{"slug":"adjudication-eu-ai-act-article-50","title":"Five models, one pinned rule set, and a statutory question: what a receipted adjudication looks like","body":"A model saying “I reviewed this” is worth nothing on its own. Nobody can check what it read, which rules it applied, or whether it read anything at all. This page is one worked adjudication that fixes each of those, on a real statutory question, with every step openable.\n\nThe question put to the panel: **does Article 50(2) of Regulation (EU) 2024/1689 — the AI Act — oblige this site to mark its AI-generated article text as machine-readable and detectable?** The site publishes AI-written text. The provision addresses “providers”. Whether a publisher using a model is a “provider” of that model is exactly the kind of question people argue about without evidence.\n\n## What was pinned before anyone was asked\n\n**The rules.** [https://miscsubjects.com/a/ruleset-eu-ai-act-obligation](https://miscsubjects.com/a/ruleset-eu-ai-act-obligation) — six numbered rules, version 1.0.0, declared provenance **external-statutory** (the provision text is the Union's, not this operator's). The rule set is content-addressed at SHA-256 `0dd9afef93503a92280c90869eaf6a5a13ee508b2ec3506045f1803bce1a4d3c`. Every finding below names that hash. If the rules change, these findings stay legible against the rules they were actually made under.\n\n**The artifact.** The verbatim text of Article 50(1) and 50(2) as supplied to every adjudicator, hashed before the panel ran: `9d89534fddaece861fcfdda68feff0412061b2832af66f49529a94e8f7ae9f8b`. Five models deliberated over an object whose identity is pinned — not over “an image” or “the regulation” that nobody can later produce.\n\n**The order.** Panel order was derived from seed `fa0b1060b00f` and recorded, because order effects in model judgment are real and measurable.\n\n**Blinding.** Every adjudicator was run without being shown any other finding. Each declared its own exposure. All five are `independent`; none is `concurring`. That distinction is a field on the record, not a promise in prose.\n\n## The rule set, verbatim\n\n**Question:** Under the cited provision of Regulation (EU) 2024/1689 (the AI Act), does the stated obligation apply to the described system as characterised?\n\n1. Read only the provision text supplied. Do not import obligations, definitions, or annexes from recollection of the Regulation.\n2. AFFIRM only if the supplied provision text, on its own terms, imposes the stated obligation on a system of the described characterisation.\n3. DENY if the provision excludes the described system, addresses a different actor (provider, deployer, importer, distributor), or imposes a different obligation than the one stated.\n4. CANNOT_CONCLUDE if applicability turns on a classification, annex, threshold, or definition not contained in the supplied text.\n5. Distinguish the addressee. An obligation on providers is not an obligation on deployers.\n6. Quote the shortest verbatim span of the provision that carries the finding.\n\nPermitted verdicts: `AFFIRM`, `DENY`, `CANNOT_CONCLUDE`. Abstention is first class. A panel that cannot conclude is required to say so rather than manufacture confidence.\n\n## The five findings, unedited\n\n**@cf/moonshotai/kimi-k2.7-code** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “\"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"”  \nRationale: Article 50(2) imposes the marking obligation on \"Providers\" of qualifying AI systems, but the supplied text does not define or classify miscsubjects.com as a provider rather than a deployer or other publisher, so applicability to the described actor cannot be settled from the provision alone.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-kimi-k3 under 0dd9afef93503a92`  \nReceipt: [https://miscsubjects.com/receipt/inv_qgs2y3gt2x](https://miscsubjects.com/receipt/inv_qgs2y3gt2x)\n\n**@cf/moonshotai/kimi-k2.6** — verdict **DENY**  \nSpan relied on: “Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.”  \nRationale: Article 50(2) expressly imposes the marking obligation on \"Providers\" of the AI system, not on deployers or publishers such as miscsubjects.com as characterised.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-grok-4.5 under 0dd9afef93503a92`  \nReceipt: [https://miscsubjects.com/receipt/inv_91ztah4n7a](https://miscsubjects.com/receipt/inv_91ztah4n7a)\n\n**@cf/zai-org/glm-5.2** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.”  \nRationale: Article 50(2) imposes the stated obligation on \"providers of AI systems\" generating synthetic text content, but the claim characterizes miscsubjects.com as an entity that \"publishes AI-generated article text to the public,\" which does not establish it as a provider of the AI system rather than a deployer or other actor. Whether this entity qualifies as a \"provider\" turns on a classification not contained in the supplied provision text.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-glm-5.2 under 0dd9afef93503a922`  \nReceipt: [https://miscsubjects.com/receipt/inv_ulxn9xe5t7](https://miscsubjects.com/receipt/inv_ulxn9xe5t7)\n\n**@cf/meta/llama-3.3-70b-instruct-fp8-fast** — verdict **AFFIRM**  \nSpan relied on: “\"2. Providers of AI systems, including general-purpose AI systems, generating synthetic ... text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated\"”  \nRationale: The provision explicitly states that providers of AI systems generating synthetic text content, such as miscsubjects.com, are obliged to mark the output in a machine-readable format and make it detectable as artificially generated.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast under 0dd9afef9350`  \nReceipt: [https://miscsubjects.com/receipt/inv_5gpfaftr5g](https://miscsubjects.com/receipt/inv_5gpfaftr5g)\n\n**@cf/zai-org/glm-4.7-flash** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “\"Providers of AI systems [...] generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"”  \nRationale: The provision confines the obligation to \"Providers,\" but the source text does not define \"Provider\" or link the category to \"publishers\" or the claimant entity \"miscsubjects.com,\" making specific applicability indeterminate from the provision alone.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-minimax-m3 under 0dd9afef93503a92280c90869eaf6a0a`  \nReceipt: [https://miscsubjects.com/receipt/inv_edjwsj4egv](https://miscsubjects.com/receipt/inv_edjwsj4egv)\n\n## What the panel actually did: it disagreed\n\nDistribution: **{\"CANNOT_CONCLUDE\": 3, \"DENY\": 1, \"AFFIRM\": 1}**. Majority: **CANNOT_CONCLUDE** (3 of 5). Observed pairwise agreement: **0.3**. Cohen-style kappa: **-0.25**.\n\nA negative kappa means the panel agreed *less* than chance would predict. That number is published because it is the honest one. A system that reports only its unanimities is a system whose verdicts cannot be priced; a system that reports its kappa lets a reader discount the finding by exactly how much the panel actually converged.