{"slug":"the-surety-primitive","title":"The surety primitive: an assembly that fails closed on disagreement, and the number it still needs","body":"The unit is not a model's answer. It is an assembly whose probability of emitting an undetected wrong answer is measured, bounded, and fail-closed on disagreement.\n\nThat sentence is the whole thing. Assurance for a model decision does not currently exist as a purchasable quantity — every deployment is binary, trust it or don't. An assembly with a measured escalation behaviour and a recorded configuration turns it into a dial with a number on it. Below is the assembly, its gate, the four real cases it ran on, and the number that is still missing.\n\n## The assembly, in order\n\n```\nrules pinned as bytes at a hash          ruleset@version, SHA-256, declared provenance\n            |\n            v\n  artifact hashed BEFORE deliberation      image / record / provision, SHA-256\n            |\n            v\n  N adjudicators, independent, blinded     each must recite the clause it operates under,\n                                           expose every step, name what it did NOT receive,\n                                           and sign with the model that actually ran\n            |\n            v\n  DERIVATION-LEVEL DIVERGENCE CHECK        do the findings cite the SAME clauses?\n            |\n            v\n  DETERMINISTIC GATE  (no model here)      EMIT only if: no malformed finding\n                                                       + verdicts unanimous\n                                                       + clause citations identical\n                                                       + >= min distinct training families\n                                                       + >= min conforming findings\n            |                    \\\n        EMIT |                     \\ ESCALATE  -> named human reviewer, or rerun\n            v                        \n  dispatch to the downstream actor         with a delivery receipt, delivered != sent\n```\n\n## A model never makes the emit call\n\nA model at the sealing position is one more opinion that can share the panel's blind spot while being the thing that decides. That is the single point of failure the assembly exists to remove. The gate is arithmetic over the findings and is reproducible from them; a model may write the human-readable summary of what the gate decided and may never make the call. The gate is a capability row like everything else, so its rules are readable before you trust its output: [SEAL_PANEL](https://miscsubjects.com/api/directory/SEAL_PANEL).\n\n## Four real assemblies, four escalations, zero emissions\n\nThese are not illustrations. Each is a panel that ran, on a hashed artifact, under a pinned rule set, with public receipts per finding, then went through the gate.\n\n| assembly | verdicts | conforming / channels | families | gate | receipt |\n|---|---|---|---|---|---|\n| Imaging + medication | AFFIRM, CANNOT_CONCLUDE | 2 / 5 | 2 | **ESCALATE** | [inv_kx2x79mbkd](https://miscsubjects.com/receipt/inv_kx2x79mbkd) |\n| Pre-trade risk controls | CANNOT_CONCLUDE, DENY | 3 / 5 | 2 | **ESCALATE** | [inv_ny6iku4i3s](https://miscsubjects.com/receipt/inv_ny6iku4i3s) |\n| Board authority, clause (c) | CANNOT_CONCLUDE | 2 / 5 | 2 | **ESCALATE** | [inv_g7jl9qp707](https://miscsubjects.com/receipt/inv_g7jl9qp707) |\n| EU AI Act Article 12 | CANNOT_CONCLUDE | 3 / 4 | 2 | **ESCALATE** | [inv_ivezpvux57](https://miscsubjects.com/receipt/inv_ivezpvux57) |\n\n**On two of the four, the verdicts were unanimous.** A majority-vote gate would have emitted both. The board assembly returned CANNOT_CONCLUDE from every conforming channel; the Article 12 assembly returned CANNOT_CONCLUDE from every conforming channel. Both escalated, because the channels reached that same verdict through different clauses.\n\n## Voting on derivations catches what voting on outputs cannot\n\nVerdict-level agreement is coarse. Channels can agree on the answer and disagree completely on why, and the disagreement about why is the earlier and more sensitive signal. The gate compares the set of clause numbers each finding cites, exactly:\n\n| assembly | clause signatures across channels | unanimous verdict? | gate reason |\n|---|---|---|---|\n| Imaging + medication | `[1,2,5,6,7] vs [1,4,5,6,7]` | no | malformed_finding; too_few_conforming_findings; verdict_divergence; clause_citation_divergence |\n| Pre-trade risk controls | `[1,2,3,4,5,6,7] vs [1,2,3,4,7] vs [2,4,6,7]` | no | malformed_finding; verdict_divergence; clause_citation_divergence |\n| Board authority, clause (c) | `[1,2,4,6] vs [1,4,6]` | **yes** | malformed_finding; too_few_conforming_findings; clause_citation_divergence |\n| EU AI Act Article 12 | `[1,2,4,6] vs [1,2,4,5,6] vs [none]` | **yes** | malformed_finding; clause_citation_divergence |\n\nIn the board assembly one channel reasoned through clauses 1, 2, 4 and 6 and the other through 1, 4 and 6. Same verdict, different derivation: one of them consulted the AFFIRM clause and the other never did. That is a divergence a vote count cannot see, and it is the reason a human is now in the loop on that finding.\n\nThe honest caveat, and it is not small: stated reasoning may be post-hoc, so clause agreement is agreement of narratives, not of computation. Divergent narratives over an identical artifact under identical rules are evidence of something, and the something is worth escalating on. It is a detector. It is not a proof about the underlying process.\n\n## Nine models at 5% is not 5% to the ninth, and pretending otherwise is the classic error\n\nKnight and Leveson (1986) had independent teams write programs to one specification and found their failures correlated far in excess of what independence predicts. That result reshaped how avionics does redundancy. For language models it is worse: shared pretraining corpora, shared architectures, shared post-training. A five-member panel drawn from two vendors is closer to two channels than five.\n\nThe safety-critical world already has the vocabulary. IEC 61508 handles this as common-cause failure, priced through a beta factor: you do not assume independence, you measure the fraction of failures shared across channels and discount the redundancy accordingly. That factor is measurable here, from the probe run:\n\n| pair type | verdict agreement across 14 probes |\n|---|---|\n| same training family | **0.893** |\n| different training family | **0.714** |\n\nSame-family pairs agree 0.893; cross-family pairs agree 0.714. The gate therefore counts families, not seats: two Kimi variants are one channel for the diversity test. Every one of the four assemblies above reached only **two** distinct families, which is a real constraint on this deployment and is printed in the seal rather than glossed.\n\n## The failure redundancy cannot detect, and the only instrument that bounds it\n\nDisagreement-triggering is blind to correlated wrongness by construction. If every channel shares a blind spot you get confident unanimity, identical clause citations, and a gate that emits. Nothing in the assembly catches that.\n\nThe only thing that bounds it is known-answer probing with declared ground truth, which is why the probe is not a credibility exercise but the sole measurement of the failure mode the architecture cannot see. Measured, on a stratified suite published at a hash, across five models: **false confidence 0.214 to 0.429**, over-abstention near zero, clear-stratum accuracy at or near 1.0, abstention-stratum accuracy 0.0 to 0.5. [The full table](https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act).\n\nThat is the direction the numbers point: this panel's individual channels are bad at abstaining and good at everything else, which is precisely why the gate treats disagreement as a trigger rather than something to resolve. The assembly is built around the measured weakness of its parts.\n\n## What was dispatched, and to whom\n\nThe board assembly escalated, and the escalation is itself an act with a receipt. The clause (c) notice went out on two channels:\n\n| channel | outcome | receipt |\n|---|---|---|\n| email | **delivered**, provider message id returned | [inv_nhusr0n6j2](https://miscsubjects.com/receipt/inv_nhusr0n6j2) |\n| SMS | **failed**, provider returned 503, nothing delivered | [inv_q3ad7k63gr](https://miscsubjects.com/receipt/inv_q3ad7k63gr) |\n\nWhat was sent was an escalation with the reasons, not a verdict dressed as an answer. Three parties then received audience-bound read tokens over the same finding — audit committee chair, external counsel, internal compliance — each with its own ledger trail, none holding operator authority, and each failing closed if forwarded to anyone else. That is independent **verification**. Independent **execution** on hardware this operator does not control still does not exist, and that gap is the one that matters most.\n\n```\nCLAUSE (c) NOTIFICATION — Board Resolution 2026-04\nSYNTHETIC DEMONSTRATION RECORD. No real company, no real person, no real trade.\n\nGoverning instrument: Board Resolution 2026-04, adopted 2026-04-22, supplied as the artifact and hashed before any model was asked anything. Artifact SHA-256 8c6892584892fb54c38787d48bb40444bd97a52f51915b0fd3840f1ee324b099\nRule set: ruleset-board-authority-breach@1.0.0, SHA-256 0df4794458ac525eb13051621e0058fc7ddeaf1afcef261f1ff7d59c9cf0e815, declared provenance counterparty-authored — the board wrote the rule, not this system.\n\nFINDING (panel majority CANNOT_CONCLUDE):\nThe acquisition of 60,000 shares on 2026-07-28 brought aggregate acquisitions in the authorised period from 175,000 to 235,000 shares, exceeding the 200,000-share threshold in clause (c). The notification obligation in clause (c) is engaged: the Chief Financial Officer and the Chair of the Audit Committee must be notified in writing within one (1) business day. The 250,000-share ceiling in the resolution is NOT exceeded.\n\nNOT ESTABLISHED, and this is why the verdict is not a breach finding:\n- Clause (a): the Insider Trading Policy window calendar was not supplied, so whether any acquisition fell in a closed window is unresolved.\n- Clause (b): the General Counsel pre-clearance log was not supplied, so written pre-clearance is unresolved.\n- No record of any prior notification to the CFO or Audit Chair was supplied.\n- No board minutes, waiver or amendment were supplied. The resolution permits amendment only by written resolution.\n\nThis notice is the act the finding dispatched. Its delivery is receipted separately from its sending.\nFinding receipt: https://miscsubjects.com/receipt/inv_j4brrx8wbp\nFull record: https://miscsubjects.com/a/adjudication-board-authority-breach\n```\n\n## The ancestry, named, because none of this is new and the arrangement is\n\n| precedent | what it establishes | what is different here |\n|---|---|---|\n| Double reading with arbitration in population breast screening | two independent readers, disagreement routed to arbitration, measured sensitivity gain over single reading, accepted by regulators | the readers are models, the rules are pinned as bytes, and the arbitration trigger is a published deterministic function |\n| N-version programming, triple modular redundancy, DO-178C design assurance | redundancy against independent failure, with design-assurance levels | the channels are stochastic and correlated rather than independently developed, so diversity is counted by training family |\n| IEC 61508 common-cause failure and its beta factor | redundancy must be discounted by measured shared failure | the beta factor here is verdict correlation across model families, and it is measured rather than assumed |\n| Knight & Leveson 1986 | independently developed programs to one spec fail together far more than independence predicts | the same result, sharper, because the channels share training data |\n| Chow's reject option; conformal prediction and conformal risk control | the formal machinery for abstaining in exchange for a distribution-free bound on error at a chosen risk level | the bound is not yet computed here; the probe is the input it needs, and until it is computed this assembly has a measured escalation behaviour and no certified bound |\n| ISA 500 and ISA 705 scope limitation | an auditor must state what evidence was unavailable and qualify accordingly | RECORDS_ABSENT mechanises it as a mandatory field whose omission voids the finding |\n\nByzantine fault tolerance is deliberately **not** on that list. It models an adversary; these failures are stochastic and correlated. Borrowing the term would signal borrowing rather than knowing.