{"_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-abstention-no-action","urls":{"read":"https://miscsubjects.com/api/articles/adjudication-abstention-no-action/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-abstention-no-action/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-abstention-no-action/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-abstention-no-action/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-abstention-no-action/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-abstention-no-action/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-abstention-no-action/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-abstention-no-action","title":"Abstention under agreement discipline: making \"cannot conclude\" a sealed, machine-comparable outcome — including fixing our own law to get there.","register":"technical","tags":["governance","adjudication","abstention","use-case","evaluation"],"updated_at":"2026-07-30T13:31:25.704Z","body_excerpt":"## The property abstention benchmarks do not measure\n\nBenchmarks for abstention exist — AbstentionBench (arXiv:2506.09038) measures whether models abstain when they should. What we have not identified any benchmark measuring — the harder discipline this page concerns — is whether independent models can refuse to answer for identical stated reasons — the same clauses, the same trigger states, the same cited absences — in a form one refusal can be mechanically compared against another. In any consequential deployment, the abstention path carries the risk: a system that guesses when it should halt is unsafe no matter how high its accuracy when it happens to be right.\n\nThis page documents making abstention a first-class, sealable outcome — including the part where the governing specification itself was the defect, and the four amendments, each forced by a live panel's residual disagreement, that ended in the first clean NO_ACTION seal on record.\n\n## Why abstention must seal\n\nThe derivation-agreement gate has four outcomes: APPROVE (unanimous affirmation, identical derivations), NEGATE (unanimous denial, identical derivations), ESCALATE (any divergence — a human decides), and NO_ACTION (unanimous, derivation-identical abstention: the panel agrees the determination cannot be made on the supplied records, and agrees exactly why).\n\n[[embed:source:s3]]\n\nNO_ACTION is not a failure code. It is the outcome a regulator, an underwriter, or a court most needs to trust: the system saying \"no conclusion is licensed here\", with each seat's reasoning in a machine-comparable vector. Three of the four outcomes had clean live receipts. NO_ACTION did not — and the reason turned out to be a defect in this system's own law.\n\n## The defect: a disposition with no referent\n\nUnder constitution v1.3.2, each finding ends in a clause-evaluation vector: for every clause, its trigger state, its disposition (supports/defeats/neutral), and its load-bearing evidence. On a case built to force abstention — an access request whose authorizing roster was deliberately not supplied — three models all returned CANNOT_CONCLUDE, all cited the same clauses, and the gate still refused to seal:\n\n[[embed:source:s2]]\n\nOne seat marked the gap-carrying clause `supports`; another marked it `defeats`. Neither was wrong, because the question was undefined: supports *what*? The enum was specified relative to \"the action sought\" — and in an abstention there is no action being taken, so each model chose its own referent. The specification, not the models, was the source of the variance. That is the same lesson this system had already learned about case inputs — an earlier governed critique found eight defects in a case file, the lead one a necessity-stated-as-sufficiency error — now turned on the constitution itself:\n\n[[embed:source:s6]]\n\n## The repair loop: one rule per residual divergence\n\nThe method was the one established by the variance study — treat the governing text as a measured variable, change one rule at a time, and rerun live panels after each change:\n\n[[embed:source:s5]]\n\n**Amendment 1 — bind the referent, add the missing value.** Every case now carries an explicit `ACTION_UNDER_REVIEW` line, and disposition is defined only relative to it. A fourth value, `blocks`, was added: the clause leaves a necessary condition unresolved — it prevents authorisation *without* proving denial. On an abstention, the gap-carrying clause is always `blocks`. Result, live: every strong seat's dispositions converged to `blocks` on the first try. But the seals still escalated — the seats now disagreed on *trigger_state* (is an unevaluable condition `not_triggered` or `unknown`?) and on which record evidences an absence.\n\n**Amendment 2 — an unevaluable condition is always `unknown`.** `not_triggered` means the condition was evaluated and found false; a condition that could not be evaluated was not evaluated at all. And the case itself was amended once, the same way the input-critique precedent","ranking":"safety-first (interaction_risk/limitations), then quote-gated effective_weight","claims":[{"id":"c1","text":"A governed abstention — CANNOT_CONCLUDE with a machine-comparable derivation — is a distinct sealed outcome (NO_ACTION), not a failure mode.","tier":"system","section":"Why abstention must seal","interaction_risk":false,"status":"active","source_ids":["s3"],"why_material":"Systems are benchmarked on answering; the rarer, more valuable capability is refusing to answer in a comparable, auditable way.