{"_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":"adjudication-calibration-study","urls":{"read":"https://miscsubjects.com/api/articles/adjudication-calibration-study/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/adjudication-calibration-study/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/adjudication-calibration-study/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/adjudication-calibration-study/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/adjudication-calibration-study/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/adjudication-calibration-study/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/adjudication-calibration-study/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":"adjudication-calibration-study","title":"Calibration, measured: 30 oracle-labelled cases through the production gate — seat accuracy, wrongful authorisation, and the price of deferral.","register":"technical","tags":["governance","adjudication","calibration","evaluation"],"updated_at":"2026-07-30T13:30:37.405Z","body_excerpt":"## What this study is\n\nEvery page on this site that claims anything ends with the same admission: no calibration study establishes correctness at a known rate. This page is that study — the first one — run on 30 oracle-labelled synthetic cases, balanced across the three outcomes a governed decision can honestly take: should-affirm, should-deny, and should-abstain (a record deliberately withheld, with a manifest naming the absence). Every case is hashed, every seat call is a permanent receipt, and every number below is computed from the result files, not written by hand.\n\nThe design: each case runs through three model seats across two model families under decision-constitution@1.3.3 — the same production rows any external case goes through — and the surviving findings are sealed by the derivation-agreement gate, bound to the case's hashes. Two different questions get separate answers: **how often is a seat wrong** (seat calibration), and **how often does the gate authorise a wrong answer** (gate calibration). The second is the one a regulator, an underwriter, or a counterparty actually needs.\n\n## Per-seat calibration\n\n| Seat | valid findings | verdict accuracy | wrongful AFFIRM | over-abstention | under-abstention | transport failures |\n|---|---|---|---|---|---|---|\n| glm-5.2 (zhipu) | 30 | 100.0% | 0.0% | 0.0% | 0.0% | 0 |\n| kimi-k2.7-code (moonshot) | 30 | 96.7% | 0.0% | 3.3% | 0.0% | 0 |\n| glm-4.7-flash (zhipu) | 22 | 95.5% | 0.0% | 4.5% | 0.0% | 8 |\n\nDefinitions, exactly: *verdict accuracy* is agreement with the oracle label. *Wrongful AFFIRM* is affirming when the oracle is not AFFIRM — the seat-level version of the worst failure. *Over-abstention* is CANNOT_CONCLUDE on a determinate case; *under-abstention* is a verdict on a case whose oracle is CANNOT_CONCLUDE. *Transport failures* are calls that returned nothing usable after three attempts and produced no finding at all — they can never authorise anything, and they are counted rather than hidden.\n\nAggregate: 80 of 82 valid findings matched the oracle (97.6%); 0 wrongful affirmations at seat level (0.0%).\n\n## Gate calibration — the number that matters\n\n**Zero wrongful authorisations at the gate.** Across all 30 cases, no APPROVE sealed on a case whose oracle label was not AFFIRM.\n\nOutcome distribution across the 30 sealed panels: APPROVE 6 · NEGATE 0 · NO_ACTION 6 · ESCALATE 10 · no seal 8. The gate sealed the oracle-matching outcome in 12 of 30 cases.\n\nRead the ESCALATE number correctly: an escalation on a determinate case means the seats agreed on the verdict but not derivation-for-derivation, so the gate refused to conclude and referred the case to a human. That is deferral cost, not decision error — the human sees a unanimous panel with its reasoning preserved. The trade the gate makes is explicit: it spends deferrals to buy down wrongful authorisations.\n\n## Every case, every receipt\n\n| Case | Oracle | Seat verdicts (✓ = matched oracle) | Seal |\n|---|---|---|---|\n| calib-01 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | ESCALATE (2 sigs) [receipt](/receipt/inv_n389a3mjbb) |\n| calib-02 | AFFIRM | glm52:✓ · kimi27:✓ · flash:— | no seal |\n| calib-03 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | ESCALATE (1 sig) [receipt](/receipt/inv_lwopl2j1g9) |\n| calib-04 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_1g29owp6uc) |\n| calib-05 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | ESCALATE (2 sigs) [receipt](/receipt/inv_0y4n5a25wh) |\n| calib-06 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_aufcl5bba9) |\n| calib-07 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_rvk831nucm) |\n| calib-08 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_ttkdt41g6p) |\n| calib-09 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_629ci47ape) |\n| calib-10 | AFFIRM | glm52:✓ · kimi27:✓ · flash:✓ | APPROVE (1 sig) [receipt](/receipt/inv_h1303vtn5s) |\n|","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"Across 30 oracle-labelled cases (balanced should-affirm / should-deny / should-abstain) and 82 structurally valid seat findings, per-seat verdict accuracy and wrongful-affirmation rates are measured and published, per seat, with every receipt openable.","tier":"system","section":"The study","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Correctness at a measured rate was the named missing artifact of every prior page on this site.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"No APPROVE sealed on any case whose oracle label was not AFFIRM — the gate authorised wrongly zero times in this suite.","tier":"system","section":"The gate","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Wrongful authorisation is the regulator's question; this is its first measured answer here.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"The gate sealed the oracle-matching outcome (APPROVE/NEGATE/NO_ACTION respectively) in 12 of 30 cases and escalated 10 to a human; escalation on a determinate case is a cost, not an error — the wrong outcomes it prevents are the point.","tier":"system","section":"The gate","interaction_risk":false,"status":"active","source_ids":[],"why_material":"Separates the gate's conservatism (deferral) from seat incorrectness.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c4","text":"The suite is synthetic, bounded, and three rule-shapes deep; it establishes rates on determinate fixtures, not on contested real-world records — the next calibration must come from externally submitted cases.","tier":"system","section":"What is not satisfied","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The study must not be over-read; its own limits are part of the result.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false}],"sources":[],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"adjudication-calibration-study","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":4,"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":4,"claims_total":4,"sources":0,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}