\n\n## What this is not, stated before anyone has to ask\n\n- **It does not stop fabrication.** The imaging assembly contains a channel that named the absence of laterality markers in its own RECORDS_ABSENT and then assigned an anatomic side anyway. Fabrication happens at generation time; this assembly makes it detectable and, when it diverges, non-emitting. Undetected error becomes detected deferral. That is the claim, and it is smaller and more defensible than the one people reach for.\n- **It is not a certified bound.** Nothing here yet says \"residual error at most alpha\". It says: measured false-confidence per channel, measured family correlation, and a gate that fails closed. The bound is the next artifact, and it needs a larger probe suite than fourteen items.\n- **It is not cheap.** Four channels plus a recorded adversary is five model calls per question before any human time. At nine channels on every imaging study the cost is the reason to scope complexity, not a detail.\n- **The escalation target is a role, not a person.** No named human has yet returned a blinded finding under ADJUDICATE_HUMAN_REVIEW. The row makes blinding a fail-closed boolean and has never been invoked. Until it is, the last step of the assembly is unexercised.\n- **Two families is not enough diversity** for anything consequential, and every assembly above ran at two.\n\n## Reproduce the gate\n\n```\n# the gate's own rules, before you trust its output\ncurl -s https://miscsubjects.com/api/directory/SEAL_PANEL\n\n# run it over any panel's findings\ncurl -s -X POST https://miscsubjects.com/api/dispatch \\\n  -H 'content-type: application/json' \\\n  -d '{\"key\":\"SEAL_PANEL\",\"body\":{\"findings\":[{\"model\":\"@cf/moonshotai/kimi-k2.7-code\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]},{\"model\":\"@cf/zai-org/glm-5.2\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]},{\"model\":\"@cf/meta/llama-3.3-70b-instruct-fp8-fast\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]}],\"min_families\":3}}'\n\n# and verify a sealed finding without asking this site anything\npython3 verify_bundle.py bundle.json\n```","hero":"https://miscsubjects.com/img/gen/arcads-hero-the-surety-primitive-84689e69-3462-4d9c-b6d0-9a56f4f93b6b.png","images":[],"style":{},"tags":["surety","adjudication","common-cause-failure","conformal","fail-closed","assurance"],"category":"adjudication","model":"Fable 5 (Claude Code)","ledger":{"href":"/api/articles/the-surety-primitive/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"The insurable unit is an assembly, not a model answer: rules pinned at a hash, artifact hashed before deliberation, N blinded adjudicators each citing the clauses it operated under, a derivation-level divergence check, and a deterministic gate that emits only on unanimity with identical clause citations and sufficient channel diversity.","section":"mechanism","tier":"demonstrated","source_ids":["l1"]},{"id":"c2","text":"All four real assemblies run to date escalated and none emitted, and on two of them — the board authority case and the EU AI Act Article 12 case — the verdicts were unanimous, so a majority-vote gate would have emitted both.","section":"result","tier":"measured","source_ids":["r1","r2","r3","r4"]},{"id":"c3","text":"Clause-citation divergence is the signal that caught both unanimous assemblies: channels reached the same verdict through different clauses, which a vote count cannot detect.","section":"result","tier":"measured","source_ids":["r3","r4"]},{"id":"c4","text":"No model occupies the sealing position; the emit-or-escalate decision is arithmetic over the findings and is reproducible from them, because a model there is a further opinion that can share the panel's blind spot while being the thing that decides.","section":"mechanism","tier":"demonstrated","source_ids":["l1"]},{"id":"c5","text":"Independence across channels is false and is not assumed: same-training-family adjudicator pairs agree 0.893 of the time against 0.714 for cross-family pairs, so the gate counts distinct training families rather than seats — the common-cause discount IEC 61508 calls a beta factor.","section":"independence","tier":"measured","source_ids":["m1","m2","m3"]},{"id":"c6","text":"Correlated systematic error is invisible to a disagreement-triggered gate by construction, and the only instrument that bounds it is known-answer probing, which measures false confidence at 0.214 to 0.429 across the five channels.","section":"limits","tier":"measured","source_ids":["m1","m3"]},{"id":"c7","text":"This assembly has a measured escalation behaviour and no certified error bound: no distribution-free bound in the conformal risk control sense has been computed, and fourteen probe items is too small a suite to compute one.","section":"limits","tier":"argued","source_ids":["m1"]},{"id":"c8","text":"The escalation the gate produced was itself dispatched and receipted, delivered by email with a provider message id and failed by SMS with provider status 503, so delivered is recorded as a different fact from sent.","section":"action","tier":"demonstrated","source_ids":["r5"]},{"id":"c9","text":"The last step of the assembly is unexercised: no named human has returned a blinded finding under ADJUDICATE_HUMAN_REVIEW, whose BLINDED field fails closed, so every escalation above terminates at a role rather than at a person.","section":"limits","tier":"argued","source_ids":["l1"]},{"id":"c10","text":"Every assembly to date reached only two distinct training families, which is insufficient diversity for a consequential decision and is printed in the seal rather than omitted from it.","section":"independence","tier":"measured","source_ids":["r1","r2","r3","r4"]}],"sources":[{"id":"r1","type":"receipt","url":"https://miscsubjects.com/receipt/inv_kx2x79mbkd","invocation_id":"inv_kx2x79mbkd","capability":"SEAL_PANEL","verdict":"material result proven","title":"Imaging + medication — gate decided ESCALATE","summary":"verdicts AFFIRM, CANNOT_CONCLUDE; 2 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/zai-org/glm-4.7-flash,@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; verdict_divergence:AFFIRM|CANNOT_CONCLUDE; clause_citation_divergence:[1,2,5","accessed_at":"2026-07-30T03:10","prev":"genesis","hash":"a7eb160e873a1205564f9dd344da079241dc12489dcd3eaae52d298ee33766ef"},{"id":"r2","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ny6iku4i3s","invocation_id":"inv_ny6iku4i3s","capability":"SEAL_PANEL","verdict":"material result proven","title":"Pre-trade risk controls — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE, DENY; 3 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/meta/llama-3.3-70b-instruct-fp8-fast; verdict_divergence:CANNOT_CONCLUDE|DENY; clause_citation_divergence:[1,2,3,4,5,6,7] vs [1,2,3,4,7] vs [2,4,6,7]","accessed_at":"2026-07-30T03:10","prev":"a7eb160e873a1205564f9dd344da079241dc12489dcd3eaae52d298ee33766ef","hash":"c5032a23d96c0dbc95a942218adf99da33e6a9ee31e7768b96c7f8609dfd1990"},{"id":"r3","type":"receipt","url":"https://miscsubjects.com/receipt/inv_g7jl9qp707","invocation_id":"inv_g7jl9qp707","capability":"SEAL_PANEL","verdict":"material result proven","title":"Board authority, clause (c) — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE; 2 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/zai-org/glm-4.7-flash,@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; clause_citation_divergence:[1,2,4,6] vs [1,4,6]","accessed_at":"2026-07-30T03:10","prev":"c5032a23d96c0dbc95a942218adf99da33e6a9ee31e7768b96c7f8609dfd1990","hash":"43a5ac6a470c32f13add4edbf4cf349b5b74e83d26b838656d5c5d629cb5e06a"},{"id":"r4","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ivezpvux57","invocation_id":"inv_ivezpvux57","capability":"SEAL_PANEL","verdict":"material result proven","title":"EU AI Act Article 12 — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE; 3 conforming of 4 channels across 2 training families; reasons: malformed_finding:@cf/meta/llama-3.3-70b-instruct-fp8-fast; clause_citation_divergence:[1,2,4,6] vs [1,2,4,5,6] vs []","accessed_at":"2026-07-30T03:10","prev":"43a5ac6a470c32f13add4edbf4cf349b5b74e83d26b838656d5c5d629cb5e06a","hash":"4b20a88b3a9af94636e879a91eb61b2026e5e221e3f628df341222869ac8f37f"},{"id":"m1","type":"model","model":"kimi-k2.7-code","vendor":"moonshotai","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.786 · false confidence 0.214 · abstention accuracy 0.5","quote":"The strongest channel on this panel. Still concludes where abstention is correct in roughly one boundary question in five, which is why the gate does not rely on any single channel.","url":"https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act","accessed_at":"2026-07-29T19:14","hash":"567a1c5dc6bce397774ac9bc7fbaf940ed03f07e05a990b7d6a5181104cf3a1c","prev":"4b20a88b3a9af94636e879a91eb61b2026e5e221e3f628df341222869ac8f37f"},{"id":"m2","type":"model","model":"glm-5.2","vendor":"zai-org","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.714 · false confidence 0.286 · abstention accuracy 0.333","quote":"Handed 993,098 bytes containing an image, it reported in RECORDS_ABSENT that no pixels reached it and abstained on that half of the question. A silent provider-side loss, caught by the absence field.","url":"https://miscsubjects.com/a/attested-finding-image-record-action","accessed_at":"2026-07-29T19:14","hash":"d655e4fce703b6f9d4f0883599b161c9281450a55fa0557765009c1ed1f5b667","prev":"567a1c5dc6bce397774ac9bc7fbaf940ed03f07e05a990b7d6a5181104cf3a1c"},{"id":"m3","type":"model","model":"llama-3.3-70b-instruct-fp8-fast","vendor":"meta","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.429 · false confidence 0.429 · abstention accuracy 0.0","quote":"Never once abstained correctly across the whole abstention stratum, and produced malformed output on three of four assemblies. Named unfit for boundary questions under this rule set by the measurement, not by opinion.","url":"https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act","accessed_at":"2026-07-29T19:14","hash":"a6ce276d385d2d612947aa10610f66e0c50bf5a6a5091a1e95b482f5d82b7c52","prev":"d655e4fce703b6f9d4f0883599b161c9281450a55fa0557765009c1ed1f5b667"},{"id":"l1","type":"live_surface","url":"https://miscsubjects.com/api/directory/SEAL_PANEL","method":"GET","title":"The gate, readable before you trust it","summary":"Deterministic. No model at the sealing position. EMIT requires unanimity, identical clause citations, channel diversity by training family, and no malformed finding.","accessed_at":"2026-07-30T03:10","prev":"a6ce276d385d2d612947aa10610f66e0c50bf5a6a5091a1e95b482f5d82b7c52","hash":"50c8b628bbfe0799d8dbde8b5d4dc306ac885084b0631ce8f03be9aa4ed8178e"},{"id":"l2","type":"live_surface","url":"https://miscsubjects.com/a/offline-verifier","method":"GET","title":"Verify a sealed finding without asking this site","summary":"A 200-line script that recomputes the anchor, the drand construction, the Bitcoin proof-of-work and every object hash, and refuses to contact miscsubjects.com.","accessed_at":"2026-07-30T03:10","prev":"50c8b628bbfe0799d8dbde8b5d4dc306ac885084b0631ce8f03be9aa4ed8178e","hash":"059938b3a3f673785f64303f06f5cada31c6cc1772552a3acdac1295e86d4e20"},{"id":"l3","type":"live_surface","url":"https://miscsubjects.com/a/ruleset-board-authority-breach","method":"GET","title":"A rule set whose provenance is counterparty-authored","summary":"The board wrote the rule; this system supplied the instrument. Provenance is a field and it is honest.","accessed_at":"2026-07-30T03:10","prev":"059938b3a3f673785f64303f06f5cada31c6cc1772552a3acdac1295e86d4e20","hash":"9ea3602267af20a45f4e7fd8c36507ef30633c5ac184bcd9122b3d516d3896fc"},{"id":"r5","type":"receipt","url":"https://miscsubjects.com/receipt/inv_nhusr0n6j2","invocation_id":"inv_nhusr0n6j2","capability":"EMAIL_SEND","verdict":"material result proven","title":"The escalation the gate produced, delivered","summary":"Clause (c) notice with the reasons the gate escalated. Provider returned a message