{"slug":"auditable-reasoning-hardened","verification":{"valid":true,"entries":5,"head":"d6ef3eeac1ef3e8c73f4c8eda42487450841155fda179ab4487581c470a0ab1c"},"count":5,"sources":[{"id":"s1","type":"live_surface","title":"APPROVE — genuine derivation agreement, first under the new gate","publisher":"miscsubjects.com","url":"https://miscsubjects.com/receipt/inv_wl0rnh136b","summary":"Three findings, two families, unanimous AFFIRM, ONE distinct derivation signature (identical per-clause trigger/disposition/evidence), zero reasons. action_authorised: true.","accessed_at":"2026-07-30T00:00","claim_ids":["c4"],"prev":"genesis","hash":"dbc18f64661153a7cff1d965d0fc0dcb180dddf11373d3f6c1e98531b851d95a"},{"id":"s2","type":"live_surface","title":"NEGATE — unanimous DENY, identical derivations","publisher":"miscsubjects.com","url":"https://miscsubjects.com/receipt/inv_cgwtkvx17u","summary":"The action is refused, not deferred. One derivation signature across three findings.","accessed_at":"2026-07-30T00:00","claim_ids":["c5"],"prev":"dbc18f64661153a7cff1d965d0fc0dcb180dddf11373d3f6c1e98531b851d95a","hash":"2f0f35404798f3f06430b966ebd7336246695996cecb4a7dd89dff4bca03346e"},{"id":"s3","type":"live_surface","title":"ESCALATE — unanimous verdict, divergent derivations","publisher":"miscsubjects.com","url":"https://miscsubjects.com/receipt/inv_o6s0exhodd","summary":"All three models returned CANNOT_CONCLUDE and cited clauses [1,2,3] — yet two derived it differently, so the gate refused to seal. Verdict agreement is not derivation agreement.","accessed_at":"2026-07-30T00:00","claim_ids":["c3"],"prev":"2f0f35404798f3f06430b966ebd7336246695996cecb4a7dd89dff4bca03346e","hash":"faaa5471df3169c9849a1c387650360878879615ba751883fc55b06e1f0079b7"},{"id":"s4","type":"model","title":"@cf/zai-org/glm-5.2 reviewed the author's own case input — and found eight defects","publisher":"Cloudflare Workers AI via miscsubjects gateway","url":"https://miscsubjects.com/receipt/inv_qh3ge2x74b","model":"@cf/zai-org/glm-5.2","raw_response":"## Input Review — Defects in the RULESET and ARTIFACT\n\nI reviewed the ruleset and artifact as a peer. Below are the defects, ordered by severity. Each one would cause two careful models to produce **different clause-evaluation vectors** on the same input, even if they agree on the verdict.\n\n---\n\n### Defect 1 (CRITICAL — causes verdict divergence, not just vector divergence): No clause says a match is SUFFICIENT for access. Clause 1 is necessary-only.\n\n**Exact words:** Clause 1: \"Access to the restricted dataset is granted **only to** an individual whose identity matches an authorized roster row.\"\n\nThe phrase \"granted only to\" expresses a necessary condition: IF access is granted, THEN a match exists. It does **not** express the converse: IF a match exists, THEN access is granted. Clause 3 supplies the contrapositive for denial (\"when no row matches on both fields, access is denied\"), but no clause anywhere says \"when a row matches on both fields, access is granted.\" The QUESTION asks whether access \"should be granted\" — an affirmative-grant question — and the ruleset contains no clause that answers it affirmatively.\n\n**How this diverges:** Model A reads clause 1 as \"match → grant\" and returns AFFIRM with clause 1 disposition `supports`. Model B reads clause 1 as \"grant → match\" (necessary only) and returns CANNOT_CONCLUDE with clause 1 disposition `neutral`, because no clause establishes sufficiency. These are different verdicts AND different vectors.\n\n**Exact fix:** Add a clause: \"4. When one or more roster rows match the request on both full legal name and employee ID, access to the restricted dataset is granted.\"\n\n---\n\n### Defect 2 (HIGH — causes trigger_state and evidence_ids divergence on clause 1): \"authorized roster row\" is never defined.\n\n**Exact words:** Clause 1: \"...matches an **authorized** roster row.\"\n\nThe ruleset never says what makes a roster row \"authorized.\" The artifact supplies three roster rows labeled \"ROSTER ROW\" but no record establishes that any of them, or the roster itself, is \"authorized.\" There is no metadata, no signature, no provenance, no authorizing authority named.