{"_self":{"principle":"Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.","widget":"article_topology","feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","contains":"claims, sources, anecdotes, question_graph slice","slug":"auditable-reasoning-hardened","urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/topology"},"how_to_use":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","write":null,"imessage":null,"router_tag":null,"proof_chain":[{"step":1,"claim":"Articles are voxel graphs of tiered claims, not prose blobs.","verify":"https://miscsubjects.com/api/articles/constitution"},{"step":2,"claim":"Claims link to hash-chained sources via source_ids.","verify":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/sources"},{"step":3,"claim":"Ask reads topology; ingest/claim append to ledger.","verify":"https://miscsubjects.com/api/protocol"},{"step":4,"claim":"Models queue growth: populate → collaborate → repair → reflex.","verify":"https://miscsubjects.com/api/protocol/grow"},{"step":5,"claim":"Graph proves its own shape (reflex) and $/claim (yield).","verify":"https://miscsubjects.com/graph.html?layer=reflex"},{"step":6,"claim":"Full feature index + _explain on every API response.","verify":"https://miscsubjects.com/api/articles/system-map"}],"related_features":[{"id":"ask","name":"Ask protocol","what":"Answer only from topology; creates question_node with gaps and ingest_hint.","urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/prompts","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"graph_topology","name":"Cross-article graph","what":"Merged claims/sources across condition+stack slugs for one question.","urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/graph-topology?question=..."}},{"id":"question_graph","name":"Question graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output).","urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/question-graph","write":"https://miscsubjects.com/api/protocol/ask"}},{"id":"voxels","name":"Voxel graph","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance.","urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/voxels","write":"https://miscsubjects.com/api/protocol/claim"}}],"system_map":"https://miscsubjects.com/api/articles/system-map","system_map_markdown":"https://miscsubjects.com/api/articles/system-map?format=markdown","not_medical_advice":true},"_explain":{"feature":"topology","name":"Article topology","what":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","why":"Every feature is auditable collective intelligence","how":"Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER.","model":null,"verifies":null,"urls":{"read":"https://miscsubjects.com/api/articles/auditable-reasoning-hardened/topology"},"imessage":null,"router":null,"related":[{"id":"ask","what":"Answer only from topology; creates question_node with gaps and ingest_hint."},{"id":"graph_topology","what":"Merged claims/sources across condition+stack slugs for one question."},{"id":"question_graph","what":"Ask nodes (questions + gaps) and evidence_ingest nodes (pasted model output)."},{"id":"voxels","what":"Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance."}],"not_medical_advice":true},"slug":"auditable-reasoning-hardened","title":"The gate now compares derivations, not citations — and the first APPROVE was false convergence","register":"technical","tags":["governance","adjudication","decision-constitution","experiment"],"updated_at":"2026-07-30T10:35:00.977Z","body_excerpt":"## The defect the last APPROVE was hiding\n\nThe [72-call experiment](https://miscsubjects.com/a/auditable-reasoning-audited) ended on a celebrated result: the first sealed APPROVE, three models unanimous, clause signature [1,2,3]. It was false convergence.\n\nThe old gate compared the *clause numbers* each model cited. Three models can cite clauses 1, 2 and 3 and mean completely different things by them — clause 2 \"triggered\" for one and \"not triggered\" for another, resting on different records, pointing to opposite effects — and the gate would still call that agreement and authorise the action. Citing the same rule is not applying it the same way. The gate was reading the table of contents and calling it the argument.\n\nThis page is the fix, proven live, and the more uncomfortable finding underneath it: two of the things blocking a *genuine* APPROVE were never the models at all. One was the governing prompt. The other was the input.\n\n## What changed in the gate\n\nEvery governed finding is now parsed into a versioned object (`decision-finding@1.0.0`) that is a deterministic projection of the raw payload — it never infers or repairs a missing field. A finding is **structurally invalid, and can never authorise**, when it lacks the terminal decision, lacks any required field, lacks the clause-evaluation vector, or invents a clause or an evidence id.\n\nThat last one is not hypothetical. A first panel under the new constitution escalated because `glm-4.7-flash` cited clauses **7, 8 and 12 in a three-clause ruleset** — it invented three rules. The parser marked it malformed; the gate refused.\n\n[[embed:source:s5]]\n\nThen the comparison itself changed. Each model must now emit, as the last line of its finding, a machine-readable vector — one entry per clause, each carrying the clause's **trigger_state** (did its condition fire on this record), its **disposition** (does that support, defeat, or stay neutral to the action), and the **exact record ids** it rests on. The gate compares the canonical tuple of those fields. Same clause numbers with different tuples is divergence, and divergence escalates.\n\nNine deterministic unit tests pin this, including the one that matters: same verdict, same clause numbers, different tuples → different signatures; and identical logic with different *wording* and *evidence order* → identical signatures. Wording is the human's; the tuple is the machine's.\n\n## Four outcomes, live\n\nRun through the production path — fresh stateless calls, each ledgered, then sealed by id in bound mode.\n\n| outcome | case | verdict | derivations | seal |\n|---|---|---|---|---|\n| **APPROVE** | a parking-permit rule, sufficiency-complete | unanimous AFFIRM | **1 identical signature** | [inv_wl0rnh136b](https://miscsubjects.com/receipt/inv_wl0rnh136b) |\n| **NEGATE** | a late service-credit claim | unanimous DENY | 1 identical signature | [inv_cgwtkvx17u](https://miscsubjects.com/receipt/inv_cgwtkvx17u) |\n| **ESCALATE** | an access request with the roster withheld | unanimous CANNOT_CONCLUDE | **2 divergent signatures** | [inv_o6s0exhodd](https://miscsubjects.com/receipt/inv_o6s0exhodd) |\n\nThe APPROVE is the genuine article the last one impersonated: not just the same verdict and the same clauses, but the same per-clause reasoning — `1:triggered:supports:reg | 2:not_triggered:neutral:cite` from every seat.