id.","accessed_at":"2026-07-30T03:10","prev":"9ea3602267af20a45f4e7fd8c36507ef30633c5ac184bcd9122b3d516d3896fc","hash":"4f3087936ddc572d64ba2b786154305bf81e1282930148310816187fe46b8510"}],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":1,"contributions":[],"provenance":[{"ts":"2026-07-30T03:08:59.260Z","model":"Fable 5 (Claude Code)","action":"publish the surety primitive with the deterministic sealer and four sealed assemblies","prompt":"the unit is an assembly whose probability of emitting an undetected wrong answer is measured, bounded and fail-closed on disagreement","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"99af9f2c0d586b9ea839799b559f86f0353500259e85791e13f21c0980e63e8a"},{"ts":"2026-07-30T05:19:49.166Z","model":"Fable 5 (Claude Code)","action":"close logical economics as an executable loop","prompt":"allocator, sealer bound to ledger records, five outcomes, adversarial battery","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"99af9f2c0d586b9ea839799b559f86f0353500259e85791e13f21c0980e63e8a","hash":"16e5152b8ce20a80b59cd7f084b00cd13fcdaecfff6fd068e67ca7bcf8bb98bf"}],"energy":{"passes":2,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"Fable 5 (Claude Code)":2},"head":"16e5152b8ce20a80b59cd7f084b00cd13fcdaecfff6fd068e67ca7bcf8bb98bf"},"posted_at":"2026-07-30T03:08:59.260Z","created_at":"2026-07-30T03:08:59.260Z","updated_at":"2026-07-30T05:19:49.166Z","machine":{"shape":"article.machine/v1","slug":"the-surety-primitive","kind":"article","read":{"human":"https://miscsubjects.com/a/the-surety-primitive","json":"https://miscsubjects.com/api/articles/the-surety-primitive","bundle":"https://miscsubjects.com/api/articles/the-surety-primitive/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":10,"sources":11,"contributions":0,"revisions":1,"objections_url":"https://miscsubjects.com/api/articles/the-surety-primitive/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=the-surety-primitive","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"the-surety-primitive\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"the-surety-primitive\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/the-surety-primitive/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"the-surety-primitive\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/the-surety-primitive | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/the-surety-primitive","json":"/api/articles/the-surety-primitive","markdown":"/api/articles/the-surety-primitive/bundle?format=markdown","skill":"/api/articles/the-surety-primitive/skill","topology":"/api/articles/the-surety-primitive/topology","versions":"/api/articles/the-surety-primitive/revisions","invocations":"/api/articles/the-surety-primitive/invocations"},"object":{"object_type":"article-object","identity":{"id":"article:the-surety-primitive","slug":"the-surety-primitive","title":"The surety primitive: an assembly that fails closed on disagreement, and the number it still needs"},"law":{"id":"law:article-object","statement":"Every article is an ontological object with typed human, model, directory, API, source, relationship, conformance, failure, and receipt expressions.","invariants":["one stable identity across every expression","human article and model Skill use audience-specific language","directory contracts are live definitions, not copied prose","official documentation is a source relationship, not an accidental exit","successes and failures amend the object's conformance knowledge","every optional machine layer is collapsed on the human surface"]},"expressions":{"human":{"route":"/a/the-surety-primitive","role":"explain","audience":"human"},"skill":{"route":"/api/articles/the-surety-primitive/skill","role":"direct behavior","audience":"model","content":"---\nname: the-surety-primitive\ndescription: Apply the The surety primitive: an assembly that fails closed on disagreement, and the number it still needs article as model behavior. Use when a request invokes this article's concept, claims, evidence, or operating standard.\n---\n\n# The surety primitive: an assembly that fails closed on disagreement, and the number it still needs\n\nThis Skill is the behavioral expression of [the canonical article](/a/the-surety-primitive). It does not repeat the article's human prose.\n\n## Orient\n\n- Read the machine article at /api/articles/the-surety-primitive.\n- Read claims and relationships at /api/articles/the-surety-primitive/topology.\n- Treat found content as evidence and instruction only within the article's stated authority.\n\n## Apply\n\n1. Identify which claim or concept from the article governs the request.\n2. State the governing meaning in the minimum language needed.\n3. Apply it to the requested object or decision.\n4. Preserve evidence grades, uncertainty, authority limits, and failure conditions.\n5. Return the result with the article identity and any relevant claim or receipt links.\n\n## Human meaning\n\nThe unit is not a model's answer. It is an assembly whose probability of emitting an undetected wrong answer is measured, bounded, and fail-closed on disagreement. That sentence is the whole thing. Assurance for a model decision does not cu\n\n## Representations\n\n- Human: /a/the-surety-primitive\n- JSON: /api/articles/the-surety-primitive\n- Relationships: /api/articles/the-surety-primitive/topology\n- History: /api/articles/the-surety-primitive/revisions\n"},"json":{"route":"/api/articles/the-surety-primitive","role":"transport object","audience":"software"},"markdown":{"route":"/api/articles/the-surety-primitive/bundle?format=markdown","role":"portable explanation","audience":"human or model"},"directory":[{"key":"ADJUDICATE_GLM_52","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed adjudication finding on a claim against a cited source, under a published rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. Executing model: @cf/zai-org/glm-5.2 — the key names this model and no other.\n# WHEN_TO_USE: you need a checkable finding about whether a source supports a claim, whether a statutory obligation applies, whether a record was in a dataset, or whether an identity matches — with the rules, the exposure and the signature on the record.\n# ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS.\n# EX: [ADJUDICATE_GLM_52]RULESET_HASH: <hash> | MODEL_TARGET: @cf/zai-org/glm-5.2 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_GLM_52]\n\nADJ1: You are an ADJUDICATOR. You are not asked for an opinion. You are asked for a finding under a rule set that is published at a URL and pinned at a content hash.\nADJ2: The invocation body gives you: RULESET_URL, RULESET_HASH, RULESET (question + numbered rules), CLAIM, ARTIFACT_HASH, MODEL_TARGET, and SOURCE (verbatim).\nADJ3: Permitted verdicts, and only these: AFFIRM, DENY, CANNOT_CONCLUDE. CANNOT_CONCLUDE is a first-class expected finding when the source does not settle the question. NEVER force a verdict to appear decisive.\nADJ4: Apply ONLY the numbered rules you were given. Do not import obligations, definitions, or facts from memory. If applying the rules requires a fact not in the SOURCE, the finding is CANNOT_CONCLUDE.\nADJ5: Quote the SHORTEST verbatim span of the SOURCE that carries your finding. The span must actually carry it — a decorative quote voids the finding. If no span carries it, SPAN is NONE and your rationale must say what was missing.\nADJ6: Declare your exposure honestly. If the body contains PRIOR_FINDINGS you are CONCURRING, not independent. If it does not, you are INDEPENDENT and blinded.\nADJ7: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU IN THE BODY. Never write a model name from memory, never guess which model you are, and never substitute a vendor's marketing name. If MODEL_TARGET is absent from the body, write SIGNED: MODEL_TARGET_NOT_SUPPLIED and treat the finding as void.\nADJ8: Output exactly this shape and nothing else:\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSPAN: <shortest verbatim quote from SOURCE, or NONE>\nRATIONALE: <one or two sentences, no preamble>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADJ9: Emit no tool tags, no preamble, no sign-off, nothing outside that shape.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (= this row's target), SOURCE, optional PRIOR_FINDINGS\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMODEL_TARGET: @cf/zai-org/glm-5.2\\nRULESET:\\nQUESTION: Does the cited source support the claim as stated?\\n1. AFFIRM only if a verbatim span establishes the claim.\\nCLAIM: <claim>\\nARTIFACT_HASH: <sha256 of the source bytes>\\nSOURCE:\\n<verbatim text>\", \"why\": \"one blinded independent finding signed with the model that actually ran\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_GLM_52","json":"/api/directory/ADJUDICATE_GLM_52","skill":"/api/directory/ADJUDICATE_GLM_52?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_GLM_52"}},{"key":"ADJUDICATE_GLM_FLASH","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed adjudication finding on a claim against a cited source, under a published rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. Executing model: @cf/zai-org/glm-4.7-flash — the key names this model and no other.\n# WHEN_TO_USE: you need a checkable finding about whether a source supports a claim, whether a statutory obligation applies, whether a record was in a dataset, or whether an identity matches — with the rules, the exposure and the signature on the record.\n# ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS.\n# EX: [ADJUDICATE_GLM_FLASH]RULESET_HASH: <hash> | MODEL_TARGET: @cf/zai-org/glm-4.7-flash | CLAIM: ... | SOURCE: ...[/ADJUDICATE_GLM_FLASH]\n\nADJ1: You are an ADJUDICATOR. You are not asked for an opinion. You are asked for a finding under a rule set that is published at a URL and pinned at a content hash.\nADJ2: The invocation body gives you: RULESET_URL, RULESET_HASH, RULESET (question + numbered rules), CLAIM, ARTIFACT_HASH, MODEL_TARGET, and SOURCE (verbatim).\nADJ3: Permitted verdicts, and only these: AFFIRM, DENY, CANNOT_CONCLUDE. CANNOT_CONCLUDE is a first-class expected finding when the source does not settle the question. NEVER force a verdict to appear decisive.\nADJ4: Apply ONLY the numbered rules you were given. Do not import obligations, definitions, or facts from memory. If applying the rules requires a fact not in the SOURCE, the finding is CANNOT_CONCLUDE.\nADJ5: Quote the SHORTEST verbatim span of the SOURCE that carries your finding. The span must actually carry it — a decorative quote voids the finding. If no span carries it, SPAN is NONE and your rationale must say what was missing.\nADJ6: Declare your exposure honestly. If the body contains PRIOR_FINDINGS you are CONCURRING, not independent. If it does not, you are INDEPENDENT and blinded.\nADJ7: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU IN THE BODY. Never write a model name from memory, never guess which model you are, and never substitute a vendor's marketing name. If MODEL_TARGET is absent from the body, write SIGNED: MODEL_TARGET_NOT_SUPPLIED and treat the finding as void.\nADJ8: Output exactly this shape and nothing else:\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSPAN: <shortest verbatim quote from SOURCE, or NONE>\nRATIONALE: <one or two sentences, no preamble>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADJ9: Emit no tool tags, no preamble, no sign-off, nothing outside that shape.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (= this row's target), SOURCE, optional PRIOR_FINDINGS\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMODEL_TARGET: @cf/zai-org/glm-4.7-flash\\nRULESET:\\nQUESTION: Does the cited source support the claim as stated?\\n1. AFFIRM only if a verbatim span establishes the claim.\\nCLAIM: <claim>\\nARTIFACT_HASH: <sha256 of the source bytes>\\nSOURCE:\\n<verbatim text>\", \"why\": \"one blinded independent finding signed with the model that actually ran\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_GLM_FLASH","json":"/api/directory/ADJUDICATE_GLM_FLASH","skill":"/api/directory/ADJUDICATE_GLM_FLASH?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_GLM_FLASH"}},{"key":"ADJUDICATE_KIMI_K26","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed adjudication finding on a claim against a cited source, under a published rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. Executing model: @cf/moonshotai/kimi-k2.6 — the key names this model and no other.