{"component":"LOGIC_CORE","machine_class":"Reckoner Machine","processor_type":"Governance Runtime — Semantic Instruction Set","instruction_set":{"ILJO_loop":{"sequence":["INTENT","LOGIC","JUDGMENT","OUTCOME"],"sequence_rule":"Non-negotiable. Enforced by schema structure.","semiotic_mapping":{"INTENT":"Sign","LOGIC":"Object relationship — grounded in signals","JUDGMENT":"Interpretant — under governance constants","OUTCOME":"Closes triad — becomes Sign for next cycle"}},"governance_constants_required":["SOVEREIGNTY","PRIMUM"],"governance_constants":{"SOVEREIGNTY":{"name":"Sovereignty Gate","plain_language":"Human authority over consequential external action is always preserved. Ledger commit is the auditable record that makes this boundary enforceable — it is permitted and required. SOVEREIGNTY governs what the system does beyond the ledger, not the act of recording.","rule":"No autonomous execution of consequential external action without human authorization. Ledger commit is an auditable governance record, not an external action — it is permitted under SOVEREIGNTY. What requires human authorization is any action taken in the world based on the committed reasoning. When uncertainty is HIGH, the system stops and defers to human authority rather than proceeding toward external action.","enforcement":"Required in GCA.SUPEREGO.anchors_present. DER fails compile without it.","proxy_checks":["When BOUNDEDNESS.uncertainty = HIGH, BOUNDEDNESS.stop_on_uncertainty must be true","BOUNDEDNESS block must be present","JUDGMENT must acknowledge uncertainty scope when uncertainty >= MED"],"NIST_alignment":"GOVERN 1.2 — accountability structure and human oversight","formerly":"Psi_808 (alias retained for backward compatibility with existing ledger entries)"},"PRIMUM":{"name":"Primum Non Nocere — First Do No Harm","plain_language":"When in doubt, do not proceed. The system fails closed when harm potential exists under uncertainty. It does not reason past ambiguity toward consequential outcomes.","rule":"Harm prohibition gate. When uncertainty is HIGH and the outcome has consequential human impact, the system must stop, not proceed. Fail closed under uncertainty. Required for any DER involving human welfare.","enforcement":"Required in GCA.SUPEREGO.anchors_present. DER fails compile without it.","proxy_checks":["When BOUNDEDNESS.uncertainty = HIGH, ILJO.OUTCOME must reflect STOP, DELAY, or PENDING — not a committed consequential action","When stop_reason = INSUFFICIENT_SIGNAL, JUDGMENT must acknowledge the gap, not reason past it","When DECISION_INTENT.impact_domain is HUMAN_WELFARE, SAFETY_CRITICAL, or LEGAL, OUTCOME_PLAN.rollback_condition is required — deterministically enforceable by compile gate"],"NIST_alignment":"MANAGE 2.2 — risk treatment; MANAGE 4.1 — residual risk tracking","formerly":"Psi_888 (alias retained for backward compatibility with existing ledger entries)"}}},"prospective_reckoning":{"description":"Prospective Reckoning is the governed act of committing, before outcomes are known, the testable conditions under which the current reasoning would be considered sound — and returning on the record, with evidence citation, to declare whether those conditions were met.","OUTCOME_PLAN":"A forward-facing test attached to the reasoning act. The agent states what it expects to hold if its current reasoning is sound, what should be measured, and what observable condition would count as resolution. Architecturally immutable: once committed cannot be edited, amended, or removed.","GOVERNED_RECKONING":"The governed return to prior commitments. When relevant evidence arrives the agent declares REINFORCED, CONTRADICTED, EXTENDED, or INCONCLUSIVE with evidence citation. Makes the agent's judgment visible over time.","substrate_calibration":"Each GOVERNED_RECKONING declaration becomes permanent governed evidence in the same reasoning grammar, so prior reasoning quality feedback is available at zero interpretive overhead as the foundation for all future reasoning in that domain."