{
    "ok": true,
    "_meta": {
        "validator": "oppl_complex_asset_json_validator",
        "validator_version": "1.1.17",
        "captured_at_utc": "2026-08-09T18:01:59+00:00",
        "captured_unix": 1786298519,
        "input_source": "url",
        "input_url": "https://oppl.ai/llms/runs/etf/IE0003MKK4H3_strict_latest.json",
        "source_assessment_hash": "05a9963cef9f92358bc023de7cb0561ce7ad7a0692db7948cd642f7155e400f8",
        "agent_enabled": true,
        "agent_provider": "openrouter",
        "agent_model": "gpt-4.1-mini",
        "agent_temperature": 0,
        "agent_max_tokens": 1800,
        "warn_short_agent": true,
        "validator_modes": {
            "deterministic": "executed",
            "agent": "executed"
        }
    },
    "isin": "IE0003MKK4H3",
    "classification": "complex",
    "policy_mode": "strict",
    "decision_rule_applied": "strict_etf_derivative_permission_complex_rule",
    "source_classification": "complex",
    "source_decision_rule_applied": "strict_etf_synthetic_complex_rule",
    "resolution": {
        "applied": true,
        "resolution_class": "deterministic_complex_basis_repair",
        "reason_code": "unsupported_source_decision_rule_with_supported_alternative_complex_basis",
        "source_classification": "complex",
        "source_decision_rule_applied": "strict_etf_synthetic_complex_rule",
        "resolved_classification": "complex",
        "resolved_decision_rule_applied": "strict_etf_derivative_permission_complex_rule",
        "trigger_signal": "synthetic_replication",
        "supported_replacement_basis": "derivative_permission",
        "supported_replacement_basis_type": "strict_supported_permission_or_ancillary_derivative_evidence",
        "overridden_unsupported_signals": [
            "synthetic_replication"
        ],
        "supported_hard_signals": [],
        "core_derivative_evidence_count": 0,
        "swap_evidence_count": 0,
        "reassessment_required": false,
        "publishable_resolution": true,
        "message": "The source assessment is correctly Complex, but decision_rule_applied=strict_etf_synthetic_complex_rule relies on unsupported synthetic_replication. The same product evidence independently supports Complex via derivative_permission, so the validator preserves classification=complex, replaces the effective decision rule with strict_etf_derivative_permission_complex_rule, and treats the unsupported source rule/flags as an evidence-hygiene repair rather than a classification failure."
    },
    "validator_verdict": "warn",
    "publishable": true,
    "confidence": 0.78,
    "issue_count": 1,
    "issues": [
        {
            "severity": "warn",
            "code": "source_complex_decision_rule_auto_repaired",
            "message": "The source assessment is correctly Complex, but decision_rule_applied=strict_etf_synthetic_complex_rule relies on unsupported synthetic_replication. The same product evidence independently supports Complex via derivative_permission, so the validator preserves classification=complex, replaces the effective decision rule with strict_etf_derivative_permission_complex_rule, and treats the unsupported source rule/flags as an evidence-hygiene repair rather than a classification failure."
        }
    ],
    "suggested_repairs": [
        "Repair the upstream source decision rule and remove unsupported source flags so the source assessment points to the Complex feature actually proven by the evidence. No further model rerun is required unless new contradictory evidence is found."
    ],
    "reassessment": {
        "required": false,
        "reason": "deterministic_resolution_applied"
    },
    "deterministic_review": {
        "ok": true,
        "validator_type": "deterministic",
        "validator_verdict": "warn",
        "publishable": true,
        "confidence": 0.78,
        "issues": [
            {
                "severity": "warn",
                "code": "source_complex_decision_rule_auto_repaired",
                "message": "The source assessment is correctly Complex, but decision_rule_applied=strict_etf_synthetic_complex_rule relies on unsupported synthetic_replication. The same product evidence independently supports Complex via derivative_permission, so the validator preserves classification=complex, replaces the effective decision rule with strict_etf_derivative_permission_complex_rule, and treats the unsupported source rule/flags as an evidence-hygiene repair rather than a classification failure."
            }
        ],
        "suggested_repairs": [
            "Repair the upstream source decision rule and remove unsupported source flags so the source assessment points to the Complex feature actually proven by the evidence. No further model rerun is required unless new contradictory evidence is found."
        ],
        "reassessment": {
            "required": false,
            "reason": "deterministic_resolution_applied"
        },
        "resolution": {
            "applied": true,
            "resolution_class": "deterministic_complex_basis_repair",
            "reason_code": "unsupported_source_decision_rule_with_supported_alternative_complex_basis",
            "source_classification": "complex",
            "source_decision_rule_applied": "strict_etf_synthetic_complex_rule",
            "resolved_classification": "complex",
            "resolved_decision_rule_applied": "strict_etf_derivative_permission_complex_rule",
            "trigger_signal": "synthetic_replication",
            "supported_replacement_basis": "derivative_permission",
            "supported_replacement_basis_type": "strict_supported_permission_or_ancillary_derivative_evidence",
            "overridden_unsupported_signals": [
                "synthetic_replication"
            ],
            "supported_hard_signals": [],
            "core_derivative_evidence_count": 0,
            "swap_evidence_count": 0,
            "reassessment_required": false,
            "publishable_resolution": true,
            "message": "The source assessment is correctly Complex, but decision_rule_applied=strict_etf_synthetic_complex_rule relies on unsupported synthetic_replication. The same product evidence independently supports Complex via derivative_permission, so the validator preserves classification=complex, replaces the effective decision rule with strict_etf_derivative_permission_complex_rule, and treats the unsupported source rule/flags as an evidence-hygiene repair rather than a classification failure."