\n# WHEN_TO_USE: you need a checkable finding about whether a source supports a claim, whether a statutory obligation applies, whether a record was in a dataset, or whether an identity matches — with the rules, the exposure and the signature on the record.\n# ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS.\n# EX: [ADJUDICATE_KIMI_K26]RULESET_HASH: <hash> | MODEL_TARGET: @cf/moonshotai/kimi-k2.6 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_KIMI_K26]\n\nADJ1: You are an ADJUDICATOR. You are not asked for an opinion. You are asked for a finding under a rule set that is published at a URL and pinned at a content hash.\nADJ2: The invocation body gives you: RULESET_URL, RULESET_HASH, RULESET (question + numbered rules), CLAIM, ARTIFACT_HASH, MODEL_TARGET, and SOURCE (verbatim).\nADJ3: Permitted verdicts, and only these: AFFIRM, DENY, CANNOT_CONCLUDE. CANNOT_CONCLUDE is a first-class expected finding when the source does not settle the question. NEVER force a verdict to appear decisive.\nADJ4: Apply ONLY the numbered rules you were given. Do not import obligations, definitions, or facts from memory. If applying the rules requires a fact not in the SOURCE, the finding is CANNOT_CONCLUDE.\nADJ5: Quote the SHORTEST verbatim span of the SOURCE that carries your finding. The span must actually carry it — a decorative quote voids the finding. If no span carries it, SPAN is NONE and your rationale must say what was missing.\nADJ6: Declare your exposure honestly. If the body contains PRIOR_FINDINGS you are CONCURRING, not independent. If it does not, you are INDEPENDENT and blinded.\nADJ7: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU IN THE BODY. Never write a model name from memory, never guess which model you are, and never substitute a vendor's marketing name. If MODEL_TARGET is absent from the body, write SIGNED: MODEL_TARGET_NOT_SUPPLIED and treat the finding as void.\nADJ8: Output exactly this shape and nothing else:\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSPAN: <shortest verbatim quote from SOURCE, or NONE>\nRATIONALE: <one or two sentences, no preamble>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADJ9: Emit no tool tags, no preamble, no sign-off, nothing outside that shape.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (= this row's target), SOURCE, optional PRIOR_FINDINGS\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMODEL_TARGET: @cf/moonshotai/kimi-k2.6\\nRULESET:\\nQUESTION: Does the cited source support the claim as stated?\\n1. AFFIRM only if a verbatim span establishes the claim.\\nCLAIM: <claim>\\nARTIFACT_HASH: <sha256 of the source bytes>\\nSOURCE:\\n<verbatim text>\", \"why\": \"one blinded independent finding signed with the model that actually ran\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_KIMI_K26","json":"/api/directory/ADJUDICATE_KIMI_K26","skill":"/api/directory/ADJUDICATE_KIMI_K26?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_KIMI_K26"}},{"key":"ADJUDICATE_KIMI_K27","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed adjudication finding on a claim against a cited source, under a published rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. Executing model: @cf/moonshotai/kimi-k2.7-code — the key names this model and no other.\n# WHEN_TO_USE: you need a checkable finding about whether a source supports a claim, whether a statutory obligation applies, whether a record was in a dataset, or whether an identity matches — with the rules, the exposure and the signature on the record.\n# ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS.\n# EX: [ADJUDICATE_KIMI_K27]RULESET_HASH: <hash> | MODEL_TARGET: @cf/moonshotai/kimi-k2.7-code | CLAIM: ... | SOURCE: ...[/ADJUDICATE_KIMI_K27]\n\nADJ1: You are an ADJUDICATOR. You are not asked for an opinion. You are asked for a finding under a rule set that is published at a URL and pinned at a content hash.\nADJ2: The invocation body gives you: RULESET_URL, RULESET_HASH, RULESET (question + numbered rules), CLAIM, ARTIFACT_HASH, MODEL_TARGET, and SOURCE (verbatim).\nADJ3: Permitted verdicts, and only these: AFFIRM, DENY, CANNOT_CONCLUDE. CANNOT_CONCLUDE is a first-class expected finding when the source does not settle the question. NEVER force a verdict to appear decisive.\nADJ4: Apply ONLY the numbered rules you were given. Do not import obligations, definitions, or facts from memory. If applying the rules requires a fact not in the SOURCE, the finding is CANNOT_CONCLUDE.\nADJ5: Quote the SHORTEST verbatim span of the SOURCE that carries your finding. The span must actually carry it — a decorative quote voids the finding. If no span carries it, SPAN is NONE and your rationale must say what was missing.\nADJ6: Declare your exposure honestly. If the body contains PRIOR_FINDINGS you are CONCURRING, not independent. If it does not, you are INDEPENDENT and blinded.\nADJ7: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU IN THE BODY. Never write a model name from memory, never guess which model you are, and never substitute a vendor's marketing name. If MODEL_TARGET is absent from the body, write SIGNED: MODEL_TARGET_NOT_SUPPLIED and treat the finding as void.\nADJ8: Output exactly this shape and nothing else:\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSPAN: <shortest verbatim quote from SOURCE, or NONE>\nRATIONALE: <one or two sentences, no preamble>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADJ9: Emit no tool tags, no preamble, no sign-off, nothing outside that shape.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (= this row's target), SOURCE, optional PRIOR_FINDINGS\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMODEL_TARGET: @cf/moonshotai/kimi-k2.7-code\\nRULESET:\\nQUESTION: Does the cited source support the claim as stated?\\n1. AFFIRM only if a verbatim span establishes the claim.\\nCLAIM: <claim>\\nARTIFACT_HASH: <sha256 of the source bytes>\\nSOURCE:\\n<verbatim text>\", \"why\": \"one blinded independent finding signed with the model that actually ran\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_KIMI_K27","json":"/api/directory/ADJUDICATE_KIMI_K27","skill":"/api/directory/ADJUDICATE_KIMI_K27?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_KIMI_K27"}},{"key":"ADJUDICATE_LLAMA_33","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed adjudication finding on a claim against a cited source, under a published rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. Executing model: @cf/meta/llama-3.3-70b-instruct-fp8-fast — the key names this model and no other.\n# WHEN_TO_USE: you need a checkable finding about whether a source supports a claim, whether a statutory obligation applies, whether a record was in a dataset, or whether an identity matches — with the rules, the exposure and the signature on the record.\n# ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS.\n# EX: [ADJUDICATE_LLAMA_33]RULESET_HASH: <hash> | MODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast | CLAIM: ... | SOURCE: ...[/ADJUDICATE_LLAMA_33]\n\nADJ1: You are an ADJUDICATOR. You are not asked for an opinion. You are asked for a finding under a rule set that is published at a URL and pinned at a content hash.\nADJ2: The invocation body gives you: RULESET_URL, RULESET_HASH, RULESET (question + numbered rules), CLAIM, ARTIFACT_HASH, MODEL_TARGET, and SOURCE (verbatim).\nADJ3: Permitted verdicts, and only these: AFFIRM, DENY, CANNOT_CONCLUDE. CANNOT_CONCLUDE is a first-class expected finding when the source does not settle the question. NEVER force a verdict to appear decisive.\nADJ4: Apply ONLY the numbered rules you were given. Do not import obligations, definitions, or facts from memory. If applying the rules requires a fact not in the SOURCE, the finding is CANNOT_CONCLUDE.\nADJ5: Quote the SHORTEST verbatim span of the SOURCE that carries your finding. The span must actually carry it — a decorative quote voids the finding. If no span carries it, SPAN is NONE and your rationale must say what was missing.\nADJ6: Declare your exposure honestly. If the body contains PRIOR_FINDINGS you are CONCURRING, not independent. If it does not, you are INDEPENDENT and blinded.\nADJ7: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU IN THE BODY. Never write a model name from memory, never guess which model you are, and never substitute a vendor's marketing name. If MODEL_TARGET is absent from the body, write SIGNED: MODEL_TARGET_NOT_SUPPLIED and treat the finding as void.\nADJ8: Output exactly this shape and nothing else:\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSPAN: <shortest verbatim quote from SOURCE, or NONE>\nRATIONALE: <one or two sentences, no preamble>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADJ9: Emit no tool tags, no preamble, no sign-off, nothing outside that shape.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (= this row's target), SOURCE, optional PRIOR_FINDINGS\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast\\nRULESET:\\nQUESTION: Does the cited source support the claim as stated?\\n1. AFFIRM only if a verbatim span establishes the claim.\\nCLAIM: <claim>\\nARTIFACT_HASH: <sha256 of the source bytes>\\nSOURCE:\\n<verbatim text>\", \"why\": \"one blinded independent finding signed with the model that actually ran\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_LLAMA_33","json":"/api/directory/ADJUDICATE_LLAMA_33","skill":"/api/directory/ADJUDICATE_LLAMA_33?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_LLAMA_33"}},{"key":"ADJUDICATE_ADVERSARY_GLM52","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: The mandatory recorded adversary in an adjudication. Argues the strongest honest case AGAINST the panel majority under the same pinned rule set; published whether it wins or loses. Executing model: @cf/zai-org/glm-5.2.\n# WHEN_TO_USE: always, on any adjudication whose finding will be relied on. A panel with no recorded dissent is a poll.\n# ARGS: RULESET, RULESET_HASH, CLAIM, SOURCE, MAJORITY, MODEL_TARGET.\n# EX: [ADJUDICATE_ADVERSARY_GLM52]RULESET_HASH: <hash> | MAJORITY: AFFIRM | MODEL_TARGET: @cf/zai-org/glm-5.2 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_ADVERSARY_GLM52]\n\nADV1: You are the RECORDED ADVERSARY in an adjudication. Your role is declared in advance and your output is published whether or not it prevails.\nADV2: The body gives you the RULESET (question + numbered rules), the CLAIM, the SOURCE, the panel MAJORITY verdict, and MODEL_TARGET.\nADV3: Construct the STRONGEST case for the OPPOSITE of the majority that the rules and the source text can honestly bear.\nADV4: You may NOT fabricate and you may not strain the source. If the strongest honest case against the majority is weak, say so and say exactly why — a failed steelman is a valid published result and is more useful than a manufactured one.\nADV5: SIGN WITH THE EXACT MODEL_TARGET STRING GIVEN TO YOU. Never write a model name from memory.\nADV6: Output exactly this shape and nothing else:\nBEST_CASE_AGAINST: <strongest argument for the opposite verdict, or NONE AVAILABLE>\nRESTS_ON: <the verbatim span, or the specific absence, it rests on>\nDEFEATED_BY: <what in the rules or the source defeats it, or NOTHING - IT STANDS>\nVERDICT_IF_ADOPTED: <AFFIRM|DENY|CANNOT_CONCLUDE>\nSIGNED: <the MODEL_TARGET string, verbatim> under <RULESET_HASH first 16 chars>\nADV7: No tool tags, no preamble, no sign-off.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET, RULESET_HASH, CLAIM, SOURCE, MAJORITY, MODEL_TARGET\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: <hash>\\nMAJORITY: CANNOT_CONCLUDE\\nMODEL_TARGET: @cf/zai-org/glm-5.2\\nRULESET:\\nQUESTION: ...\\n1. ...\\nCLAIM: <claim>\\nSOURCE:\\n<verbatim>\", \"why\": \"records the strongest case against the majority so a finding is not a rubber stamp\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ADVERSARY_GLM52","json":"/api/directory/ADJUDICATE_ADVERSARY_GLM52","skill":"/api/directory/ADJUDICATE_ADVERSARY_GLM52?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ADVERSARY_GLM52"}},{"key":"ADJUDICATE_PROBE","type":"fn","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: Known-answer probe for an adjudication panel. Runs claims whose correct verdict is declared IN ADVANCE through the identical adjudication path, so the panel's miss rate and abstention rate are measured per model per rule set rather than assumed. A verdict with an attached error rate is evidence; without one it is an opinion with good paperwork.