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c2","text":"Under constitution v1.3.2 a clean NO_ACTION was unreachable: disposition (supports/defeats/neutral) was undefined for an abstention, so unanimous abstaining panels diverged on how to encode the gap.","tier":"system","section":"The defect","interaction_risk":false,"status":"active","source_ids":["s2"],"why_material":"A spec defect in the governing law itself, found by the gate refusing to seal.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c3","text":"The fix was four one-rule amendments, each derived from the exact residual divergence of the previous live panel: bind disposition to an explicit ACTION_UNDER_REVIEW and add 'blocks'; an unevaluable condition is always trigger_state unknown; evidence_ids is the minimal load-bearing set and an unknown clause cites the absence-establishing record; a consequence-mandating clause is always blocks.","tier":"system","section":"The repair loop","interaction_risk":false,"status":"active","source_ids":["s5","s6"],"why_material":"The method is the product: divergence is read as specification ambiguity and the specification is amended, with receipts at every step.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c4","text":"Each amendment removed exactly the divergence field it targeted, live: dispositions converged first, then trigger_state, then evidence — with the residual visible in the intermediate seals.","tier":"system","section":"The repair loop","interaction_risk":false,"status":"active","source_ids":["s4"],"why_material":"The iterations are on the ledger, not summarized after the fact.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c5","text":"Under the final v1.3.3 text, a four-finding, two-family panel produced one identical derivation signature and sealed NO_ACTION — the first clean abstention on record, completing all four gate outcomes (APPROVE, NEGATE, ESCALATE, NO_ACTION).","tier":"system","section":"The seal","interaction_risk":false,"status":"active","source_ids":["s1"],"why_material":"The abstention path is now proven end to end, not asserted.","retracted_at":null,"retraction_reason":null,"challenged_by":[],"effective_weight":0.1,"quote_gated":false},{"id":"c6","text":"The cheapest seat still misreads the abstention rules at a visible rate and is caught by the gate each time; and no calibration study establishes abstention correctness against oracle-labelled should-abstain cases.","tier":"system","section":"What is not satisfied","interaction_risk":false,"status":"active","source_ids":[],"why_material":"The honest limits: the gate proves agreement discipline, not calibrated abstention accuracy.","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_7rqy8ywuls","title":"The first clean NO_ACTION seal","summary":"Four findings, two model families, one derivation signature, unanimous CANNOT_CONCLUDE, zero divergence reasons. The abstention outcome, sealed.","claim_ids":["c5"],"hash":"1436228890bd794846ced69c5b6c07da5e4e7489e2907268b4d272f4ba44d7f3"},{"id":"s2","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_o6s0exhodd","title":"The defect run: unanimous abstention the gate refused","summary":"Under v1.3.2, three models abstained on the same clauses and the gate still escalated — one seat marked the gap clause supports, another defeats, because disposition was undefined for an abstention.","claim_ids":["c2"],"hash":"fe36ca446ab5ea929e71f9205c8ee7fb2be4313065a2180f3f7867dd57f60b72"},{"id":"s3","type":"live_surface","url":"https://miscsubjects.com/a/auditable-reasoning-hardened","title":"The derivation-agreement gate","summary":"The sealer that compares clause-by-clause derivations, not verdicts — the machinery all of this runs through.","claim_ids":["c1"],"hash":"f66f20acae4a520064231ed3ed51253596d8ea3af9fef8ed05c7059a6305c258"},{"id":"s4","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_o5959lzlvw","title":"Intermediate seal: dispositions converged, evidence did not","summary":"After the blocks amendment and a manifest record, all three seats abstained as blocks — and still diverged, on trigger_state and evidence choice. Each residual divergence named the next amendment.","claim_ids":["c4"],"hash":"ff7d96d24e470f7b0d0a86391fca6399d9ab2b02790f7f93ec47d3ec32dcb3e3"},{"id":"s5","type":"live_surface","url":"https://miscsubjects.com/a/auditable-reasoning-audited","title":"The 72-call variance study","summary":"The method this page continues: the governing text is a measured causal variable, changed one rule at a time against live panels.","claim_ids":["c3"],"hash":"778bb636d7dbf331d73b46b8afc5e8208a7d7f2c87c658dbd17a46e96ee6988c"},{"id":"s6","type":"live_surface","url":"https://miscsubjects.com/receipt/inv_qh3ge2x74b","title":"The input-critique precedent","summary":"The earlier eight-defect critique that established the pattern: most divergence is specification ambiguity, and the specification includes this system's own constitution.","claim_ids":["c3"],"hash":"0b81f7b34c84a6a12b0a87920f91e7701985aad6c71b253c86d029c33300ea6b"}],"anecdotal_sources":[],"scientific_sources":[],"user_reports":[],"related_articles":[],"question_graph":{"slug":"adjudication-abstention-no-action","questions":[],"evidence":[],"edges":[],"counts":{"questions":0,"evidence":0,"edges":0}},"honesty":{"active_claims":6,"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":6,"claims_total":6,"sources":6,"anecdotal":0,"scientific":0,"user_reports":0,"questions":0,"evidence_ingests":0}}