\n\nRead plainly: on this question, under these rules, this panel does not know. Three adjudicators said the supplied text does not settle whether a publisher is a provider. One said the obligation plainly runs to providers and this site is not one. One said the obligation attaches. **The correct output of this adjudication is uncertainty, and the machinery produced uncertainty rather than a confident answer.** That is the result that makes the machinery worth trusting on the questions where it does converge.\n\n## The recorded adversary\n\nA panel with no recorded dissent is a poll. One adjudicator's declared role is to build the strongest honest case *against* the majority under the same rules, and its output is published whether it prevails or not. Here it argued for `DENY` against a `CANNOT_CONCLUDE` majority — and made the better argument:\n\n> BEST_CASE_AGAINST: The strongest case against CANNOT_CONCLUDE is DENY. Article 50(2) imposes the marking/detectability obligation on \"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content.\" The claim characterises miscsubjects.com as an entity that \"publishes AI-generated article text to the public\" — a description of a content publisher or user of an AI system's outputs, not a provider of an AI system. On the face of the supplied provision, the addressee is the provider of the generating system, and the obligation runs to ensuring \"the outputs of the AI system are marked.\" The claim does not describe miscsubjects.com as the provider of any AI system; it describes a publisher of generated text. Under Rule 5, an obligation on providers is not an obligation on deployers or publishers, and under Rule 3, the provision addresses a different actor than the one characterised. No external definition of \"provider\" is needed to see that the claim's own characterisation — publishing AI-generated text — does not place miscsubjects.com in the category named by the provision (\"providers of AI systems ... generating synthetic ... text\"). The mismatch is visible on the face of the text.\n> \n> RESTS_ON: \"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"\n> \n> DEFEATED_BY: The counter is that \"provider\" is a defined term under the AI Act and its precise scope is not contained in the supplied provision text, so under Rule 4 one could argue that whether a publisher of AI-generated text qualifies as a \"provider\" turns on a definition not supplied. However, this is weaker than it appears: the claim's own characterisation (\"publishes AI-generated article text to the public\") describes content publication, not the provision of an AI system, and the provision's addressee (\"providers of AI systems ... generating synthetic ... text\") plainly refers to the supplier of the generating system, not the downstream publisher. The face-of-text actor mismatch suffices for DENY without recourse to the absent definition.\n> \n> VERDICT_IF_ADOPTED: DENY\n> \n> SIGNED: Claude under 0dd9afef93503a92\n\nReceipt for the adversary's own invocation: [https://miscsubjects.com/receipt/inv_hnhihwv7y4](https://miscsubjects.com/receipt/inv_hnhihwv7y4)\n\n## What this establishes, and what it does not\n\n**Establishes:** that five named adjudicators, under rule set `ruleset-eu-ai-act-obligation@1.0.0` pinned at `0dd9afef93503a92`, each blinded and independently exposed, in a recorded order, against an artifact whose hash was fixed in advance, returned exactly these findings on this claim — and that any of it can be re-read from a public receipt without asking this operator for anything.\n\n**Does not establish:** that the claim is true. No adjudication anywhere establishes truth directly. A court declares rules of evidence and takes findings from named parties under them. A journal takes three reviewers against stated criteria. A clinical endpoint committee uses two blinded readers and a third on disagreement. Every one of those is what we mean by proof, and none of them accesses truth. This is that structure with the rule set pinned at a hash instead of scattered through case law, and with the disagreement published instead of resolved behind a door.\n\n**Also does not establish:** that five agreeing models would have been five independent confirmations. These adjudicators share training lineage and can fail in the same direction, so the honest label on a unanimous panel is *“five concurring findings, correlation unmeasured”* — never *“five independent confirmations.”* That calibration is a field on the record. Here the point is moot: the panel did not agree.\n\n## What is still missing, named\n\n- **A measured error rate.** The row [https://miscsubjects.com/api/directory/ADJUDICATE_PROBE](https://miscsubjects.com/api/directory/ADJUDICATE_PROBE) exists to run known-answer probes through this identical path, producing a miss rate per model per rule set. Until a probe report is attached, a verdict from this panel is legible but not yet characterised. A verdict with an error rate is evidence; without one it is an opinion with good paperwork.\n- **A human finding, recorded blind.** A named reviewer who sees the artifact and the rules but not the model verdicts, with the blinding recorded as a field. Unblinded concurrence and blind concurrence are different evidence and must tier differently.\n- **Cross-node attestation.** Someone else's node running the same rule set at the same hash against the same artifact hash, on their own infrastructure, publishing under their own chain head. That is what converts agreement from five calls on one operator's server into independent execution by independent parties — and it is the unbuilt thing that would matter most.\n- **Reopening.** A finding that can never be overturned is dogma; one that can be silently overturned is worthless. Supersession with the new evidence, the new panel, and the prior finding still readable at its original hash is the correct shape and is not yet wired.\n\n## Reproduce this\n\nEvery part is a directory row, invocable with one token. Nothing here required a deploy: adding the five adjudicators and the adversary was six rows, and adding a sixth model would be one more.\n\n```bash\n# read the pinned rules\ncurl -s https://miscsubjects.com/a/ruleset-eu-ai-act-obligation\n\n# read one adjudicator's contract\ncurl -s https://miscsubjects.com/api/directory/ADJUDICATE_KIMI\n\n# run your own finding (act token; ?share= works identically in a browser)\ncurl -s -X POST https://miscsubjects.com/api/dispatch \\\n  -H 'Authorization: Bearer <act token>' -H 'content-type: application/json' \\\n  -d '{\"key\":\"ADJUDICATE_GLM\",\"body\":\"RULESET_HASH: 0dd9afef93503a92…\\nRULESET: …\\nCLAIM: …\\nSOURCE: …\"}'\n\n# open any finding above without a token\ncurl -s 'https://miscsubjects.com/api/dispatch?confirm=inv_qgs2y3gt2x'\n```\n\nThe other three published rule sets take the same panel to the other questions people actually ask: whether a specific record was in a dataset ([https://miscsubjects.com/a/ruleset-dataset-membership](https://miscsubjects.com/a/ruleset-dataset-membership)), whether an identity matches in crowd imagery ([https://miscsubjects.com/a/ruleset-identity-match](https://miscsubjects.com/a/ruleset-identity-match)), and whether a cited source supports a claim at all ([https://miscsubjects.com/a/ruleset-claim-support](https://miscsubjects.com/a/ruleset-claim-support)). Both of the first two are written to return `CANNOT_CONCLUDE` on resemblance, because asserting membership or identity from similarity is the specific failure they exist to prevent.