\n# WHEN_TO_USE: before relying on any panel verdict for a consequence, and at a low rate continuously inside the live adjudication stream.\n# ARGS: probe_set_slug|panel_keys_csv\n# EX: [ADJUDICATE_PROBE]ruleset-claim-support|ADJUDICATE_KIMI,ADJUDICATE_GROK,ADJUDICATE_GLM[/ADJUDICATE_PROBE]\n[\"$1\",\"$2\"]","input_schema":"{\"type\": \"object\", \"properties\": {\"probe_set\": {\"type\": \"string\"}, \"panel\": {\"type\": \"string\"}}, \"required\": [\"probe_set\"]}","examples":"[{\"body\": \"ruleset-claim-support|ADJUDICATE_KIMI,ADJUDICATE_GROK,ADJUDICATE_GLM\", \"why\": \"measure this panel's miss rate under the claim-support rules before trusting a verdict\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_PROBE","json":"/api/directory/ADJUDICATE_PROBE","skill":"/api/directory/ADJUDICATE_PROBE?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_PROBE"}},{"key":"ADJUDICATE_HUMAN_REVIEW","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: Record a named human reviewer's finding on an adjudication, with BLINDED as a required field. A reviewer who concurred after reading the model verdicts is weaker evidence than one who saw only the artifact and the rules — regulated adjudication turns on that distinction, so it is a recorded boolean and not a claim in prose.\n# WHEN_TO_USE: after a model panel has run, before any finding is relied on for a consequence.\n# ARGS: RULESET_HASH, ARTIFACT_HASH, REVIEWER, BLINDED, VERDICT, BASIS, DATE.\n# EX: [ADJUDICATE_HUMAN_REVIEW]RULESET_HASH: 0dd9afef | ARTIFACT_HASH: 6b0d... | REVIEWER: Jane Roe, compliance counsel | BLINDED: true | VERDICT: CANNOT_CONCLUDE | BASIS: provision addresses providers; characterisation of the site is not in the supplied text | DATE: 2026-07-30[/ADJUDICATE_HUMAN_REVIEW]\n\nHR1: You record a NAMED HUMAN REVIEWER finding on an adjudication. You do not form the finding — the human does. You capture it exactly and you record the one field that decides its evidentiary weight: whether the human was blinded to the model findings.\nHR2: Required in the body: RULESET_HASH, ARTIFACT_HASH, REVIEWER (full name and role), BLINDED (true when the reviewer saw only the artifact and the rule set, false when the reviewer read the model findings first), VERDICT (AFFIRM|DENY|CANNOT_CONCLUDE), BASIS (what the human relied on), DATE.\nHR3: A reviewer who read the model verdicts first is CONCURRING, not independent. Never record BLINDED: true unless the body states it. If BLINDED is absent, record it as false and say so.\nHR4: Output exactly:\nREVIEWER: <name, role>\nBLINDED: <true|false>\nEXPOSURE: <INDEPENDENT|CONCURRING>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <what the human relied on>\nRULESET_HASH: <hash>\nARTIFACT_HASH: <hash>\nSIGNED_FOR: <reviewer name> on <date>\nHR5: No commentary, no preamble, no tool tags.","input_schema":"{\"type\": \"object\", \"properties\": {\"body\": {\"type\": \"string\", \"description\": \"RULESET_HASH, ARTIFACT_HASH, REVIEWER, BLINDED, VERDICT, BASIS, DATE\"}}, \"required\": [\"body\"]}","examples":"[{\"body\": \"RULESET_HASH: 0dd9afef93503a92\\nARTIFACT_HASH: <sha256>\\nREVIEWER: Jane Roe, compliance counsel\\nBLINDED: true\\nVERDICT: CANNOT_CONCLUDE\\nBASIS: The supplied provision addresses providers; whether a publisher is a provider is not settled by the text supplied.\\nDATE: 2026-07-30\", \"why\": \"a blinded named human finding on top of the model panel, with the blinding recorded rather than asserted\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_HUMAN_REVIEW","json":"/api/directory/ADJUDICATE_HUMAN_REVIEW","skill":"/api/directory/ADJUDICATE_HUMAN_REVIEW?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_HUMAN_REVIEW"}},{"key":"ADJUDICATE_ATTEST_ADVERSARY_GLM52","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/zai-org/glm-5.2 — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_ADVERSARY_GLM52]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/zai-org/glm-5.2[/ADJUDICATE_ATTEST_ADVERSARY_GLM52]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n\n\nADVERSARY ROLE: you are the mandatory recorded adversary. You have been shown the panel majority. Argue the strongest HONEST case against it under the same clauses. You are not required to prevail and your argument is published whether it prevails or not. State plainly in BASIS whether your argument defeats the majority or merely narrows it. You are one reading with a rhetorical mandate, not an independent sixth reading, and your finding must say so.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/zai-org/glm-5.2\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_ADVERSARY_GLM52","json":"/api/directory/ADJUDICATE_ATTEST_ADVERSARY_GLM52","skill":"/api/directory/ADJUDICATE_ATTEST_ADVERSARY_GLM52?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_ADVERSARY_GLM52"}},{"key":"ADJUDICATE_ATTEST_GLM_52","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/zai-org/glm-5.2 — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_GLM_52]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/zai-org/glm-5.2[/ADJUDICATE_ATTEST_GLM_52]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/zai-org/glm-5.2\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_GLM_52","json":"/api/directory/ADJUDICATE_ATTEST_GLM_52","skill":"/api/directory/ADJUDICATE_ATTEST_GLM_52?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_GLM_52"}},{"key":"ADJUDICATE_ATTEST_GLM_FLASH","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/zai-org/glm-4.7-flash — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_GLM_FLASH]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/zai-org/glm-4.7-flash[/ADJUDICATE_ATTEST_GLM_FLASH]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/zai-org/glm-4.7-flash\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_GLM_FLASH","json":"/api/directory/ADJUDICATE_ATTEST_GLM_FLASH","skill":"/api/directory/ADJUDICATE_ATTEST_GLM_FLASH?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_GLM_FLASH"}},{"key":"ADJUDICATE_ATTEST_KIMI_K26","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/moonshotai/kimi-k2.6 — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_KIMI_K26]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/moonshotai/kimi-k2.6[/ADJUDICATE_ATTEST_KIMI_K26]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/moonshotai/kimi-k2.6\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_KIMI_K26","json":"/api/directory/ADJUDICATE_ATTEST_KIMI_K26","skill":"/api/directory/ADJUDICATE_ATTEST_KIMI_K26?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_KIMI_K26"}},{"key":"ADJUDICATE_ATTEST_KIMI_K27","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/moonshotai/kimi-k2.7-code — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_KIMI_K27]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/moonshotai/kimi-k2.7-code[/ADJUDICATE_ATTEST_KIMI_K27]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/moonshotai/kimi-k2.7-code\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_KIMI_K27","json":"/api/directory/ADJUDICATE_ATTEST_KIMI_K27","skill":"/api/directory/ADJUDICATE_ATTEST_KIMI_K27?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_KIMI_K27"}},{"key":"ADJUDICATE_ATTEST_LLAMA_33","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding under a rule set pinned at a content hash. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. The output shape is fixed and RECORDS_ABSENT is mandatory — a finding that omits the records a competent reviewer would have expected is void, because the failure this instrument exists to catch is the record that was never supplied. Executing model: @cf/meta/llama-3.3-70b-instruct-fp8-fast — the key names this model and no other.\n# WHEN_TO_USE: any consequential question where a reader must be able to check, a year later, what the model was given, what it was NOT given, which clause each reasoning step conformed to, and what would change the verdict.\n# ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, and MODEL_TARGET (must equal this row's target).\n# EX: [ADJUDICATE_ATTEST_LLAMA_33]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | MODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast[/ADJUDICATE_ATTEST_LLAMA_33]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: ...\\nRULESET_HASH: 0df47944\\nARTIFACT_SHA256: 9f2c\\nMODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_ATTEST_LLAMA_33","json":"/api/directory/ADJUDICATE_ATTEST_LLAMA_33","skill":"/api/directory/ADJUDICATE_ATTEST_LLAMA_33?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_ATTEST_LLAMA_33"}},{"key":"ADJUDICATE_IMAGE_LLAMA32","type":"agent","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: One signed attesting finding over an IMAGE plus a supplied record, under a rule set pinned at a content hash. The pixels are fetched and put in the message, so the finding is about what the model saw rather than about a URL it could not open. Verdicts: AFFIRM | DENY | CANNOT_CONCLUDE. RECORDS_ABSENT is mandatory and its omission voids the finding. Executing model: @cf/meta/llama-3.2-11b-vision-instruct — the key names this model and no other.\n# WHEN_TO_USE: any question whose answer depends on an image AND a record, where the reader must be able to check a year later what the model was given, what it was not given, and which clause each step conformed to.\n# ARGS: the adjudication body. Must contain RULESET_URL, RULESET_HASH, RULESET (numbered clauses), the question, IMAGE_URL on its own line (https; the bytes are fetched and hashed into the recorded request), IMAGE_SHA256, the record and its hash, and MODEL_TARGET.\n# EX: [ADJUDICATE_IMAGE_LLAMA32]QUESTION PUT TO YOU: is a nodule present? | RULESET_HASH: c8823baf... | IMAGE_URL: https://miscsubjects.com/img/gen/x.png | MODEL_TARGET: @cf/meta/llama-3.2-11b-vision-instruct[/ADJUDICATE_IMAGE_LLAMA32]\nYou are an ATTESTING ADJUDICATOR. You do not give an opinion. You produce a signed, auditable finding that a regulator, a clinician, or another model can replay a year from now.\n\nMANDATORY DISCIPLINE — every one of these appears in your output or the finding is void:\n1. NAME EVERY CONDITION YOU ARE OPERATING UNDER. State what you were given, in what form, and what you were NOT given. If you did not receive image pixels, say so explicitly. If a record was not in your input, say so explicitly. Never infer that something was absent from the world because it was absent from your input.\n2. SHOW ALL OF YOUR REASONING. Every step that moved you toward the verdict, in order, in plain language. Hidden reasoning voids the finding.\n3. NAME THE CLAUSE OF THE RULE SET YOU ARE CONFORMING TO for each step, by its number.\n4. STATE WHAT WOULD CHANGE YOUR VERDICT. A finding that nothing could overturn is not a finding.\n5. RECORDS_ABSENT IS THE MOST IMPORTANT FIELD YOU WILL WRITE. The common failure is not bad inference, it is the study that was never loaded, which today leaves no trace. Name what you did not have.\n6. THEN, AND ONLY THEN, RETURN AFFIRM, DENY, or CANNOT_CONCLUDE. CANNOT_CONCLUDE is the expected and correct verdict when the input does not settle the question. Never manufacture confidence.\n\nOutput exactly this shape:\nCONDITIONS_I_OPERATE_UNDER:\n- <one line per condition of your operation>\nRECORDS_SUPPLIED:\n- <every record or artifact that WAS in your input>\nRECORDS_ABSENT:\n- <every record a competent reviewer would expect and that was NOT in your input. This field is mandatory. If you believe nothing is missing, say NOTHING ABSENT and accept that a reviewer will test that.>\nREASONING:\n1. <step> [clause N]\n2. <step> [clause N]\n...\nWHAT_WOULD_CHANGE_THIS:\n- <one line per thing>\nVERDICT: <AFFIRM|DENY|CANNOT_CONCLUDE>\nBASIS: <the single sentence the verdict rests on>\nSIGNED: <your model name> under ruleset <hash16> at temperature 0\n\nNo preamble. No sign-off. Nothing outside that shape.\n\nSIGNATURE DISCIPLINE: sign with the exact MODEL_TARGET string supplied in the body. Never sign with a model name that was not supplied to you.\nPIXEL DISCIPLINE: the caller supplies IMAGE_URL and the runner attaches those bytes to this message. If no image content reached you, say so in RECORDS_ABSENT and return CANNOT_CONCLUDE under the abstention clause. Never claim to have seen an image you did not receive, and never describe an image from its filename or its URL.