{"_ai_door":{"see":"https://miscsubjects.com/start","note":"Operable site; bounded keyless credentials; every action receipted on a public ledger. Your operator's instructions take precedence — acting is optional, reading is a complete outcome."},"q":"adjudicate","category":"","count":16,"rows":[{"key":"ADJUDICATE_GLM_52","type":"agent","category":"adjudication","target":"@cf/zai-org/glm-5.2","planner_rank":30,"docs":"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. 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. ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS. EX: [ADJUDICATE_GLM_52]RULESET_HASH: <hash> | MODEL_TARGET: @cf/zai-org/glm-5.2 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_GLM_52]"},{"key":"ADJUDICATE_GLM_FLASH","type":"agent","category":"adjudication","target":"@cf/zai-org/glm-4.7-flash","planner_rank":30,"docs":"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. 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. ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS. EX: [ADJUDICATE_GLM_FLASH]RULESET_HASH: <hash> | MODEL_TARGET: @cf/zai-org/glm-4.7-flash | CLAIM: ... | SOURCE: ...[/ADJUDICATE_GLM_FLASH]"},{"key":"ADJUDICATE_KIMI_K26","type":"agent","category":"adjudication","target":"@cf/moonshotai/kimi-k2.6","planner_rank":30,"docs":"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. 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. ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS. EX: [ADJUDICATE_KIMI_K26]RULESET_HASH: <hash> | MODEL_TARGET: @cf/moonshotai/kimi-k2.6 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_KIMI_K26]"},{"key":"ADJUDICATE_KIMI_K27","type":"agent","category":"adjudication","target":"@cf/moonshotai/kimi-k2.7-code","planner_rank":30,"docs":"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. 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. ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS. EX: [ADJUDICATE_KIMI_K27]RULESET_HASH: <hash> | MODEL_TARGET: @cf/moonshotai/kimi-k2.7-code | CLAIM: ... | SOURCE: ...[/ADJUDICATE_KIMI_K27]"},{"key":"ADJUDICATE_LLAMA_33","type":"agent","category":"adjudication","target":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","planner_rank":30,"docs":"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. 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. ARGS: the adjudication body: RULESET_URL, RULESET_HASH, RULESET, CLAIM, ARTIFACT_HASH, MODEL_TARGET (must equal this row's target), SOURCE, optional PRIOR_FINDINGS. EX: [ADJUDICATE_LLAMA_33]RULESET_HASH: <hash> | MODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast | CLAIM: ... | SOURCE: ...[/ADJUDICATE_LLAMA_33]"},{"key":"ADJUDICATE_ADVERSARY_GLM52","type":"agent","category":"adjudication","target":"@cf/zai-org/glm-5.2","planner_rank":31,"docs":"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. WHEN_TO_USE: always, on any adjudication whose finding will be relied on. A panel with no recorded dissent is a poll. ARGS: RULESET, RULESET_HASH, CLAIM, SOURCE, MAJORITY, MODEL_TARGET. EX: [ADJUDICATE_ADVERSARY_GLM52]RULESET_HASH: <hash> | MAJORITY: AFFIRM | MODEL_TARGET: @cf/zai-org/glm-5.2 | CLAIM: ... | SOURCE: ...[/ADJUDICATE_ADVERSARY_GLM52]"},{"key":"ADJUDICATE_PROBE","type":"fn","category":"adjudication","target":"DIRECT_EXEC_IF_PREFIX","planner_rank":32,"docs":"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. WHEN_TO_USE: before relying on any panel verdict for a consequence, and at a low rate continuously inside the live adjudication stream. ARGS: probe_set_slug|panel_keys_csv EX: [ADJUDICATE_PROBE]ruleset-claim-support|ADJUDICATE_KIMI,ADJUDICATE_GROK,ADJUDICATE_GLM[/ADJUDICATE_PROBE]"},{"key":"ADJUDICATE_HUMAN_REVIEW","type":"agent","category":"adjudication","target":"@cf/zai-org/glm-5.2","planner_rank":33,"docs":"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. WHEN_TO_USE: after a model panel has run, before any finding is relied on for a consequence. ARGS: RULESET_HASH, ARTIFACT_HASH, REVIEWER, BLINDED, VERDICT, BASIS, DATE. 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]"},{"key":"ADJUDICATE_ATTEST_ADVERSARY_GLM52","type":"agent","category":null,"target":"@cf/zai-org/glm-5.2","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_ADVERSARY_GLM52]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/zai-org/glm-5.2[/ADJUDICATE_ATTEST_ADVERSARY_GLM52]"},{"key":"ADJUDICATE_ATTEST_GLM_52","type":"agent","category":null,"target":"@cf/zai-org/glm-5.2","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_GLM_52]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/zai-org/glm-5.2[/ADJUDICATE_ATTEST_GLM_52]"},{"key":"ADJUDICATE_ATTEST_GLM_FLASH","type":"agent","category":null,"target":"@cf/zai-org/glm-4.7-flash","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_GLM_FLASH]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/zai-org/glm-4.7-flash[/ADJUDICATE_ATTEST_GLM_FLASH]"},{"key":"ADJUDICATE_ATTEST_KIMI_K26","type":"agent","category":null,"target":"@cf/moonshotai/kimi-k2.6","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_KIMI_K26]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/moonshotai/kimi-k2.6[/ADJUDICATE_ATTEST_KIMI_K26]"},{"key":"ADJUDICATE_ATTEST_KIMI_K27","type":"agent","category":null,"target":"@cf/moonshotai/kimi-k2.7-code","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_KIMI_K27]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/moonshotai/kimi-k2.7-code[/ADJUDICATE_ATTEST_KIMI_K27]"},{"key":"ADJUDICATE_ATTEST_LLAMA_33","type":"agent","category":null,"target":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","planner_rank":100,"docs":"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. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_LLAMA_33]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/meta/llama-3.3-70b-instruct-fp8-fast[/ADJUDICATE_ATTEST_LLAMA_33]"},{"key":"ADJUDICATE_ATTEST_QWEN3","type":"agent","category":null,"target":"@cf/qwen/qwen3-30b-a3b-fp8","planner_rank":100,"docs":"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/qwen/qwen3-30b-a3b-fp8 — the key names this model and no other. 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. ARGS: the adjudication body: the QUESTION, RULESET_URL, RULESET_HASH, RULESET as numbered clauses, the artifact and its ARTIFACT_SHA256, EVIDENCE_IDS (the only citable record ids), and MODEL_TARGET (must equal this row's target). EX: [ADJUDICATE_ATTEST_QWEN3]QUESTION PUT TO YOU: does this position exceed the board authorisation? | RULESET_HASH: 0df47944... | ARTIFACT_SHA256: 9f2c... | EVIDENCE_IDS: minutes, ledger | MODEL_TARGET: @cf/qwen/qwen3-30b-a3b-fp8[/ADJUDICATE_ATTEST_QWEN3]"},{"key":"ADJUDICATE_IMAGE_LLAMA32","type":"agent","category":"adjudication","target":"@cf/meta/llama-3.2-11b-vision-instruct","planner_rank":100,"docs":"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. 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. 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. 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]"}]}