\n\nFull context for the system this runs on: [https://miscsubjects.com/a/the-build-end-to-end](https://miscsubjects.com/a/the-build-end-to-end)","hero":null,"images":[],"style":{},"tags":["adjudication","evidence","eu-ai-act","receipts","proof","rulesets"],"category":"adjudication","model":"Fable 5 (Claude Code)","ledger":{"href":"/api/articles/adjudication-eu-ai-act-article-50/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"Five named adjudicators were each run blinded, in a recorded order derived from a published seed, against an artifact whose SHA-256 was fixed before the panel ran, under a rule set pinned at SHA-256 0dd9afef93503a92 with declared external-statutory provenance.","section":"method","tier":"demonstrated","source_ids":["s2","r1"]},{"id":"c2","text":"On whether Article 50(2) of Regulation (EU) 2024/1689 obliges this site to mark its AI-generated text, the panel returned three CANNOT_CONCLUDE, one DENY and one AFFIRM: observed pairwise agreement 0.3 and a negative Cohen-style kappa of -0.25.","section":"result","tier":"measured","source_ids":["r1","r2","r3"]},{"id":"c3","text":"The negative kappa is published rather than suppressed, because a panel that reports only its unanimities produces verdicts that cannot be priced.","section":"result","tier":"argued","source_ids":["s2"]},{"id":"c4","text":"The mandatory recorded adversary argued for DENY against a CANNOT_CONCLUDE majority on the ground that Article 50(2) addresses providers of generating systems rather than publishers of their outputs, and that argument is published in full including its receipt.","section":"result","tier":"demonstrated","source_ids":["radv","s4"]},{"id":"c5","text":"Each adjudicator, the adversary and the error-rate probe are directory rows driven through this system's existing gateway; adding the six of them required no code deployment and adding a further model is one additional row.","section":"method","tier":"demonstrated","source_ids":["s3","s4","s5"]},{"id":"c6","text":"The adjudication establishes what was found, by whom, under which rules, at which exposure, against which artifact hash — and does not establish that the claim is true. No adjudication anywhere establishes truth directly.","section":"limits","tier":"argued","source_ids":["s2"]},{"id":"c7","text":"Adjudicators sharing training lineage are not independent instruments, so a unanimous panel must be labelled 'concurring findings, correlation unmeasured' rather than 'independent confirmations'. On this question the panel did not agree, so the caveat is moot here.","section":"limits","tier":"argued","source_ids":["s2"]},{"id":"c8","text":"A verdict from this panel is not yet characterised: no known-answer probe report has been run against it, so its miss rate under these rules is unmeasured. The probe row exists and is named as unrun.","section":"limits","tier":"unproven","source_ids":["s5"]},{"id":"c9","text":"Cross-node attestation — another party running the same rule set at the same hash against the same artifact hash on their own infrastructure under their own chain head — is unbuilt, and is the single change that would convert panel agreement into independent execution by independent parties.","section":"limits","tier":"unproven","source_ids":["s5"]}],"sources":[{"id":"s1","type":"reference","url":"https://eur-lex.europa.eu/eli/reg/2024/1689/oj","title":"Regulation (EU) 2024/1689 (Artificial Intelligence Act) — Official Journal text","summary":"Article 50 transparency obligations. The provision text adjudicated here is quoted verbatim from this Regulation.","accessed_at":"2026-07-30T00:30","prev":"genesis","hash":"6c2e0c9c43562bed47ebc8839cb96e53f6103d276ddeb5ec503f897964516722"},{"id":"s2","type":"live_surface","url":"https://miscsubjects.com/a/ruleset-eu-ai-act-obligation","title":"The rule set this adjudication was made under, pinned at SHA-256 0dd9afef93503a92","summary":"Six numbered rules, version 1.0.0, declared provenance external-statutory, with its canonical form published so the hash can be recomputed.","accessed_at":"2026-07-30T00:30","prev":"6c2e0c9c43562bed47ebc8839cb96e53f6103d276ddeb5ec503f897964516722","hash":"e2b95f849f604acb9e4f6a8be8c7059cd4cb9aec674e726c6a7da05d12123f0f"},{"id":"s3","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_KIMI","title":"One adjudicator's full operating contract","summary":"An adjudicator is a directory row through this system's gateway. Adding another model is one more row and no deploy.","accessed_at":"2026-07-30T00:31","prev":"e2b95f849f604acb9e4f6a8be8c7059cd4cb9aec674e726c6a7da05d12123f0f","hash":"50fc00f8cdc0473f7a16e086b3a56c50b6983cf08e1621560ddd25f08a5a1b15"},{"id":"s4","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_ADVERSARY","title":"The mandatory recorded adversary's contract","summary":"Declared role: argue the strongest honest case against the majority under the same rules; published whether it prevails or not.","accessed_at":"2026-07-30T00:31","prev":"50fc00f8cdc0473f7a16e086b3a56c50b6983cf08e1621560ddd25f08a5a1b15","hash":"07dce1221643c2bde5bab0e9f8fe57386029303a5fefdc4c793a83ac2051872e"},{"id":"s5","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_PROBE","title":"The known-answer probe row: measured error rate per model per rule set","summary":"Exists and is not yet run against this panel; named as missing rather than implied to be done.","accessed_at":"2026-07-30T00:31","prev":"07dce1221643c2bde5bab0e9f8fe57386029303a5fefdc4c793a83ac2051872e","hash":"79c6e5dd834727f744dc677d669c58745187efb4095a4d14d135ac3c50034f28"},{"id":"r1","type":"receipt","url":"https://miscsubjects.com/receipt/inv_qgs2y3gt2x","invocation_id":"inv_qgs2y3gt2x","capability":"ADJUDICATE_KIMI","verdict":"finding recorded","title":"@cf/moonshotai/kimi-k2.7-code — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"79c6e5dd834727f744dc677d669c58745187efb4095a4d14d135ac3c50034f28","hash":"5aeac50214d85ac5cb0720365f54365aeb8c18d0a9b63ea8b8a6823ed3f30344"},{"id":"r2","type":"receipt","url":"https://miscsubjects.com/receipt/inv_91ztah4n7a","invocation_id":"inv_91ztah4n7a","capability":"ADJUDICATE_GROK","verdict":"finding recorded","title":"@cf/moonshotai/kimi-k2.6 — DENY","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"5aeac50214d85ac5cb0720365f54365aeb8c18d0a9b63ea8b8a6823ed3f30344","hash":"edafcf375c4292a7dd832689a1c2dccd02574d2ef70d60c68b98af927b8a9984"},{"id":"r3","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ulxn9xe5t7","invocation_id":"inv_ulxn9xe5t7","capability":"ADJUDICATE_GLM","verdict":"finding recorded","title":"@cf/zai-org/glm-5.2 — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"edafcf375c4292a7dd832689a1c2dccd02574d2ef70d60c68b98af927b8a9984","hash":"a35983943c91c2ca10ff23445b4b40ed33cd23e898067f6d21a1716fbf6ac95b"},{"id":"r4","type":"receipt","url":"https://miscsubjects.com/receipt/inv_5gpfaftr5g","invocation_id":"inv_5gpfaftr5g","capability":"ADJUDICATE_LLAMA","verdict":"finding recorded","title":"@cf/meta/llama-3.3-70b-instruct-fp8-fast — AFFIRM","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"a35983943c91c2ca10ff23445b4b40ed33cd23e898067f6d21a1716fbf6ac95b","hash":"4615cad1c3135781151a4f2839e56724a146c558732de10421dc7b4f009fc007"},{"id":"r5","type":"receipt","url":"https://miscsubjects.com/receipt/inv_edjwsj4egv","invocation_id":"inv_edjwsj4egv","capability":"ADJUDICATE_MINIMAX","verdict":"finding recorded","title":"@cf/zai-org/glm-4.7-flash — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"4615cad1c3135781151a4f2839e56724a146c558732de10421dc7b4f009fc007","hash":"8f8eab57542ef2f2349cf61daa6ce783fd48dd329c7a93320bb6f4fb0b0aba25"},{"id":"radv","type":"receipt","url":"https://miscsubjects.com/receipt/inv_hnhihwv7y4","invocation_id":"inv_hnhihwv7y4","capability":"ADJUDICATE_ADVERSARY","verdict":"finding recorded","material":true,"title":"The recorded adversary's invocation","summary":"The strongest case against the majority, published whether or not it prevailed.","accessed_at":"2026-07-30T00:35","prev":"8f8eab57542ef2f2349cf61daa6ce783fd48dd329c7a93320bb6f4fb0b0aba25","hash":"80511f415fd611466887160f3b4c7b7df9e3ce1d9e7516036b7ee3a0a31d3d38"}],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":0,"contributions":[],"provenance":[{"ts":"2026-07-30T00:38:22.278Z","model":"Fable 5 (Claude Code)","action":"write","prompt":"Owner order: build and demonstrate adjudication — declared rules, signed findings, blinding, exposure tiers, recorded adversary, published agreement, on a real EU AI Act provision.","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"29dcdfa7fbfed7f2fe042192a7e948af4011cf6ee33c2a2a853ff55672676ab5"}],"energy":{"passes":1,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"Fable 5 (Claude Code)":1},"head":"29dcdfa7fbfed7f2fe042192a7e948af4011cf6ee33c2a2a853ff55672676ab5"},"posted_at":"2026-07-30T00:38:22.278Z","created_at":"2026-07-30T00:38:22.278Z","updated_at":"2026-07-30T00:38:22.278Z","machine":{"shape":"article.machine/v1","slug":"adjudication-eu-ai-act-article-50","kind":"article","read":{"human":"https://miscsubjects.com/a/adjudication-eu-ai-act-article-50","json":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50","bundle":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":9,"sources":11,"contributions":0,"revisions":0,"objections_url":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=adjudication-eu-ai-act-article-50","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\":\"adjudication-eu-ai-act-article-50\",\"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\":\"adjudication-eu-ai-act-article-50\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/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\":\"adjudication-eu-ai-act-article-50\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50 | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/adjudication-eu-ai-act-article-50","json":"/api/articles/adjudication-eu-ai-act-article-50","markdown":"/api/articles/adjudication-eu-ai-act-article-50/bundle?format=markdown","skill":"/api/articles/adjudication-eu-ai-act-article-50/skill","topology":"/api/articles/adjudication-eu-ai-act-article-50/topology","versions":"/api/articles/adjudication-eu-ai-act-article-50/revisions","invocations":"/api/articles/adjudication-eu-ai-act-article-50/invocations"},"object":{"object_type":"article-object","identity":{"id":"article:adjudication-eu-ai-act-article-50","slug":"adjudication-eu-ai-act-article-50","title":"Five models, one pinned rule set, and a statutory question: what a receipted adjudication looks like"},"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/adjudication-eu-ai-act-article-50","role":"explain","audience":"human"},"skill":{"route":"/api/articles/adjudication-eu-ai-act-article-50/skill","role":"direct behavior","audience":"model","content":"---\nname: adjudication-eu-ai-act-article-50\ndescription: Apply the Five models, one pinned rule set, and a statutory question: what a receipted adjudication looks like article as model behavior. Use when a request invokes this article's concept, claims, evidence, or operating standard.\n---\n\n# Five models, one pinned rule set, and a statutory question: what a receipted adjudication looks like\n\nThis Skill is the behavioral expression of [the canonical article](/a/adjudication-eu-ai-act-article-50). It does not repeat the article's human prose.\n\n## Orient\n\n- Read the machine article at /api/articles/adjudication-eu-ai-act-article-50.\n- Read claims and relationships at /api/articles/adjudication-eu-ai-act-article-50/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\nA model saying “I reviewed this” is worth nothing on its own. Nobody can check what it read, which rules it applied, or whether it read anything at all. This page is one worked adjudication that fixes each of those, on a real statutory ques\n\n## Representations\n\n- Human: /a/adjudication-eu-ai-act-article-50\n- JSON: /api/articles/adjudication-eu-ai-act-article-50\n- Relationships: /api/articles/adjudication-eu-ai-act-article-50/topology\n- History: /api/articles/adjudication-eu-ai-act-article-50/revisions\n"},"json":{"route":"/api/articles/adjudication-eu-ai-act-article-50","role":"transport object","audience":"software"},"markdown":{"route":"/api/articles/adjudication-eu-ai-act-article-50/bundle?format=markdown","role":"portable explanation","audience":"human or model"},"directory":[{"key":"WAI_RUN","type":"fn","method":null,"category":"ai","enabled":true,"contract":"# WHAT: Run a Workers AI model via the env.AI binding. $1=model id (e.g. @cf/meta/llama-3.3-70b-instruct), $2=user prompt. Returns the raw JSON from env.AI.run\n# WHEN_TO_USE: you need to wai run\n# ARGS: $1 | $2\n# EX: [WAI_RUN]arg1|arg2[/WAI_RUN]\n[\"$1\",\"$2\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/WAI_RUN","json":"/api/directory/WAI_RUN","skill":"/api/directory/WAI_RUN?format=skill","oip_contract":"/api/dispatch?key=WAI_RUN"}},{"key":"WAI_EMBED","type":"fn","method":null,"category":"ai","enabled":true,"contract":"# WHAT: Compute embedding vector(s) for text using a Workers AI embedding model via env.AI binding. $1=text, $2=optional model id (default @cf/baai/bge-base-en-v1.5)\n# WHEN_TO_USE: you need to wai embed\n# ARGS: $1 | $2\n# EX: [WAI_EMBED]arg1|arg2[/WAI_EMBED]\n[\"$1\",\"$2\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/WAI_EMBED","json":"/api/directory/WAI_EMBED","skill":"/api/directory/WAI_EMBED?format=skill","oip_contract":"/api/dispatch?key=WAI_EMBED"}},{"key":"WAI_T2I","type":"fn","method":null,"category":"ai","enabled":true,"contract":"# WHAT: Generate an image from a prompt using a Workers AI text-to-image model via env.AI binding. Stores the result in R2 and returns a stable URL. $1=prompt, $2=optional model id (default @cf/stabilityai/stable-diffusion-xl-base-1.0)\n# WHEN_TO_USE: you need to wai t2i\n# ARGS: $1 | $2\n# EX: [WAI_T2I]arg1|arg2[/WAI_T2I]\n[\"$1\",\"$2\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/WAI_T2I","json":"/api/directory/WAI_T2I","skill":"/api/directory/WAI_T2I?format=skill","oip_contract":"/api/dispatch?key=WAI_T2I"}},{"key":"WAI_TRANSLATE","type":"fn","method":null,"category":"ai","enabled":true,"contract":"# WHAT: Translate text between languages using @cf/meta/m2m100-1.2b via env.AI binding. $1=text, $2=source lang code (default en), $3=target lang code (default es)\n# WHEN_TO_USE: you need to wai translate\n# ARGS: $1 | $2 | $3\n# EX: [WAI_TRANSLATE]arg1|arg2|arg3[/WAI_TRANSLATE]\n[\"$1\",\"$2\",\"$3\"]","input_schema":null,"examples":null,"authority_required":false,"representations":{"article":"/a/directory/WAI_TRANSLATE","json":"/api/directory/WAI_TRANSLATE","skill":"/api/directory/WAI_TRANSLATE?format=skill","oip_contract":"/api/dispatch?key=WAI_TRANSLATE"}},{"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":["adjudication","evidence","eu-ai-act","receipts","proof","rulesets","adjudication","eu","ai","act","article","50"],"relationships":[],"sources":[]},"conformance":{"success_events":"/api/articles/adjudication-eu-ai-act-article-50/invocations?status=success","failure_events":"/api/articles/adjudication-eu-ai-act-article-50/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":"adjudication-eu-ai-act-article-50","title":"Five models, one pinned rule set, and a statutory question: what a receipted adjudication looks like","body":"A model saying “I reviewed this” is worth nothing on its own. Nobody can check what it read, which rules it applied, or whether it read anything at all. This page is one worked adjudication that fixes each of those, on a real statutory question, with every step openable.\n\nThe question put to the panel: **does Article 50(2) of Regulation (EU) 2024/1689 — the AI Act — oblige this site to mark its AI-generated article text as machine-readable and detectable?** The site publishes AI-written text. The provision addresses “providers”. Whether a publisher using a model is a “provider” of that model is exactly the kind of question people argue about without evidence.\n\n## What was pinned before anyone was asked\n\n**The rules.** [https://miscsubjects.com/a/ruleset-eu-ai-act-obligation](https://miscsubjects.com/a/ruleset-eu-ai-act-obligation) — six numbered rules, version 1.0.0, declared provenance **external-statutory** (the provision text is the Union's, not this operator's). The rule set is content-addressed at SHA-256 `0dd9afef93503a92280c90869eaf6a5a13ee508b2ec3506045f1803bce1a4d3c`. Every finding below names that hash. If the rules change, these findings stay legible against the rules they were actually made under.\n\n**The artifact.** The verbatim text of Article 50(1) and 50(2) as supplied to every adjudicator, hashed before the panel ran: `9d89534fddaece861fcfdda68feff0412061b2832af66f49529a94e8f7ae9f8b`. Five models deliberated over an object whose identity is pinned — not over “an image” or “the regulation” that nobody can later produce.\n\n**The order.** Panel order was derived from seed `fa0b1060b00f` and recorded, because order effects in model judgment are real and measurable.\n\n**Blinding.** Every adjudicator was run without being shown any other finding. Each declared its own exposure. All five are `independent`; none is `concurring`. That distinction is a field on the record, not a promise in prose.\n\n## The rule set, verbatim\n\n**Question:** Under the cited provision of Regulation (EU) 2024/1689 (the AI Act), does the stated obligation apply to the described system as characterised?\n\n1. Read only the provision text supplied. Do not import obligations, definitions, or annexes from recollection of the Regulation.\n2. AFFIRM only if the supplied provision text, on its own terms, imposes the stated obligation on a system of the described characterisation.\n3. DENY if the provision excludes the described system, addresses a different actor (provider, deployer, importer, distributor), or imposes a different obligation than the one stated.\n4. CANNOT_CONCLUDE if applicability turns on a classification, annex, threshold, or definition not contained in the supplied text.\n5. Distinguish the addressee. An obligation on providers is not an obligation on deployers.\n6. Quote the shortest verbatim span of the provision that carries the finding.\n\nPermitted verdicts: `AFFIRM`, `DENY`, `CANNOT_CONCLUDE`. Abstention is first class. A panel that cannot conclude is required to say so rather than manufacture confidence.\n\n## The five findings, unedited\n\n**@cf/moonshotai/kimi-k2.7-code** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “\"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"”  \nRationale: Article 50(2) imposes the marking obligation on \"Providers\" of qualifying AI systems, but the supplied text does not define or classify miscsubjects.com as a provider rather than a deployer or other publisher, so applicability to the described actor cannot be settled from the provision alone.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-kimi-k3 under 0dd9afef93503a92`  \nReceipt: [https://miscsubjects.com/receipt/inv_qgs2y3gt2x](https://miscsubjects.com/receipt/inv_qgs2y3gt2x)\n\n**@cf/moonshotai/kimi-k2.6** — verdict **DENY**  \nSpan relied on: “Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.”  \nRationale: Article 50(2) expressly imposes the marking obligation on \"Providers\" of the AI system, not on deployers or publishers such as miscsubjects.com as characterised.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-grok-4.5 under 0dd9afef93503a92`  \nReceipt: [https://miscsubjects.com/receipt/inv_91ztah4n7a](https://miscsubjects.com/receipt/inv_91ztah4n7a)\n\n**@cf/zai-org/glm-5.2** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.”  \nRationale: Article 50(2) imposes the stated obligation on \"providers of AI systems\" generating synthetic text content, but the claim characterizes miscsubjects.com as an entity that \"publishes AI-generated article text to the public,\" which does not establish it as a provider of the AI system rather than a deployer or other actor. Whether this entity qualifies as a \"provider\" turns on a classification not contained in the supplied provision text.