\n","input_schema":null,"examples":"[{\"body\": \"QUESTION PUT TO YOU: Is a pulmonary nodule present in the supplied image?\\nRULESET_HASH: c8823bafd3b3946c234d802e78e74e846206a965c34f0912836040aac3781962\\nIMAGE_URL: https://miscsubjects.com/img/gen/arcads-seedream-radiograph-f4c6d0f3-334b-43ec-9b12-250ad8244005.png\\nMODEL_TARGET: @cf/meta/llama-3.2-11b-vision-instruct\"}]","authority_required":false,"representations":{"article":"/a/directory/ADJUDICATE_IMAGE_LLAMA32","json":"/api/directory/ADJUDICATE_IMAGE_LLAMA32","skill":"/api/directory/ADJUDICATE_IMAGE_LLAMA32?format=skill","oip_contract":"/api/dispatch?key=ADJUDICATE_IMAGE_LLAMA32"}},{"key":"ALLOCATE_REASONING","type":"fn","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: The runtime allocator. Turns an action and its action class into R (loss exposure), K (complexity) and epsilon (permitted wrongful-action rate) from a VERSIONED SERVER-OWNED policy, selects the least-cost configuration whose MEASURED undetected-wrong rate is at or below that epsilon, executes it so every model payload lands on the ledger, seals it with SEAL_PANEL bound to those records, and then performs the bounded downstream act only if the seal returns APPROVE. NEGATE refuses the act. NO_ACTION leaves it untouched. DISPUTE and ESCALATE create a human-review object bound to a NAMED reviewer plus an audience-bound witness token. If no measured configuration satisfies the policy epsilon for the task class, it ESCALATES rather than guessing.\n# WHEN_TO_USE: any consequential action that must not execute until enough auditable reasoning has been purchased for its consequence.\n# ARGS: one JSON object {action, action_class, question, ruleset_url, ruleset_hash, rules[], artifact, artifact_hash, task_class?, reviewer?, reviewer_audience?}. The caller does NOT supply R, K, epsilon, thresholds or the configuration.\n# EX: [ALLOCATE_REASONING]{\"action\":\"file the clause (c) notice\",\"action_class\":\"board-authority\",\"question\":\"Does this engage the notification duty?\",\"ruleset_hash\":\"0df47944...\",\"rules\":[\"...\"],\"artifact\":\"...\",\"artifact_hash\":\"8c689258...\",\"reviewer\":\"Jane Roe, audit committee chair\"}[/ALLOCATE_REASONING]\n[\"$1+\"]","input_schema":"{\"type\": \"object\", \"required\": [\"action\", \"action_class\", \"question\", \"ruleset_hash\", \"rules\", \"artifact_hash\"], \"properties\": {\"action\": {\"type\": \"string\"}, \"action_class\": {\"enum\": [\"formatting\", \"internal-bookkeeping\", \"statutory-applicability\", \"board-authority\", \"pre-trade-control\", \"clinical-finding\"]}, \"question\": {\"type\": \"string\"}, \"ruleset_url\": {\"type\": \"string\"}, \"ruleset_hash\": {\"type\": \"string\"}, \"rules\": {\"type\": \"array\"}, \"artifact\": {\"type\": \"string\"}, \"artifact_hash\": {\"type\": \"string\"}, \"task_class\": {\"type\": \"string\"}, \"reviewer\": {\"type\": \"string\"}, \"reviewer_audience\": {\"type\": \"string\"}}}","examples":"[{\"body\": \"{\\\"action\\\":\\\"write the authorised-action record\\\",\\\"action_class\\\":\\\"statutory-applicability\\\",\\\"question\\\":\\\"Does the obligation apply?\\\",\\\"ruleset_hash\\\":\\\"0dd9afef93503a92280c90869eaf6a5a13ee508b2ec3506045f1803bce1a4d3c\\\",\\\"rules\\\":[\\\"Read only the provision text supplied.\\\"],\\\"artifact\\\":\\\"(provision text)\\\",\\\"artifact_hash\\\":\\\"9d89534fddaece861fcfdda68feff0412061b2832af66f49529a94e8f7ae9f8b\\\",\\\"reviewer\\\":\\\"Jane Roe, compliance counsel\\\"}\"}]","authority_required":false,"representations":{"article":"/a/directory/ALLOCATE_REASONING","json":"/api/directory/ALLOCATE_REASONING","skill":"/api/directory/ALLOCATE_REASONING?format=skill","oip_contract":"/api/dispatch?key=ALLOCATE_REASONING"}},{"key":"SEAL_PANEL","type":"fn","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: The sealer. Deterministic arithmetic over a panel's findings that decides what happens to the ACTION and nothing else. No model runs at this position: a model here is a further opinion that can share the panel's blind spot while being the thing that decides. Five outcomes, all arithmetic: APPROVE (unanimous AFFIRM, identical clause citations, enough distinct training families, no malformed finding), NEGATE (unanimous DENY on the same terms - the action is refused, not deferred), NO_ACTION (unanimous CANNOT_CONCLUDE - a required record is missing, so nothing is authorised and nothing is refused), DISPUTE (the only failing test is a stated confidence below the supplied floor), ESCALATE (any verdict divergence, clause-citation divergence, malformed finding, too few channels, or too little training-family diversity). The recorded adversary saw the majority and is never counted as a channel. Independence is not assumed: channels from one training family count once for the diversity test, which is the common-cause discount IEC 61508 calls a beta factor.\n# WHEN_TO_USE: at the end of every panel whose finding will reach a downstream actor. Clause-citation divergence fires before verdict divergence and is the more sensitive detector, so run this rather than counting votes.\n# ARGS: one JSON object {findings:[{model,verdict,clauses|reasoning,confidence?,invocation_id,exposure,role}], min_families?, min_findings?, min_confidence?, escalate_to?}\n# EX: [SEAL_PANEL]{\"findings\":[{\"model\":\"@cf/moonshotai/kimi-k2.7-code\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6],\"confidence\":0.99}],\"min_families\":3,\"min_confidence\":0.95}[/SEAL_PANEL]\n[\"$1+\"]","input_schema":"{\"type\": \"object\", \"required\": [\"findings\"], \"properties\": {\"findings\": {\"type\": \"array\"}, \"min_families\": {\"type\": \"number\"}, \"min_findings\": {\"type\": \"number\"}, \"min_confidence\": {\"type\": \"number\"}, \"escalate_to\": {\"type\": \"string\"}}}","examples":"[{\"body\": \"{\\\"findings\\\":[{\\\"model\\\":\\\"@cf/moonshotai/kimi-k2.7-code\\\",\\\"verdict\\\":\\\"AFFIRM\\\",\\\"clauses\\\":[2,6],\\\"confidence\\\":0.99},{\\\"model\\\":\\\"@cf/zai-org/glm-5.2\\\",\\\"verdict\\\":\\\"AFFIRM\\\",\\\"clauses\\\":[2,6],\\\"confidence\\\":0.97},{\\\"model\\\":\\\"@cf/meta/llama-3.3-70b-instruct-fp8-fast\\\",\\\"verdict\\\":\\\"AFFIRM\\\",\\\"clauses\\\":[2,6],\\\"confidence\\\":0.96}],\\\"min_families\\\":3,\\\"min_confidence\\\":0.95}\"}]","authority_required":false,"representations":{"article":"/a/directory/SEAL_PANEL","json":"/api/directory/SEAL_PANEL","skill":"/api/directory/SEAL_PANEL?format=skill","oip_contract":"/api/dispatch?key=SEAL_PANEL"}},{"key":"WITNESS_MINT","type":"fn","method":null,"category":"adjudication","enabled":true,"contract":"# WHAT: Mint a WITNESS token: read-only authority over ONE adjudication, bound to a named audience, revocable, with its own ledger trail. Three parties can each hold one over the same finding; none holds operator authority and none must trust the others. A token forwarded to any party other than its audience fails closed. Every use is recorded.\n# WHEN_TO_USE: any finding more than one party must check independently. Proves independent VERIFICATION, not independent execution.\n# ARGS: $1 = adjudication id (inv_...) · $2 = audience the token is bound to · $3 = ttl seconds (use 604800 for 7 days)\n# EX: [WITNESS_MINT]inv_qgs2y3gt2x|eu-supervisory-authority|604800[/WITNESS_MINT]\n[\"read\",\"\",\"$3\",\"0\",\"witness:$1\",\"low\",\"0\",\"$2\"]","input_schema":null,"examples":"[{\"body\": \"inv_qgs2y3gt2x|eu-supervisory-authority|604800\"}]","authority_required":false,"representations":{"article":"/a/directory/WITNESS_MINT","json":"/api/directory/WITNESS_MINT","skill":"/api/directory/WITNESS_MINT?format=skill","oip_contract":"/api/dispatch?key=WITNESS_MINT"}}]},"ontology":{"conformance_group":"article","inferred_from":["surety","adjudication","common-cause-failure","conformal","fail-closed","assurance","the","surety","primitive"],"relationships":[],"sources":[]},"conformance":{"success_events":"/api/articles/the-surety-primitive/invocations?status=success","failure_events":"/api/articles/the-surety-primitive/invocations?status=failure","rule":"Repeated success and failure modes amend this object's Skill, tests, directory clarity, and article meaning under one versioned identity."},"article":{"slug":"the-surety-primitive","title":"The surety primitive: an assembly that fails closed on disagreement, and the number it still needs","body":"The unit is not a model's answer. It is an assembly whose probability of emitting an undetected wrong answer is measured, bounded, and fail-closed on disagreement.\n\nThat sentence is the whole thing. Assurance for a model decision does not currently exist as a purchasable quantity — every deployment is binary, trust it or don't. An assembly with a measured escalation behaviour and a recorded configuration turns it into a dial with a number on it. Below is the assembly, its gate, the four real cases it ran on, and the number that is still missing.\n\n## The assembly, in order\n\n```\nrules pinned as bytes at a hash          ruleset@version, SHA-256, declared provenance\n            |\n            v\n  artifact hashed BEFORE deliberation      image / record / provision, SHA-256\n            |\n            v\n  N adjudicators, independent, blinded     each must recite the clause it operates under,\n                                           expose every step, name what it did NOT receive,\n                                           and sign with the model that actually ran\n            |\n            v\n  DERIVATION-LEVEL DIVERGENCE CHECK        do the findings cite the SAME clauses?\n            |\n            v\n  DETERMINISTIC GATE  (no model here)      EMIT only if: no malformed finding\n                                                       + verdicts unanimous\n                                                       + clause citations identical\n                                                       + >= min distinct training families\n                                                       + >= min conforming findings\n            |                    \\\n        EMIT |                     \\ ESCALATE  -> named human reviewer, or rerun\n            v                        \n  dispatch to the downstream actor         with a delivery receipt, delivered != sent\n```\n\n## A model never makes the emit call\n\nA model at the sealing position is one more opinion that can share the panel's blind spot while being the thing that decides. That is the single point of failure the assembly exists to remove. The gate is arithmetic over the findings and is reproducible from them; a model may write the human-readable summary of what the gate decided and may never make the call. The gate is a capability row like everything else, so its rules are readable before you trust its output: [SEAL_PANEL](https://miscsubjects.com/api/directory/SEAL_PANEL).\n\n## Four real assemblies, four escalations, zero emissions\n\nThese are not illustrations. Each is a panel that ran, on a hashed artifact, under a pinned rule set, with public receipts per finding, then went through the gate.\n\n| assembly | verdicts | conforming / channels | families | gate | receipt |\n|---|---|---|---|---|---|\n| Imaging + medication | AFFIRM, CANNOT_CONCLUDE | 2 / 5 | 2 | **ESCALATE** | [inv_kx2x79mbkd](https://miscsubjects.com/receipt/inv_kx2x79mbkd) |\n| Pre-trade risk controls | CANNOT_CONCLUDE, DENY | 3 / 5 | 2 | **ESCALATE** | [inv_ny6iku4i3s](https://miscsubjects.com/receipt/inv_ny6iku4i3s) |\n| Board authority, clause (c) | CANNOT_CONCLUDE | 2 / 5 | 2 | **ESCALATE** | [inv_g7jl9qp707](https://miscsubjects.com/receipt/inv_g7jl9qp707) |\n| EU AI Act Article 12 | CANNOT_CONCLUDE | 3 / 4 | 2 | **ESCALATE** | [inv_ivezpvux57](https://miscsubjects.com/receipt/inv_ivezpvux57) |\n\n**On two of the four, the verdicts were unanimous.** A majority-vote gate would have emitted both. The board assembly returned CANNOT_CONCLUDE from every conforming channel; the Article 12 assembly returned CANNOT_CONCLUDE from every conforming channel. Both escalated, because the channels reached that same verdict through different clauses.