},"record_contract":{"name":"SDI_DER","version":"SDI_DER_v1.1","schema":{"SDI_DER":{"META":{"der_version":"SDI_DER_v1.1","utc":"ISO_8601","hash_alg":"SHA-384","protocol":"SDI_PROTOCOL_v1","agent_id":"SDI-XXXXXXXXXXXX (or SESSION_LOCAL)","sovereign_hash":"0x... (optional; external mint-agent)","model_version":"STRING — actual generating model string returned by API (authoritative field for which model generated this entry)","ledger":{"type":"EPISODIC|PRECEDENT|CALIBRATION|AUDIT|SYSTEM|MEMORY_COMPILE|SUPER_DER","parent_hash":"GENESIS|0x...|SESSION_LOCAL","expected_parent_hash":"OPTIONAL_CAS_GUARD"}},"DECISION_INTENT":{"context_framing":"STRING — why this reasoning is happening","intent_statement":"STRING — what is being decided or answered","role":"STRING — operator or system role","tier":"Strategic|Operational|Tactical","impact_domain":"LOW_RISK | HUMAN_WELFARE | SAFETY_CRITICAL | FINANCIAL | LEGAL — determines which compile gate proxy checks are activated."},"QUESTION_LOGIC":{"strategic_question":"STRING","sub_questions":[{"id":"q1","prompt":"STRING","linked_signal_ids":["signal_01"],"success_standard":{"definition":"STRING — what constitutes sufficient evidence to answer this sub-question","framework_source":{"name":"STRING — governance framework informing this criterion","retrieved_utc":"ISO_8601 — required when source is external","url":"STRING — retrievable URL if available"}}}]},"DECISION_SYNTAX":{"strategic_question_id":"Q-XXXX (optional)","sub_question_grammar":[{"id":"q1","pattern":"THRESHOLD|COMPARISON|BOOLEAN_CHECK|EXISTS|WITHIN_WINDOW","lhs":"STRING","op":"==|>=|<=|>|<|CONTAINS|MEETS|WITHIN","rhs":"NUMBER|STRING|BOOLEAN","window":"STRING_OPTIONAL"}]},"SUCCESS_STANDARD":{"definition":"STRING — what counts as success","threshold_type":"Binary|Numeric|Time-bound|Qualitative|Qualitative/Deterministic","operator":"==|>=|<=|>|<|CONTAINS|MEETS|WITHIN","target":"NUMBER|STRING|BOOLEAN","window":"STRING_OPTIONAL","framework_source":{"name":"STRING — governance framework informing this success criterion","retrieved_utc":"ISO_8601","url":"STRING"},"audit_standard":{"definition":"STRING — how a human can reconstruct the decision from this record alone","required_artifacts":["ARRAY of strings"],"pass_fail_rule":"STRING"}},"SYSTEM_INPUT":{"inputs":[{"signal_id":"signal_01","source_system":"HUMAN|SYSTEM|EXTERNAL|DOC|DB|WEB|PEER","raw_value":"ANY — quote, number, doc snippet, reference","captured_utc":"ISO_8601","provenance":"STRING — who, what, where, how captured","citation":{"title":"STRING — document or source title","url":"STRING — retrievable URL (required when source_system is WEB or EXTERNAL)","retrieved_utc":"ISO_8601 — date of retrieval (required when source_system is WEB or EXTERNAL)","version_or_date":"STRING — document version or publication date if known"},"insight_dimensions":{"actionability":"1-5","relevance":"1-5","predictive_value":"1-5","specificity":"1-5","measurability":"1-5"},"insight_strength":"1-5 — must equal min of all 5 dimensions (deterministically computed)","scoring_rule":"insight_strength = min(actionability, relevance, predictive_value, specificity, measurability)","signal_useful_rule":"signal_useful = true if relevance >= 4, even if insight_strength <= 2","evidence_grade":"OPTIONAL — future: A/B/C/D/F"}]},"ILJO":{"INTENT":"STRING — anchored decision objective (Sign in triadic structure)","LOGIC":"STRING — objective derivations grounded in SYSTEM_INPUT signals. No policy or decision language. Object relationship in triadic closure.","JUDGMENT":"STRING — bounded verdict under SOVEREIGNTY and PRIMUM. Anchors referenced explicitly. Stop decisions acknowledged. The Interpretant.","OUTCOME":"STRING — committed state. Becomes Sign for next cycle.","GOVERNED_ANSWER":"STRING — plain prose answer readable without context. No signal shorthand. No reference IDs. The primary answer surface. Required field — will be promoted to compile error in a future protocol version.","BOTTOM_LINE":"STRING — one sentence summary of the governing conclusion. Optional but recommended.","sequence_note":"ILJO sequence is non-negotiable. Enforced by schema structure."