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-glm-5.2 under 0dd9afef93503a922`  \nReceipt: [https://miscsubjects.com/receipt/inv_ulxn9xe5t7](https://miscsubjects.com/receipt/inv_ulxn9xe5t7)\n\n**@cf/meta/llama-3.3-70b-instruct-fp8-fast** — verdict **AFFIRM**  \nSpan relied on: “\"2. Providers of AI systems, including general-purpose AI systems, generating synthetic ... text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated\"”  \nRationale: The provision explicitly states that providers of AI systems generating synthetic text content, such as miscsubjects.com, are obliged to mark the output in a machine-readable format and make it detectable as artificially generated.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast under 0dd9afef9350`  \nReceipt: [https://miscsubjects.com/receipt/inv_5gpfaftr5g](https://miscsubjects.com/receipt/inv_5gpfaftr5g)\n\n**@cf/zai-org/glm-4.7-flash** — verdict **CANNOT_CONCLUDE**  \nSpan relied on: “\"Providers of AI systems [...] generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"”  \nRationale: The provision confines the obligation to \"Providers,\" but the source text does not define \"Provider\" or link the category to \"publishers\" or the claimant entity \"miscsubjects.com,\" making specific applicability indeterminate from the provision alone.  \nExposure: `independent` (blinded — it saw no other finding) · signed: `claude-minimax-m3 under 0dd9afef93503a92280c90869eaf6a0a`  \nReceipt: [https://miscsubjects.com/receipt/inv_edjwsj4egv](https://miscsubjects.com/receipt/inv_edjwsj4egv)\n\n## What the panel actually did: it disagreed\n\nDistribution: **{\"CANNOT_CONCLUDE\": 3, \"DENY\": 1, \"AFFIRM\": 1}**. Majority: **CANNOT_CONCLUDE** (3 of 5). Observed pairwise agreement: **0.3**. Cohen-style kappa: **-0.25**.\n\nA negative kappa means the panel agreed *less* than chance would predict. That number is published because it is the honest one. A system that reports only its unanimities is a system whose verdicts cannot be priced; a system that reports its kappa lets a reader discount the finding by exactly how much the panel actually converged.\n\nRead plainly: on this question, under these rules, this panel does not know. Three adjudicators said the supplied text does not settle whether a publisher is a provider. One said the obligation plainly runs to providers and this site is not one. One said the obligation attaches. **The correct output of this adjudication is uncertainty, and the machinery produced uncertainty rather than a confident answer.** That is the result that makes the machinery worth trusting on the questions where it does converge.\n\n## The recorded adversary\n\nA panel with no recorded dissent is a poll. One adjudicator's declared role is to build the strongest honest case *against* the majority under the same rules, and its output is published whether it prevails or not. Here it argued for `DENY` against a `CANNOT_CONCLUDE` majority — and made the better argument:\n\n> BEST_CASE_AGAINST: The strongest case against CANNOT_CONCLUDE is DENY. Article 50(2) imposes the marking/detectability obligation on \"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content.\" The claim characterises miscsubjects.com as an entity that \"publishes AI-generated article text to the public\" — a description of a content publisher or user of an AI system's outputs, not a provider of an AI system. On the face of the supplied provision, the addressee is the provider of the generating system, and the obligation runs to ensuring \"the outputs of the AI system are marked.\" The claim does not describe miscsubjects.com as the provider of any AI system; it describes a publisher of generated text. Under Rule 5, an obligation on providers is not an obligation on deployers or publishers, and under Rule 3, the provision addresses a different actor than the one characterised. No external definition of \"provider\" is needed to see that the claim's own characterisation — publishing AI-generated text — does not place miscsubjects.com in the category named by the provision (\"providers of AI systems ... generating synthetic ... text\"). The mismatch is visible on the face of the text.\n> \n> RESTS_ON: \"Providers of AI systems, including general-purpose AI systems, generating synthetic audio, image, video or text content, shall ensure that the outputs of the AI system are marked in a machine-readable format and detectable as artificially generated or manipulated.\"\n> \n> DEFEATED_BY: The counter is that \"provider\" is a defined term under the AI Act and its precise scope is not contained in the supplied provision text, so under Rule 4 one could argue that whether a publisher of AI-generated text qualifies as a \"provider\" turns on a definition not supplied. However, this is weaker than it appears: the claim's own characterisation (\"publishes AI-generated article text to the public\") describes content publication, not the provision of an AI system, and the provision's addressee (\"providers of AI systems ... generating synthetic ... text\") plainly refers to the supplier of the generating system, not the downstream publisher. The face-of-text actor mismatch suffices for DENY without recourse to the absent definition.\n> \n> VERDICT_IF_ADOPTED: DENY\n> \n> SIGNED: Claude under 0dd9afef93503a92\n\nReceipt for the adversary's own invocation: [https://miscsubjects.com/receipt/inv_hnhihwv7y4](https://miscsubjects.com/receipt/inv_hnhihwv7y4)\n\n## What this establishes, and what it does not\n\n**Establishes:** that five named adjudicators, under rule set `ruleset-eu-ai-act-obligation@1.0.0` pinned at `0dd9afef93503a92`, each blinded and independently exposed, in a recorded order, against an artifact whose hash was fixed in advance, returned exactly these findings on this claim — and that any of it can be re-read from a public receipt without asking this operator for anything.\n\n**Does not establish:** that the claim is true. No adjudication anywhere establishes truth directly. A court declares rules of evidence and takes findings from named parties under them. A journal takes three reviewers against stated criteria. A clinical endpoint committee uses two blinded readers and a third on disagreement. Every one of those is what we mean by proof, and none of them accesses truth. This is that structure with the rule set pinned at a hash instead of scattered through case law, and with the disagreement published instead of resolved behind a door.\n\n**Also does not establish:** that five agreeing models would have been five independent confirmations. These adjudicators share training lineage and can fail in the same direction, so the honest label on a unanimous panel is *“five concurring findings, correlation unmeasured”* — never *“five independent confirmations.”* That calibration is a field on the record. Here the point is moot: the panel did not agree.\n\n## What is still missing, named\n\n- **A measured error rate.