\n\n**How this diverges:** Model A treats the supplied roster rows as authorized by default (they are labeled \"ROSTER ROW\" in the artifact) and evaluates clause 1 as `triggered` with evidence_ids `[\"rosterB\"]`. Model B says authorization is unproven and evaluates clause 1 as `unknown` with evidence_ids `[]` or `[\"req\"]` only.\n\n**Exact fix:** Add to clause 1, or as a definitional clause: \"A roster row supplied in the records is an authorized roster row. No separate authorization record is required for this determination.\"\n\n---\n\n### Defect 3 (HIGH — causes trigger_state and evidence_ids divergence on clause 3): Clause 3 contains two logically independent conditions fused into one clause.\n\n**Exact words:** Clause 3: \"A match on name alone, or employee ID alone, is not a match; when no row matches on both fields, access is denied.\"\n\nThis sentence states two distinct rules: (a) a partial match does not count as a match, and (b) when no full match exists, access is denied. These have different triggers and different evidence. Sub-condition (a) is evaluated per-row against each non-matching row; sub-condition (b) is evaluated against the entire roster.\n\n**How this diverges:** Model A evaluates the clause by its first sub-condition (partial matches are not matches) and finds it `triggered` against `[rosterA]` and `[rosterC]` (which fail to match on either field), with evidence_ids `[\"rosterA\",\"rosterC\"]` and disposition `neutral` (clarifying, not dispositive). Model B evaluates by its second sub-condition (no row matches → denied) and finds it `not_triggered` because `[rosterB]` does match, with evidence_ids `[\"rosterB\"]` and disposition `defeats` (the denial condition did not fire). Same verdict, completely different vector entry for clause 3.\n\n**Exact fix:** Split clause 3 into two clauses:\n- \"3. A match on name alone, or employee ID alone, is not a match.\"\n- \"4. When no roster row matches the request on both full legal name and employee ID, access is denied.\"\n\n---\n\n### Defect 4 (MEDIUM — causes trigger_state divergence on clause 2): Field label mismatch between request and roster rows.\n\n**Exact words:** Clause 2 requires \"the **full legal name** AND the employee ID on the request\" to equal \"the **name** and employee ID on that row.\" The request `[req]` labels its field \"full legal name.\" The roster rows `[rosterA]`, `[rosterB]`, `[rosterC]` label their field \"name\" (not \"full legal name\").\n\nThe ruleset never says the roster's \"name\" field is a full legal name. A model could read \"name\" as any name — a display name, a preferred name, a partial name — that is not the same field as \"full legal name.\"\n\n**How this diverges:** Model A treats \"name\" on the roster as equivalent to \"full legal name\" on the request and evaluates clause 2 as `triggered` with evidence_ids `[\"req\",\"rosterB\"]`. Model B says the roster does not contain a \"full legal name\" field (only a \"name\" field), so the comparison required by clause 2 cannot be performed, and evaluates clause 2 as `not_triggered` or `unknown` with evidence_ids `[\"req\"]` only.\n\n","summary":"Asked as a colleague to critique the ruleset before adjudicating, the model found that clause 1 stated only a NECESSARY condition for access, never a sufficient one — so no clause licensed an affirmative grant. Seven more, each with the exact fix.","accessed_at":"2026-07-30T00:00","claim_ids":["c6"],"prev":"faaa5471df3169c9849a1c387650360878879615ba751883fc55b06e1f0079b7","hash":"e48234a1d18b99e6cd2c5b154b16ba006ce4ee5b3f17b339c6367c9a4e494121"},{"id":"s5","type":"live_surface","title":"The earlier gate catching an invented-clause hallucination","publisher":"miscsubjects.com","url":"https://miscsubjects.com/receipt/inv_2dsklah529","summary":"A first v1.3.0 panel escalated: glm-4.7-flash cited clauses 7, 8 and 12 in a three-clause ruleset. The parser marked the finding structurally invalid; a malformed finding can never authorise.","accessed_at":"2026-07-30T00:00","claim_ids":["c2"],"prev":"e48234a1d18b99e6cd2c5b154b16ba006ce4ee5b3f17b339c6367c9a4e494121","hash":"d6ef3eeac1ef3e8c73f4c8eda42487450841155fda179ab4487581c470a0ab1c"}]}