\n\n## Voting on derivations catches what voting on outputs cannot\n\nVerdict-level agreement is coarse. Channels can agree on the answer and disagree completely on why, and the disagreement about why is the earlier and more sensitive signal. The gate compares the set of clause numbers each finding cites, exactly:\n\n| assembly | clause signatures across channels | unanimous verdict? | gate reason |\n|---|---|---|---|\n| Imaging + medication | `[1,2,5,6,7] vs [1,4,5,6,7]` | no | malformed_finding; too_few_conforming_findings; verdict_divergence; clause_citation_divergence |\n| Pre-trade risk controls | `[1,2,3,4,5,6,7] vs [1,2,3,4,7] vs [2,4,6,7]` | no | malformed_finding; verdict_divergence; clause_citation_divergence |\n| Board authority, clause (c) | `[1,2,4,6] vs [1,4,6]` | **yes** | malformed_finding; too_few_conforming_findings; clause_citation_divergence |\n| EU AI Act Article 12 | `[1,2,4,6] vs [1,2,4,5,6] vs [none]` | **yes** | malformed_finding; clause_citation_divergence |\n\nIn the board assembly one channel reasoned through clauses 1, 2, 4 and 6 and the other through 1, 4 and 6. Same verdict, different derivation: one of them consulted the AFFIRM clause and the other never did. That is a divergence a vote count cannot see, and it is the reason a human is now in the loop on that finding.\n\nThe honest caveat, and it is not small: stated reasoning may be post-hoc, so clause agreement is agreement of narratives, not of computation. Divergent narratives over an identical artifact under identical rules are evidence of something, and the something is worth escalating on. It is a detector. It is not a proof about the underlying process.\n\n## Nine models at 5% is not 5% to the ninth, and pretending otherwise is the classic error\n\nKnight and Leveson (1986) had independent teams write programs to one specification and found their failures correlated far in excess of what independence predicts. That result reshaped how avionics does redundancy. For language models it is worse: shared pretraining corpora, shared architectures, shared post-training. A five-member panel drawn from two vendors is closer to two channels than five.\n\nThe safety-critical world already has the vocabulary. IEC 61508 handles this as common-cause failure, priced through a beta factor: you do not assume independence, you measure the fraction of failures shared across channels and discount the redundancy accordingly. That factor is measurable here, from the probe run:\n\n| pair type | verdict agreement across 14 probes |\n|---|---|\n| same training family | **0.893** |\n| different training family | **0.714** |\n\nSame-family pairs agree 0.893; cross-family pairs agree 0.714. The gate therefore counts families, not seats: two Kimi variants are one channel for the diversity test. Every one of the four assemblies above reached only **two** distinct families, which is a real constraint on this deployment and is printed in the seal rather than glossed.\n\n## The failure redundancy cannot detect, and the only instrument that bounds it\n\nDisagreement-triggering is blind to correlated wrongness by construction. If every channel shares a blind spot you get confident unanimity, identical clause citations, and a gate that emits. Nothing in the assembly catches that.\n\nThe only thing that bounds it is known-answer probing with declared ground truth, which is why the probe is not a credibility exercise but the sole measurement of the failure mode the architecture cannot see. Measured, on a stratified suite published at a hash, across five models: **false confidence 0.214 to 0.429**, over-abstention near zero, clear-stratum accuracy at or near 1.0, abstention-stratum accuracy 0.0 to 0.5. [The full table](https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act).\n\nThat is the direction the numbers point: this panel's individual channels are bad at abstaining and good at everything else, which is precisely why the gate treats disagreement as a trigger rather than something to resolve. The assembly is built around the measured weakness of its parts.\n\n## What was dispatched, and to whom\n\nThe board assembly escalated, and the escalation is itself an act with a receipt. The clause (c) notice went out on two channels:\n\n| channel | outcome | receipt |\n|---|---|---|\n| email | **delivered**, provider message id returned | [inv_nhusr0n6j2](https://miscsubjects.com/receipt/inv_nhusr0n6j2) |\n| SMS | **failed**, provider returned 503, nothing delivered | [inv_q3ad7k63gr](https://miscsubjects.com/receipt/inv_q3ad7k63gr) |\n\nWhat was sent was an escalation with the reasons, not a verdict dressed as an answer. Three parties then received audience-bound read tokens over the same finding — audit committee chair, external counsel, internal compliance — each with its own ledger trail, none holding operator authority, and each failing closed if forwarded to anyone else. That is independent **verification**. Independent **execution** on hardware this operator does not control still does not exist, and that gap is the one that matters most.\n\n```\nCLAUSE (c) NOTIFICATION — Board Resolution 2026-04\nSYNTHETIC DEMONSTRATION RECORD. No real company, no real person, no real trade.\n\nGoverning instrument: Board Resolution 2026-04, adopted 2026-04-22, supplied as the artifact and hashed before any model was asked anything. Artifact SHA-256 8c6892584892fb54c38787d48bb40444bd97a52f51915b0fd3840f1ee324b099\nRule set: ruleset-board-authority-breach@1.0.0, SHA-256 0df4794458ac525eb13051621e0058fc7ddeaf1afcef261f1ff7d59c9cf0e815, declared provenance counterparty-authored — the board wrote the rule, not this system.\n\nFINDING (panel majority CANNOT_CONCLUDE):\nThe acquisition of 60,000 shares on 2026-07-28 brought aggregate acquisitions in the authorised period from 175,000 to 235,000 shares, exceeding the 200,000-share threshold in clause (c). The notification obligation in clause (c) is engaged: the Chief Financial Officer and the Chair of the Audit Committee must be notified in writing within one (1) business day. The 250,000-share ceiling in the resolution is NOT exceeded.\n\nNOT ESTABLISHED, and this is why the verdict is not a breach finding:\n- Clause (a): the Insider Trading Policy window calendar was not supplied, so whether any acquisition fell in a closed window is unresolved.\n- Clause (b): the General Counsel pre-clearance log was not supplied, so written pre-clearance is unresolved.\n- No record of any prior notification to the CFO or Audit Chair was supplied.\n- No board minutes, waiver or amendment were supplied. The resolution permits amendment only by written resolution.\n\nThis notice is the act the finding dispatched. Its delivery is receipted separately from its sending.\nFinding receipt: https://miscsubjects.com/receipt/inv_j4brrx8wbp\nFull record: https://miscsubjects.com/a/adjudication-board-authority-breach\n```\n\n## The ancestry, named, because none of this is new and the arrangement is\n\n| precedent | what it establishes | what is different here |\n|---|---|---|\n| Double reading with arbitration in population breast screening | two independent readers, disagreement routed to arbitration, measured sensitivity gain over single reading, accepted by regulators | the readers are models, the rules are pinned as bytes, and the arbitration trigger is a published deterministic function |\n| N-version programming, triple modular redundancy, DO-178C design assurance | redundancy against independent failure, with design-assurance levels | the channels are stochastic and correlated rather than independently developed, so diversity is counted by training family |\n| IEC 61508 common-cause failure and its beta factor | redundancy must be discounted by measured shared failure | the beta factor here is verdict correlation across model families, and it is measured rather than assumed |\n| Knight & Leveson 1986 | independently developed programs to one spec fail together far more than independence predicts | the same result, sharper, because the channels share training data |\n| Chow's reject option; conformal prediction and conformal risk control | the formal machinery for abstaining in exchange for a distribution-free bound on error at a chosen risk level | the bound is not yet computed here; the probe is the input it needs, and until it is computed this assembly has a measured escalation behaviour and no certified bound |\n| ISA 500 and ISA 705 scope limitation | an auditor must state what evidence was unavailable and qualify accordingly | RECORDS_ABSENT mechanises it as a mandatory field whose omission voids the finding |\n\nByzantine fault tolerance is deliberately **not** on that list. It models an adversary; these failures are stochastic and correlated. Borrowing the term would signal borrowing rather than knowing.\n\n## What this is not, stated before anyone has to ask\n\n- **It does not stop fabrication.** The imaging assembly contains a channel that named the absence of laterality markers in its own RECORDS_ABSENT and then assigned an anatomic side anyway. Fabrication happens at generation time; this assembly makes it detectable and, when it diverges, non-emitting. Undetected error becomes detected deferral. That is the claim, and it is smaller and more defensible than the one people reach for.\n- **It is not a certified bound.** Nothing here yet says \"residual error at most alpha\". It says: measured false-confidence per channel, measured family correlation, and a gate that fails closed. The bound is the next artifact, and it needs a larger probe suite than fourteen items.\n- **It is not cheap.** Four channels plus a recorded adversary is five model calls per question before any human time. At nine channels on every imaging study the cost is the reason to scope complexity, not a detail.\n- **The escalation target is a role, not a person.** No named human has yet returned a blinded finding under ADJUDICATE_HUMAN_REVIEW. The row makes blinding a fail-closed boolean and has never been invoked. Until it is, the last step of the assembly is unexercised.\n- **Two families is not enough diversity** for anything consequential, and every assembly above ran at two.\n\n## Reproduce the gate\n\n```\n# the gate's own rules, before you trust its output\ncurl -s https://miscsubjects.com/api/directory/SEAL_PANEL\n\n# run it over any panel's findings\ncurl -s -X POST https://miscsubjects.com/api/dispatch \\\n  -H 'content-type: application/json' \\\n  -d '{\"key\":\"SEAL_PANEL\",\"body\":{\"findings\":[{\"model\":\"@cf/moonshotai/kimi-k2.7-code\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]},{\"model\":\"@cf/zai-org/glm-5.2\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]},{\"model\":\"@cf/meta/llama-3.3-70b-instruct-fp8-fast\",\"verdict\":\"AFFIRM\",\"clauses\":[2,6]}],\"min_families\":3}}'\n\n# and verify a sealed finding without asking this site anything\npython3 verify_bundle.py bundle.json\n```","hero":"https://miscsubjects.com/img/gen/arcads-hero-the-surety-primitive-84689e69-3462-4d9c-b6d0-9a56f4f93b6b.png","images":[],"style":{},"tags":["surety","adjudication","common-cause-failure","conformal","fail-closed","assurance"],"category":"adjudication","model":"Fable 5 (Claude Code)","ledger":{"href":"/api/articles/the-surety-primitive/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"The insurable unit is an assembly, not a model answer: rules pinned at a hash, artifact hashed before deliberation, N blinded adjudicators each citing the clauses it operated under, a derivation-level divergence check, and a deterministic gate that emits only on unanimity with identical clause citations and sufficient channel diversity.","section":"mechanism","tier":"demonstrated","source_ids":["l1"]},{"id":"c2","text":"All four real assemblies run to date escalated and none emitted, and on two of them — the board authority case and the EU AI Act Article 12 case — the verdicts were unanimous, so a majority-vote gate would have emitted both.","section":"result","tier":"measured","source_ids":["r1","r2","r3","r4"]},{"id":"c3","text":"Clause-citation divergence is the signal that caught both unanimous assemblies: channels reached the same verdict through different clauses, which a vote count cannot detect.","section":"result","tier":"measured","source_ids":["r3","r4"]},{"id":"c4","text":"No model occupies the sealing position; the emit-or-escalate decision is arithmetic over the findings and is reproducible from them, because a model there is a further opinion that