** The row [https://miscsubjects.com/api/directory/ADJUDICATE_PROBE](https://miscsubjects.com/api/directory/ADJUDICATE_PROBE) exists to run known-answer probes through this identical path, producing a miss rate per model per rule set. Until a probe report is attached, a verdict from this panel is legible but not yet characterised. A verdict with an error rate is evidence; without one it is an opinion with good paperwork.\n- **A human finding, recorded blind.** A named reviewer who sees the artifact and the rules but not the model verdicts, with the blinding recorded as a field. Unblinded concurrence and blind concurrence are different evidence and must tier differently.\n- **Cross-node attestation.** Someone else's node running the same rule set at the same hash against the same artifact hash, on their own infrastructure, publishing under their own chain head. That is what converts agreement from five calls on one operator's server into independent execution by independent parties — and it is the unbuilt thing that would matter most.\n- **Reopening.** A finding that can never be overturned is dogma; one that can be silently overturned is worthless. Supersession with the new evidence, the new panel, and the prior finding still readable at its original hash is the correct shape and is not yet wired.\n\n## Reproduce this\n\nEvery part is a directory row, invocable with one token. Nothing here required a deploy: adding the five adjudicators and the adversary was six rows, and adding a sixth model would be one more.\n\n```bash\n# read the pinned rules\ncurl -s https://miscsubjects.com/a/ruleset-eu-ai-act-obligation\n\n# read one adjudicator's contract\ncurl -s https://miscsubjects.com/api/directory/ADJUDICATE_KIMI\n\n# run your own finding (act token; ?share= works identically in a browser)\ncurl -s -X POST https://miscsubjects.com/api/dispatch \\\n  -H 'Authorization: Bearer <act token>' -H 'content-type: application/json' \\\n  -d '{\"key\":\"ADJUDICATE_GLM\",\"body\":\"RULESET_HASH: 0dd9afef93503a92…\\nRULESET: …\\nCLAIM: …\\nSOURCE: …\"}'\n\n# open any finding above without a token\ncurl -s 'https://miscsubjects.com/api/dispatch?confirm=inv_qgs2y3gt2x'\n```\n\nThe other three published rule sets take the same panel to the other questions people actually ask: whether a specific record was in a dataset ([https://miscsubjects.com/a/ruleset-dataset-membership](https://miscsubjects.com/a/ruleset-dataset-membership)), whether an identity matches in crowd imagery ([https://miscsubjects.com/a/ruleset-identity-match](https://miscsubjects.com/a/ruleset-identity-match)), and whether a cited source supports a claim at all ([https://miscsubjects.com/a/ruleset-claim-support](https://miscsubjects.com/a/ruleset-claim-support)). Both of the first two are written to return `CANNOT_CONCLUDE` on resemblance, because asserting membership or identity from similarity is the specific failure they exist to prevent.\n\nFull context for the system this runs on: [https://miscsubjects.com/a/the-build-end-to-end](https://miscsubjects.com/a/the-build-end-to-end)","hero":null,"images":[],"style":{},"tags":["adjudication","evidence","eu-ai-act","receipts","proof","rulesets"],"category":"adjudication","model":"Fable 5 (Claude Code)","ledger":{"href":"/api/articles/adjudication-eu-ai-act-article-50/ledger","live":true},"embeds":[],"widgets":[],"home":true,"claims":[{"id":"c1","text":"Five named adjudicators were each run blinded, in a recorded order derived from a published seed, against an artifact whose SHA-256 was fixed before the panel ran, under a rule set pinned at SHA-256 0dd9afef93503a92 with declared external-statutory provenance.","section":"method","tier":"demonstrated","source_ids":["s2","r1"]},{"id":"c2","text":"On whether Article 50(2) of Regulation (EU) 2024/1689 obliges this site to mark its AI-generated text, the panel returned three CANNOT_CONCLUDE, one DENY and one AFFIRM: observed pairwise agreement 0.3 and a negative Cohen-style kappa of -0.25.","section":"result","tier":"measured","source_ids":["r1","r2","r3"]},{"id":"c3","text":"The negative kappa is published rather than suppressed, because a panel that reports only its unanimities produces verdicts that cannot be priced.","section":"result","tier":"argued","source_ids":["s2"]},{"id":"c4","text":"The mandatory recorded adversary argued for DENY against a CANNOT_CONCLUDE majority on the ground that Article 50(2) addresses providers of generating systems rather than publishers of their outputs, and that argument is published in full including its receipt.","section":"result","tier":"demonstrated","source_ids":["radv","s4"]},{"id":"c5","text":"Each adjudicator, the adversary and the error-rate probe are directory rows driven through this system's existing gateway; adding the six of them required no code deployment and adding a further model is one additional row.","section":"method","tier":"demonstrated","source_ids":["s3","s4","s5"]},{"id":"c6","text":"The adjudication establishes what was found, by whom, under which rules, at which exposure, against which artifact hash — and does not establish that the claim is true. No adjudication anywhere establishes truth directly.","section":"limits","tier":"argued","source_ids":["s2"]},{"id":"c7","text":"Adjudicators sharing training lineage are not independent instruments, so a unanimous panel must be labelled 'concurring findings, correlation unmeasured' rather than 'independent confirmations'. On this question the panel did not agree, so the caveat is moot here.","section":"limits","tier":"argued","source_ids":["s2"]},{"id":"c8","text":"A verdict from this panel is not yet characterised: no known-answer probe report has been run against it, so its miss rate under these rules is unmeasured. The probe row exists and is named as unrun.","section":"limits","tier":"unproven","source_ids":["s5"]},{"id":"c9","text":"Cross-node attestation — another party running the same rule set at the same hash against the same artifact hash on their own infrastructure under their own chain head — is unbuilt, and is the single change that would convert panel agreement into independent execution by independent parties.","section":"limits","tier":"unproven","source_ids":["s5"]}],"sources":[{"id":"s1","type":"reference","url":"https://eur-lex.europa.eu/eli/reg/2024/1689/oj","title":"Regulation (EU) 2024/1689 (Artificial Intelligence Act) — Official Journal text","summary":"Article 50 transparency obligations. The provision text adjudicated here is quoted verbatim from this Regulation.","accessed_at":"2026-07-30T00:30","prev":"genesis","hash":"6c2e0c9c43562bed47ebc8839cb96e53f6103d276ddeb5ec503f897964516722"},{"id":"s2","type":"live_surface","url":"https://miscsubjects.com/a/ruleset-eu-ai-act-obligation","title":"The rule set this adjudication was made under, pinned at SHA-256 0dd9afef93503a92","summary":"Six numbered rules, version 1.0.0, declared provenance external-statutory, with its canonical form published so the hash can be