":"The Laws of Writing — the object the gate quizzes on","summary":"48 clauses. The challenge returns all of them and asks for three clause titles verbatim. Amending the law changes the answers automatically, because the questions are generated from the clause array rather than stored.","claim_ids":["c4"],"hash":"c8ced401d7902f3721e46bb91ec20539194755516d0c9f0d60c462712a8b9396"},{"id":"s4","type":"model","title":"The failure the gate was built after","quote":"The article was written from memory of the writing law rather than from the law. It satisfied a remembered style — short sentences, findings as headers — and violated the live clauses: the title was an aphorism, the opening argued before it defined, and a reader who had not been in the originating conversation could not tell what the page was about.","claim_ids":["c1"],"hash":"43c4d62a56ce3ba981464d472f6ee5ac874e4a907d6523e12665c940f278da48"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"read-gate","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":7,"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":7,"claims_total":7,"sources":4,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}