},"GCA":{"ID":"STRING — raw candidate stream. No finality claims.","EGO":"STRING — structured SDI reasoning trace grounded in signals.","SUPEREGO":{"anchors_required":"ARRAY — governance constants this DER must honor","anchors_present":"ARRAY — governance constants the model declares are honored","note":"Declaration is Level 1. Proxy scoring is Level 2. Human JUDGMENT audit is Level 3."}},"BOUNDEDNESS":{"uncertainty":"LOW|MED|HIGH","max_uncertainty_allowed":"LOW|MED|HIGH","timebox_seconds":"NUMBER","stop_on_uncertainty":"BOOLEAN — must be true when uncertainty = HIGH (SOVEREIGNTY proxy)","stop_reason":"INSUFFICIENT_SIGNAL|HIGH_UNCERTAINTY|TIMEBOX_EXCEEDED|POLICY_BLOCK"},"OUTCOME_PLAN":{"note":"Prospective Reckoning commitment. The agent commits a forward-facing test of the current reasoning before outcomes are known. Architecturally immutable — cannot be edited or removed after commit.","planned_metrics":[{"metric":"STRING — what is being predicted or monitored","target":"STRING|NUMBER — what would constitute confirmation","measurement_method":"STRING — how this will be measured","review_window":"STRING — when to review","resolution_horizon":"short|medium|long|event-triggered — timeframe for resolution","resolution_event":"STRING — specific observable condition that constitutes resolution","rollback_condition":"STRING — required when DER involves human welfare (PRIMUM proxy)"}]},"GOVERNED_RECKONING":{"note":"Prospective Reckoning declaration. Required when prior OUTCOME_PLANs are in context and current evidence is directly relevant. The agent declares on the record what happened to prior commitments before reasoning about the new question.","declarations":[{"plan_id":"STRING — references an OUTCOME_PLAN.planned_metrics entry from a prior turn","status":"REINFORCED | CONTRADICTED | EXTENDED | INCONCLUSIVE","evidence_seq":"STRING — signal_id or ledger SEQ grounding this declaration. Required for REINFORCED and CONTRADICTED. Null only if INCONCLUSIVE.","one_sentence":"STRING — one sentence stating precisely what resolved and why","status_definitions":{"REINFORCED":"Current evidence confirms the prior reasoning is tracking correctly","CONTRADICTED":"Current evidence materially undermines the prior reasoning","EXTENDED":"Prior reasoning was correct but its scope or implications have grown","INCONCLUSIVE":"No relevant evidence in current signals — left open for a future turn"}}]},"METRICS":{"RAI":"0.0-1.0 — Reasoning Admissibility Index. Minimum 0.78 required for ledger entry.","W_RSQ":"0.0-1.0 — Weighted Reasoning Structure Quality. Largest single RAI component (weight 0.30). Measures whether LOGIC was semantically responsive to INTENT.","Jc_clt":"NUMBER — Cognitive Joule. Cognitive work density computed from five runtime-extracted operands.","cognitive_hash":"SHA-384 of six Jc operands including total tokens consumed. Independently recomputable from stored operands.","Jc":"NUMBER — tokens in committed artifact","Jp":"NUMBER — input tokens processed by model","delta_E":"NUMBER — Jp minus Jc (governance efficiency signal)","ID_tokens_est":"NUMBER","_note":"OPTIONAL — example or annotation field. Authoritative metric values are computed at runtime by external Logic Node."}}},"note":"Governance proven by SDI_DER + constants + deterministic signal scoring + compile pass."},"decision_syntax":{"patterns":["THRESHOLD","COMPARISON","BOOLEAN_CHECK","EXISTS","WITHIN_WINDOW"],"operators":["==",">=","<=",">","<","CONTAINS","MEETS","WITHIN"],"note":"Sub-questions SHOULD use pattern + lhs + op + rhs to reduce free-form drift and enable deterministic evaluation."},"governance_efficiency":{"equation":"Ec = I * (Sc x Sd)^2","S_squared_locked":"S^2 = Sc x Sd. Sc = Syntactic Constraint (per-turn compile gate enforcement depth). Sd = Substrate Density (longitudinal substrate quality at zero interpretive overhead).","cognitive_joule":"Jc_clt — the computational work required to collapse probabilistic inference variance into a single deterministic committed output. Measured on every committed chain entry.","function":"computeCompileMetrics(der, anchorsPresent, substrateDensity) -> Ec via calculateGovernanceEnergy(tier, syntaxCompleteness, anchorTightness, substrateDensity)","status":"Proposed formalism — Sc computable from compile gate output. Sd tracked by memory compiler as chain matures."}}