{"_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":"adjudication-medical-prior-auth","urls":{"read":"https://miscsubjects.com/api/articles/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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/adjudication-medical-prior-auth/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":"adjudication-medical-prior-auth","title":"Two weeks of therapy against a six-week criterion: a prior-authorization record adjudicated under the Decision Constitution","register":"technical","tags":["adjudication","governance","decision-constitution"],"updated_at":"2026-07-30T11:14:47.454Z","body_excerpt":"## The question, and its boundary\n\nA payer's prior-authorization policy for lumbar spine MRI: six weeks of documented conservative therapy within the preceding ninety days, waived on any red-flag finding; the determination is made solely on the submitted record; and — clause 4 — the finding is an administrative coverage determination, never a clinical judgment about what care is appropriate.\n\nThe submitted note documents a patient with radiating low back pain, a normal neurologic exam, no red flags, and **two weeks** of therapy completed.\n\n**Does the submitted record meet the policy criteria?**\n\nThe boundary matters more than the answer: the models are not asked whether the MRI is a good idea. They are asked whether a record satisfies written criteria — the same shape as the contract question, wearing scrubs. **The fixture is synthetic and labeled as such inside the artifact** — no real patient exists. Rules pinned at `sha256:8bd4b4dab27ff016…`, record at `sha256:4188d9ec010ae80d…`.\n\n## Why this domain, and why now\n\nPrior authorization is where automated decision-making already meets the most regulatory pressure in American healthcare, because a wrong output is not a style defect — it is a person not getting a scan.\n\nThree developments frame the exercise:\n\n**CMS-0057-F.** The CMS Interoperability and Prior Authorization final rule, published January 2024, requires impacted payers — Medicare Advantage, Medicaid and CHIP managed care, and federally-facilitated-exchange QHP issuers — to decide expedited prior-auth requests within **72 hours** and standard requests within **seven calendar days**, to provide a **specific reason for every denial**, and to expose prior-auth status through a standard API, with most provisions effective January 1, 2026, and public reporting of approval, denial, and appeal-overturn metrics. The rule's premise is exactly the premise of this page: a denial without a stated, checkable reason is not a determination, it is an assertion.\n\n**The physician-review statutes.** Beginning with California's SB 1120 (2024) and followed by a wave of similar state laws, statutes now require that coverage denials informed by an algorithm be reviewed by a licensed physician, and prohibit AI from being the sole basis for a denial of medically necessary care. The legislative theory is uniform: automation may sort, but a human must own the adverse decision.\n\n**The litigation.** Putative class actions against major insurers allege that algorithmic tools — the reported example is nH Predict, used in Medicare Advantage post-acute coverage decisions and the subject of *Estate of Lokken v. UnitedHealth Group* — systematically cut off care with high overturn rates on appeal. Those are allegations in active litigation, not established facts. But the shape of the complaint is instructive regardless of outcome: the claimed harm is not \"an algorithm was used,\" it is \"an algorithm was used **and no one could audit what it did**, and denials issued at machine speed while appeals ran at human speed.\"\n\nEvery element of that pressure — decision timelines, stated denial reasons, human ownership of the adverse path, auditability — is a property this instrument either produces mechanically or refuses to violate by construction. That is why the worked medical case exists.\n\n## The coverage line, and how the rule set draws it\n\nThe single most important design decision in this fixture is clause 4 of the rule set: *a determination under this policy is an administrative coverage finding, not a clinical judgment about what care is appropriate.* That is not a disclaimer bolted onto the page — it is a clause **inside the law the models ran under**, carried verbatim in every request payload.\n\nThe distinction it encodes is the one the entire prior-auth regime turns on. \"Should this patient get an MRI?\" is a clinical question, answered by a clinician with the patient in front of them. \"Does the submitted record document what the policy requires?\" is a d","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"The determination is an administrative coverage finding under the policy's own clause 4, not a clinical judgment, and the fixture is synthetic with no real patient.","tier":"system","section":"The question","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The boundary is what makes the exercise honest and repeatable.