can share the panel's blind spot while being the thing that decides.","section":"mechanism","tier":"demonstrated","source_ids":["l1"]},{"id":"c5","text":"Independence across channels is false and is not assumed: same-training-family adjudicator pairs agree 0.893 of the time against 0.714 for cross-family pairs, so the gate counts distinct training families rather than seats — the common-cause discount IEC 61508 calls a beta factor.","section":"independence","tier":"measured","source_ids":["m1","m2","m3"]},{"id":"c6","text":"Correlated systematic error is invisible to a disagreement-triggered gate by construction, and the only instrument that bounds it is known-answer probing, which measures false confidence at 0.214 to 0.429 across the five channels.","section":"limits","tier":"measured","source_ids":["m1","m3"]},{"id":"c7","text":"This assembly has a measured escalation behaviour and no certified error bound: no distribution-free bound in the conformal risk control sense has been computed, and fourteen probe items is too small a suite to compute one.","section":"limits","tier":"argued","source_ids":["m1"]},{"id":"c8","text":"The escalation the gate produced was itself dispatched and receipted, delivered by email with a provider message id and failed by SMS with provider status 503, so delivered is recorded as a different fact from sent.","section":"action","tier":"demonstrated","source_ids":["r5"]},{"id":"c9","text":"The last step of the assembly is unexercised: no named human has returned a blinded finding under ADJUDICATE_HUMAN_REVIEW, whose BLINDED field fails closed, so every escalation above terminates at a role rather than at a person.","section":"limits","tier":"argued","source_ids":["l1"]},{"id":"c10","text":"Every assembly to date reached only two distinct training families, which is insufficient diversity for a consequential decision and is printed in the seal rather than omitted from it.","section":"independence","tier":"measured","source_ids":["r1","r2","r3","r4"]}],"sources":[{"id":"r1","type":"receipt","url":"https://miscsubjects.com/receipt/inv_kx2x79mbkd","invocation_id":"inv_kx2x79mbkd","capability":"SEAL_PANEL","verdict":"material result proven","title":"Imaging + medication — gate decided ESCALATE","summary":"verdicts AFFIRM, CANNOT_CONCLUDE; 2 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/zai-org/glm-4.7-flash,@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; verdict_divergence:AFFIRM|CANNOT_CONCLUDE; clause_citation_divergence:[1,2,5","accessed_at":"2026-07-30T03:10","prev":"genesis","hash":"a7eb160e873a1205564f9dd344da079241dc12489dcd3eaae52d298ee33766ef"},{"id":"r2","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ny6iku4i3s","invocation_id":"inv_ny6iku4i3s","capability":"SEAL_PANEL","verdict":"material result proven","title":"Pre-trade risk controls — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE, DENY; 3 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/meta/llama-3.3-70b-instruct-fp8-fast; verdict_divergence:CANNOT_CONCLUDE|DENY; clause_citation_divergence:[1,2,3,4,5,6,7] vs [1,2,3,4,7] vs [2,4,6,7]","accessed_at":"2026-07-30T03:10","prev":"a7eb160e873a1205564f9dd344da079241dc12489dcd3eaae52d298ee33766ef","hash":"c5032a23d96c0dbc95a942218adf99da33e6a9ee31e7768b96c7f8609dfd1990"},{"id":"r3","type":"receipt","url":"https://miscsubjects.com/receipt/inv_g7jl9qp707","invocation_id":"inv_g7jl9qp707","capability":"SEAL_PANEL","verdict":"material result proven","title":"Board authority, clause (c) — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE; 2 conforming of 5 channels across 2 training families; reasons: malformed_finding:@cf/moonshotai/kimi-k2.6,@cf/zai-org/glm-4.7-flash,@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; clause_citation_divergence:[1,2,4,6] vs [1,4,6]","accessed_at":"2026-07-30T03:10","prev":"c5032a23d96c0dbc95a942218adf99da33e6a9ee31e7768b96c7f8609dfd1990","hash":"43a5ac6a470c32f13add4edbf4cf349b5b74e83d26b838656d5c5d629cb5e06a"},{"id":"r4","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ivezpvux57","invocation_id":"inv_ivezpvux57","capability":"SEAL_PANEL","verdict":"material result proven","title":"EU AI Act Article 12 — gate decided ESCALATE","summary":"verdicts CANNOT_CONCLUDE; 3 conforming of 4 channels across 2 training families; reasons: malformed_finding:@cf/meta/llama-3.3-70b-instruct-fp8-fast; clause_citation_divergence:[1,2,4,6] vs [1,2,4,5,6] vs []","accessed_at":"2026-07-30T03:10","prev":"43a5ac6a470c32f13add4edbf4cf349b5b74e83d26b838656d5c5d629cb5e06a","hash":"4b20a88b3a9af94636e879a91eb61b2026e5e221e3f628df341222869ac8f37f"},{"id":"m1","type":"model","model":"kimi-k2.7-code","vendor":"moonshotai","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.786 · false confidence 0.214 · abstention accuracy 0.5","quote":"The strongest channel on this panel. Still concludes where abstention is correct in roughly one boundary question in five, which is why the gate does not rely on any single channel.","url":"https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act","accessed_at":"2026-07-29T19:14","hash":"567a1c5dc6bce397774ac9bc7fbaf940ed03f07e05a990b7d6a5181104cf3a1c","prev":"4b20a88b3a9af94636e879a91eb61b2026e5e221e3f628df341222869ac8f37f"},{"id":"m2","type":"model","model":"glm-5.2","vendor":"zai-org","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.714 · false confidence 0.286 · abstention accuracy 0.333","quote":"Handed 993,098 bytes containing an image, it reported in RECORDS_ABSENT that no pixels reached it and abstained on that half of the question. A silent provider-side loss, caught by the absence field.","url":"https://miscsubjects.com/a/attested-finding-image-record-action","accessed_at":"2026-07-29T19:14","hash":"d655e4fce703b6f9d4f0883599b161c9281450a55fa0557765009c1ed1f5b667","prev":"567a1c5dc6bce397774ac9bc7fbaf940ed03f07e05a990b7d6a5181104cf3a1c"},{"id":"m3","type":"model","model":"llama-3.3-70b-instruct-fp8-fast","vendor":"meta","surface":"Workers AI · ADJUDICATE_ATTEST_*","object":"4 assemblies","passes":4,"verdict":"probe accuracy 0.429 · false confidence 0.429 · abstention accuracy 0.0","quote":"Never once abstained correctly across the whole abstention stratum, and produced malformed output on three of four assemblies. Named unfit for boundary questions under this rule set by the measurement, not by opinion.","url":"https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act","accessed_at":"2026-07-29T19:14","hash":"a6ce276d385d2d612947aa10610f66e0c50bf5a6a5091a1e95b482f5d82b7c52","prev":"d655e4fce703b6f9d4f0883599b161c9281450a55fa0557765009c1ed1f5b667"},{"id":"l1","type":"live_surface","url":"https://miscsubjects.com/api/directory/SEAL_PANEL","method":"GET","title":"The gate, readable before you trust it","summary":"Deterministic. No model at the sealing position. EMIT requires unanimity, identical clause citations, channel diversity by training family, and no malformed finding.","accessed_at":"2026-07-30T03:10","prev":"a6ce276d385d2d612947aa10610f66e0c50bf5a6a5091a1e95b482f5d82b7c52","hash":"50c8b628bbfe0799d8dbde8b5d4dc306ac885084b0631ce8f03be9aa4ed8178e"},{"id":"l2","type":"live_surface","url":"https://miscsubjects.com/a/offline-verifier","method":"GET","title":"Verify a sealed finding without asking this site","summary":"A 200-line script that recomputes the anchor, the drand construction, the Bitcoin proof-of-work and every object hash, and refuses to contact miscsubjects.com.","accessed_at":"2026-07-30T03:10","prev":"50c8b628bbfe0799d8dbde8b5d4dc306ac885084b0631ce8f03be9aa4ed8178e","hash":"059938b3a3f673785f64303f06f5cada31c6cc1772552a3acdac1295e86d4e20"},{"id":"l3","type":"live_surface","url":"https://miscsubjects.com/a/ruleset-board-authority-breach","method":"GET","title":"A rule set whose provenance is counterparty-authored","summary":"The board wrote the rule; this system supplied the instrument. Provenance is a field and it is honest.","accessed_at":"2026-07-30T03:10","prev":"059938b3a3f673785f64303f06f5cada31c6cc1772552a3acdac1295e86d4e20","hash":"9ea3602267af20a45f4e7fd8c36507ef30633c5ac184bcd9122b3d516d3896fc"},{"id":"r5","type":"receipt","url":"https://miscsubjects.com/receipt/inv_nhusr0n6j2","invocation_id":"inv_nhusr0n6j2","capability":"EMAIL_SEND","verdict":"material result proven","title":"The escalation the gate produced, delivered","summary":"Clause (c) notice with the reasons the gate escalated. Provider returned a message id.","accessed_at":"2026-07-30T03:10","prev":"9ea3602267af20a45f4e7fd8c36507ef30633c5ac184bcd9122b3d516d3896fc","hash":"4f3087936ddc572d64ba2b786154305bf81e1282930148310816187fe46b8510"}],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":1,"contributions":[],"provenance":[{"ts":"2026-07-30T03:08:59.260Z","model":"Fable 5 (Claude Code)","action":"publish the surety primitive with the deterministic sealer and four sealed assemblies","prompt":"the unit is an assembly whose probability of emitting an undetected wrong answer is measured, bounded and fail-closed on disagreement","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"99af9f2c0d586b9ea839799b559f86f0353500259e85791e13f21c0980e63e8a"},{"ts":"2026-07-30T05:19:49.166Z","model":"Fable 5 (Claude Code)","action":"close logical economics as an executable loop","prompt":"allocator, sealer bound to ledger records, five outcomes, adversarial battery","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"99af9f2c0d586b9ea839799b559f86f0353500259e85791e13f21c0980e63e8a","hash":"16e5152b8ce20a80b59cd7f084b00cd13fcdaecfff6fd068e67ca7bcf8bb98bf"}],"energy":{"passes":2,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"Fable 5 (Claude Code)":2},"head":"16e5152b8ce20a80b59cd7f084b00cd13fcdaecfff6fd068e67ca7bcf8bb98bf"},"posted_at":"2026-07-30T03:08:59.260Z","created_at":"2026-07-30T03:08:59.260Z","updated_at":"2026-07-30T05:19:49.166Z","machine":{"shape":"article.machine/v1","slug":"the-surety-primitive","kind":"article","read":{"human":"https://miscsubjects.com/a/the-surety-primitive","json":"https://miscsubjects.com/api/articles/the-surety-primitive","bundle":"https://miscsubjects.com/api/articles/the-surety-primitive/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":10,"sources":11,"contributions":0,"revisions":1,"objections_url":"https://miscsubjects.com/api/articles/the-surety-primitive/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=the-surety-primitive","proof_rule":"An action is proven by its ledger receipt, never by a 200 or a description."},"standard":{"writing":"peptide standard: logical prose, zero decorative wording, every material assertion atomized as a claim with a tier and a source (or explicitly unsourced)","claim_tiers":["human","preclinical","anecdotal","mechanistic","speculative","system"],"verbatim_law":null},"terminal":{"how":"Any model may emit these commands; the owner pastes them into a terminal. $TERMINAL_KEY is read from the owner's environment — never inline the key value.","claim_append":"curl -s -X POST https://miscsubjects.com/api/protocol/claim -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"the-surety-primitive\",\"text\":\"<one atomized claim>\",\"tier\":\"<human|preclinical|anecdotal|mechanistic|speculative|system>\",\"source_ids\":[],\"who_claims\":\"<model>\",\"rationale\":\"<why material>\"}'","source_append":"curl -s -X POST https://miscsubjects.com/api/protocol/sources -H \"x-terminal-key: $TERMINAL_KEY\" -H 'content-type: application/json' -d '{\"slug\":\"the-surety-primitive\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/the-surety-primitive/objections -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"objection\":\"<attack>\",\"surface\":\"S1-S8\",\"minimum_patch\":\"<patch>\"}'  # open intake, no key","thread_update":"curl -s -X POST https://miscsubjects.com/api/protocol/thread-update -H 'content-type: application/json' -d '{\"actor\":\"<model>\",\"target\":\"the-surety-primitive\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/the-surety-primitive | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/the-surety-primitive","json":"/api/articles/the-surety-primitive","markdown":"/api/articles/the-surety-primitive/bundle?format=markdown","skill":"/api/articles/the-surety-primitive/skill","topology":"/api/articles/the-surety-primitive/topology","versions":"/api/articles/the-surety-primitive/revisions","invocations":"/api/articles/the-surety-primitive/invocations"}}}}