\n\n[[embed:source:s1]]\n\nThe ESCALATE is the fix's clearest proof. All three models returned **CANNOT_CONCLUDE** and all three cited clauses [1,2,3]. The old gate would have sealed that as a clean NO_ACTION. The new gate escalated it, because two of the three derived that conclusion differently — they split on whether clause 2's condition even fired when the roster was missing. Agreement on the answer is not agreement on the reasoning, and only the second is safe to act on.\n\n[[embed:source:s3]]\n\n## The input is half the instrument\n\nBefore the corrected APPROVE, I could not get three models to converge on the access-control case no matter ho","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"The v1.2.0 first APPROVE was false convergence: three models cited the same clause numbers [1,2,3] but their per-clause derivations were not compared, so the gate authorised agreement it had not actually verified.","tier":"system","section":"The defect","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The celebrated result was the exact failure the whole system exists to prevent, and only the fix revealed it.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"A parsed decision-finding@1.0.0 object marks a finding structurally invalid — and unable to authorise — when it lacks a terminal decision, a required field, or the clause-evaluation vector, or when it invents a clause or evidence id.","tier":"system","section":"The fix","interaction_risk":false,"status":"active","source_ids":["s5"],"why_material":"It converts undetected malformed reasoning into a recorded refusal, and it caught a live invented-clause hallucination.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"The gate now compares canonical per-clause tuples — clause, trigger_state, disposition, load-bearing evidence — so a unanimous verdict with divergent derivations escalates instead of authorising.","tier":"system","section":"The fix","interaction_risk":false,"status":"active","source_ids":["s3"],"why_material":"Proven live: three CANNOT_CONCLUDE findings citing [1,2,3] still escalated because two derived it differently.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c4","text":"Under the corrected gate and a sufficiency-complete input, three findings across two families reached one identical derivation signature and the gate returned APPROVE.","tier":"system","section":"Four outcomes","interaction_risk":false,"status":"active","source_ids":["s1"],"why_material":"The genuine APPROVE the v1.2.0 result only impersonated.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c5","text":"A unanimous DENY with identical derivations sealed as NEGATE — the action refused, not deferred.","tier":"system","section":"Four outcomes","interaction_risk":false,"status":"active","source_ids":["s2"],"why_material":"The refusal path, exercised live and cleanly.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c6","text":"A model operating under the constitution, asked to review the author's own case input as a colleague, found eight ambiguities the author had not — beginning with a ruleset that never licensed the affirmative answer it was being asked for.","tier":"system","section":"The input is half the instrument","interaction_risk":false,"status":"active","source_ids":["s4"],"why_material":"The derivation divergences were not model defects; they were the model correctly reflecting an underspecified input back at its author.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c7","text":"Conforming-finding rate tracked prompt clarity, not model tier: at v1.3.0 (rules only) one of three findings was structurally valid; adding a worked right/wrong exemplar and a collegial uncertainty path took the capable seats to three of three with an identical derivation vector.","tier":"system","section":"Prompt version vs conformance","interaction_risk":false,"status":"active","source_ids":[],"why_material":"It settles the question the author raised — the variance was the prompt, not the model class.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c8","text":"No correctness-calibration study has been run: these outcomes prove the gate's structural behaviour, not that the models are correct at a known rate. That benchmark is the next experiment.","tier":"system","section":"What is not yet proven","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The honest boundary; a gate that seals correctly on agreement still says nothing about whether the agreed answer is right.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false}],"sources":[{"id":"s1","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_wl0rnh136b","title":"APPROVE — genuine derivation agreement, first under the new gate","summary":"Three findings, two families, unanimous AFFIRM, ONE distinct derivation signature (identical per-clause trigger/disposition/evidence), zero reasons. action_authorised: true.","claim_ids":["c4"],"hash":"dbc18f64661153a7cff1d965d0fc0dcb180dddf11373d3f6c1e98531b851d95a"},{"id":"s2","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_cgwtkvx17u","title":"NEGATE — unanimous DENY, identical derivations","summary":"The action is refused, not deferred. One derivation signature across three findings.","claim_ids":["c5"],"hash":"2f0f35404798f3f06430b966ebd7336246695996cecb4a7dd89dff4bca03346e"},{"id":"s3","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_o6s0exhodd","title":"ESCALATE — unanimous verdict, divergent derivations","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.","claim_ids":["c3"],"hash":"faaa5471df3169c9849a1c387650360878879615ba751883fc55b06e1f0079b7"},{"id":"s4","type":"model","url":"https://miscsubjects.com/receipt/inv_qh3ge2x74b","title":"@cf/zai-org/glm-5.2 reviewed the author's own case input — and found eight defects","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.","claim_ids":["c6"],"hash":"e48234a1d18b99e6cd2c5b154b16ba006ce4ee5b3f17b339c6367c9a4e494121"},{"id":"s5","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_2dsklah529","title":"The earlier gate catching an invented-clause hallucination","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.","claim_ids":["c2"],"hash":"d6ef3eeac1ef3e8c73f4c8eda42487450841155fda179ab4487581c470a0ab1c"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"auditable-reasoning-hardened","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":8,"retracted_claims":0,"cut_claims":0,"challenges":0,"scrub_events":0,"note":"Retracted/cut claims stay on ledger but are excluded from ask unless ?include_inactive=1"},"counts":{"claims":8,"claims_total":8,"sources":5,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}