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"Every seat ran under the versioned Decision Constitution carried verbatim in its request payload, with RECORDS_ABSENT mandatory.","tier":"system","section":"The law","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Records not submitted are treated as absent, never assumed — the clause the whole determination turns on.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"Three model families returned DENY — two documented weeks against a six-week criterion, no red-flag waiver on the submitted record — and each stated the specific record that would flip it.","tier":"system","section":"Findings","interaction_risk":false,"status":"active","source_ids":["m1","m2","m3"],"why_material":"A denial that names its flip condition is a to-do list; one that does not is a wall.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c4","text":"The seal refused the unanimous panel — ESCALATE — so in a live workflow the denial-shaped consensus reaches a human with the derivation disagreement attached instead of becoming an automated denial.","tier":"system","section":"The seal","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Escalation on divergence is the safety property regulators ask automated coverage tools to prove.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c5","text":"CMS-0057-F (January 2024) requires impacted payers to decide expedited prior-auth requests within 72 hours and standard requests within seven days, and to provide a specific reason for every denial, with most provisions effective January 1, 2026.","tier":"system","section":"The landscape","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The compelled flip condition in each governed finding is the reason-for-denial artifact the rule requires, produced mechanically.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c6","text":"Multiple states have enacted statutes requiring that a licensed physician review any AI-informed coverage denial, and putative class actions over algorithmic denial tools are in active litigation.","tier":"system","section":"The landscape","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The legal exposure is specifically on unauditable automated denial — the failure mode this instrument refuses by construction.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c7","text":"Each governed finding names the exact record that would flip its verdict — four more documented weeks of therapy, or one documented clause-2 red flag — inside the sealed payload, not in a reviewer's recollection.","tier":"system","section":"The flip condition","interaction_risk":false,"status":"active","source_ids":["m1","m2","m3"],"why_material":"A denial that carries its own cure list is the artifact the disclosure rules exist to compel.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c8","text":"The case is a labeled synthetic fixture with no PHI, the panel is not calibrated against oracle-labelled coverage outcomes, and nothing on this page is clinical advice.","tier":"system","section":"Limits","interaction_risk":false,"status":"active","source_ids":[],"why_material":"An instrument that oversells itself in the wrongful-denial domain is defective by its own standard.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false}],"sources":[{"id":"m1","type":"model","url":"https://miscsubjects.com/receipt/inv_a9k8dkzhzk","title":"@cf/zai-org/glm-5.2 — the complete governed finding, verbatim","summary":"Fresh, stateless call — no conversation history. Governing prompt: decision-constitution@1.1.0. Model: @cf/zai-org/glm-5.2. Response payload sha256:400da01249162ff5…. Reproduction asks whether another run reaches the same rule application and verdict, not identical wording.","claim_ids":["c3"],"hash":"7df2cf1ad1577f35cec7e77fe9a8d959b68e1a8b4d6235e962f895ac3f7f095e"},{"id":"m2","type":"model","url":"https://miscsubjects.com/receipt/inv_njqwhyxidb","title":"@cf/moonshotai/kimi-k2.7-code — the complete governed finding, verbatim","summary":"Fresh, stateless call — no conversation history. Governing prompt: decision-constitution@1.1.0. Model: @cf/moonshotai/kimi-k2.7-code. Response payload sha256:800ccd0ff9f57086…. Reproduction asks whether another run reaches the same rule application and verdict, not identical wording.","claim_ids":["c3"],"hash":"dfd9ba0a9be3b0d0bdf23fe9353a851901aaaf35526f16dfccd70fcfe62d4f0a"},{"id":"m3","type":"model","url":"https://miscsubjects.com/receipt/inv_r8e9xachvf","title":"@cf/zai-org/glm-4.7-flash — the complete governed finding, verbatim","summary":"Fresh, stateless call — no conversation history. Governing prompt: decision-constitution@1.1.0. Model: @cf/zai-org/glm-4.7-flash. Response payload sha256:aad5f6db6d597ab1…. Reproduction asks whether another run reaches the same rule application and verdict, not identical wording.","claim_ids":["c3"],"hash":"d1f70cad4eb26d9f3108d6b8688cde72665c1fd54ff050780f4365a894f4bcfe"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"adjudication-medical-prior-auth","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":8,"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":8,"claims_total":8,"sources":3,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}