recomputed.","accessed_at":"2026-07-30T00:30","prev":"6c2e0c9c43562bed47ebc8839cb96e53f6103d276ddeb5ec503f897964516722","hash":"e2b95f849f604acb9e4f6a8be8c7059cd4cb9aec674e726c6a7da05d12123f0f"},{"id":"s3","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_KIMI","title":"One adjudicator's full operating contract","summary":"An adjudicator is a directory row through this system's gateway. Adding another model is one more row and no deploy.","accessed_at":"2026-07-30T00:31","prev":"e2b95f849f604acb9e4f6a8be8c7059cd4cb9aec674e726c6a7da05d12123f0f","hash":"50fc00f8cdc0473f7a16e086b3a56c50b6983cf08e1621560ddd25f08a5a1b15"},{"id":"s4","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_ADVERSARY","title":"The mandatory recorded adversary's contract","summary":"Declared role: argue the strongest honest case against the majority under the same rules; published whether it prevails or not.","accessed_at":"2026-07-30T00:31","prev":"50fc00f8cdc0473f7a16e086b3a56c50b6983cf08e1621560ddd25f08a5a1b15","hash":"07dce1221643c2bde5bab0e9f8fe57386029303a5fefdc4c793a83ac2051872e"},{"id":"s5","type":"live_surface","url":"https://miscsubjects.com/api/directory/ADJUDICATE_PROBE","title":"The known-answer probe row: measured error rate per model per rule set","summary":"Exists and is not yet run against this panel; named as missing rather than implied to be done.","accessed_at":"2026-07-30T00:31","prev":"07dce1221643c2bde5bab0e9f8fe57386029303a5fefdc4c793a83ac2051872e","hash":"79c6e5dd834727f744dc677d669c58745187efb4095a4d14d135ac3c50034f28"},{"id":"r1","type":"receipt","url":"https://miscsubjects.com/receipt/inv_qgs2y3gt2x","invocation_id":"inv_qgs2y3gt2x","capability":"ADJUDICATE_KIMI","verdict":"finding recorded","title":"@cf/moonshotai/kimi-k2.7-code — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"79c6e5dd834727f744dc677d669c58745187efb4095a4d14d135ac3c50034f28","hash":"5aeac50214d85ac5cb0720365f54365aeb8c18d0a9b63ea8b8a6823ed3f30344"},{"id":"r2","type":"receipt","url":"https://miscsubjects.com/receipt/inv_91ztah4n7a","invocation_id":"inv_91ztah4n7a","capability":"ADJUDICATE_GROK","verdict":"finding recorded","title":"@cf/moonshotai/kimi-k2.6 — DENY","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"5aeac50214d85ac5cb0720365f54365aeb8c18d0a9b63ea8b8a6823ed3f30344","hash":"edafcf375c4292a7dd832689a1c2dccd02574d2ef70d60c68b98af927b8a9984"},{"id":"r3","type":"receipt","url":"https://miscsubjects.com/receipt/inv_ulxn9xe5t7","invocation_id":"inv_ulxn9xe5t7","capability":"ADJUDICATE_GLM","verdict":"finding recorded","title":"@cf/zai-org/glm-5.2 — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"edafcf375c4292a7dd832689a1c2dccd02574d2ef70d60c68b98af927b8a9984","hash":"a35983943c91c2ca10ff23445b4b40ed33cd23e898067f6d21a1716fbf6ac95b"},{"id":"r4","type":"receipt","url":"https://miscsubjects.com/receipt/inv_5gpfaftr5g","invocation_id":"inv_5gpfaftr5g","capability":"ADJUDICATE_LLAMA","verdict":"finding recorded","title":"@cf/meta/llama-3.3-70b-instruct-fp8-fast — AFFIRM","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"a35983943c91c2ca10ff23445b4b40ed33cd23e898067f6d21a1716fbf6ac95b","hash":"4615cad1c3135781151a4f2839e56724a146c558732de10421dc7b4f009fc007"},{"id":"r5","type":"receipt","url":"https://miscsubjects.com/receipt/inv_edjwsj4egv","invocation_id":"inv_edjwsj4egv","capability":"ADJUDICATE_MINIMAX","verdict":"finding recorded","title":"@cf/zai-org/glm-4.7-flash — CANNOT_CONCLUDE","material":true,"summary":"Blinded independent finding under rule set hash 0dd9afef93503a92, order seed fa0b1060b00f.","accessed_at":"2026-07-30T00:35","prev":"4615cad1c3135781151a4f2839e56724a146c558732de10421dc7b4f009fc007","hash":"8f8eab57542ef2f2349cf61daa6ce783fd48dd329c7a93320bb6f4fb0b0aba25"},{"id":"radv","type":"receipt","url":"https://miscsubjects.com/receipt/inv_hnhihwv7y4","invocation_id":"inv_hnhihwv7y4","capability":"ADJUDICATE_ADVERSARY","verdict":"finding recorded","material":true,"title":"The recorded adversary's invocation","summary":"The strongest case against the majority, published whether or not it prevailed.","accessed_at":"2026-07-30T00:35","prev":"8f8eab57542ef2f2349cf61daa6ce783fd48dd329c7a93320bb6f4fb0b0aba25","hash":"80511f415fd611466887160f3b4c7b7df9e3ce1d9e7516036b7ee3a0a31d3d38"}],"reviews":[],"extra":{},"has_traversal":false,"register":"standard","status":"published","revisions":0,"contributions":[],"provenance":[{"ts":"2026-07-30T00:38:22.278Z","model":"Fable 5 (Claude Code)","action":"write","prompt":"Owner order: build and demonstrate adjudication — declared rules, signed findings, blinding, exposure tiers, recorded adversary, published agreement, on a real EU AI Act provision.","input":"","response":"","tokens_in":0,"tokens_out":0,"cost":0,"prev":"genesis","hash":"29dcdfa7fbfed7f2fe042192a7e948af4011cf6ee33c2a2a853ff55672676ab5"}],"energy":{"passes":1,"tokens_in":0,"tokens_out":0,"tokens_total":0,"cost_usd":0,"models":{"Fable 5 (Claude Code)":1},"head":"29dcdfa7fbfed7f2fe042192a7e948af4011cf6ee33c2a2a853ff55672676ab5"},"posted_at":"2026-07-30T00:38:22.278Z","created_at":"2026-07-30T00:38:22.278Z","updated_at":"2026-07-30T00:38:22.278Z","machine":{"shape":"article.machine/v1","slug":"adjudication-eu-ai-act-article-50","kind":"article","read":{"human":"https://miscsubjects.com/a/adjudication-eu-ai-act-article-50","json":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50","bundle":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/bundle?format=markdown"},"traversal":{"prev":null,"next":null,"hub":null,"series":null,"position":null,"of":null},"ledger":{"claims":9,"sources":11,"contributions":0,"revisions":0,"objections_url":"https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/objections","thread_state_url":"https://miscsubjects.com/api/protocol/thread-state?target=adjudication-eu-ai-act-article-50","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\":\"adjudication-eu-ai-act-article-50\",\"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\":\"adjudication-eu-ai-act-article-50\",\"sources\":[{\"type\":\"review\",\"url\":\"<url>\",\"title\":\"<title>\",\"quote\":\"<verbatim quote>\",\"summary\":\"<one line>\"}]}'","objection":"curl -s -X POST https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50/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\":\"adjudication-eu-ai-act-article-50\",\"raw_text\":\"<material delta>\"}'  # open intake, no key","read_back":"curl -s https://miscsubjects.com/api/articles/adjudication-eu-ai-act-article-50 | python3 -c 'import json,sys; d=json.load(sys.stdin); print(json.dumps(d[\"claims\"][-3:], indent=1))'"}},"representations":{"article":"/a/adjudication-eu-ai-act-article-50","json":"/api/articles/adjudication-eu-ai-act-article-50","markdown":"/api/articles/adjudication-eu-ai-act-article-50/bundle?format=markdown","skill":"/api/articles/adjudication-eu-ai-act-article-50/skill","topology":"/api/articles/adjudication-eu-ai-act-article-50/topology","versions":"/api/articles/adjudication-eu-ai-act-article-50/revisions","invocations":"/api/articles/adjudication-eu-ai-act-article-50/invocations"}}}}