        },
        "decisive_signal_evidence": {
            "checked": true,
            "decision_rule_signal": null,
            "decision_rule_signal_true": null,
            "decision_rule_signal_supported": null,
            "decision_rule_matching_evidence_count": null,
            "decision_rule_matches": [],
            "true_hard_signals": [],
            "supported_hard_signals": [],
            "unsupported_hard_signals": [],
            "checks": []
        },
        "derivative_materiality": {
            "checked": true,
            "policy_mode": "strict",
            "type": "ETF",
            "ucits": true,
            "physical_replication": true,
            "swaps_signal": false,
            "synthetic_replication": false,
            "derivatives_core_strategy": false,
            "derivatives_epm_only": true,
            "derivative_evidence_count": 1,
            "swap_evidence_count": 0,
            "permission_or_ancillary_evidence_count": 1,
            "core_derivative_evidence_count": 0,
            "only_permission_or_ancillary_derivative_evidence": true,
            "supported_independent_hard_signals": []
        },
        "source_decisive_signal_evidence": {
            "checked": true,
            "decision_rule_signal": "synthetic_replication",
            "decision_rule_signal_true": true,
            "decision_rule_signal_supported": false,
            "decision_rule_matching_evidence_count": 0,
            "decision_rule_matches": [],
            "true_hard_signals": [
                "synthetic_replication"
            ],
            "supported_hard_signals": [],
            "unsupported_hard_signals": [
                "synthetic_replication"
            ],
            "checks": {
                "synthetic_replication": {
                    "signal_true": true,
                    "direct_evidence": false,
                    "matching_evidence_count": 0,
                    "decision_rule_uses_signal": true,
                    "matches": []
                }
            }
        },
        "source_derivative_materiality": {
            "checked": true,
            "policy_mode": "strict",
            "type": "ETF",
            "ucits": true,
            "physical_replication": true,
            "swaps_signal": false,
            "synthetic_replication": true,
            "derivatives_core_strategy": false,
            "derivatives_epm_only": true,
            "derivative_evidence_count": 1,
            "swap_evidence_count": 0,
            "permission_or_ancillary_evidence_count": 1,
            "core_derivative_evidence_count": 0,
            "only_permission_or_ancillary_derivative_evidence": true,
            "supported_independent_hard_signals": []
        },
        "detected_features": {
            "helo_or_core_options_overlay": false,
            "physical_replication": true,
            "physical_replication_direct_evidence": true,
            "physical_replication_evidence_count": 1,
            "has_epm_only_evidence": true,
            "has_core_derivatives_evidence": false,
            "has_generic_fdi_permission_evidence": true,
            "has_option_overlay_evidence": false
        }
    },
    "agent_review": {
        "ok": true,
        "model": "gpt-4.1-mini",
        "temperature": 0,
        "max_tokens": 1800,
        "usage": {
            "prompt_tokens": 4800,
            "completion_tokens": 377,
            "total_tokens": 5177,
            "raw": {
                "prompt_tokens": 4800,
                "completion_tokens": 377,
                "total_tokens": 5177,
                "cost": 0.0019472,
                "is_byok": false,
                "prompt_tokens_details": {
                    "cached_tokens": 1920,
                    "cache_write_tokens": 0,
                    "audio_tokens": 0,
                    "video_tokens": 0
                },
                "cost_details": {
                    "upstream_inference_cost": 0.0019472,
                    "upstream_inference_prompt_cost": 0.001344,
                    "upstream_inference_completions_cost": 0.0006032
                },
                "completion_tokens_details": {
                    "reasoning_tokens": 0,
                    "image_tokens": 0,
                    "audio_tokens": 0
                }
            }
        },
        "cost": {
            "estimated": false,
            "actual_provider_cost_available": true,
            "model": "gpt-4.1-mini",
            "prompt_tokens": 4800,
            "completion_tokens": 377,
            "total_tokens": 5177,
            "input_cost_usd": 0.001344,
            "output_cost_usd": 0.0006032,
            "estimated_cost_usd": 0.0019472,
            "pricing_basis": "openrouter_usage_cost"
        },
        "review": {
            "validator_verdict": "warn",
            "publishable": true,
            "confidence": 0.86,
            "summary": "The assessment is internally consistent and coherent with strict policy mode. The classification as complex is supported by derivative permission/ancillary use evidence, not by synthetic replication or core derivative strategy evidence. The derivatives_epm_only=true flag is supported by product-specific permission/ancillary evidence. The unsupported synthetic_replication signal and related source decision rule have been deterministically repaired to a supported derivative permission-based complex rule. No direct swap or core derivative evidence exists. The counterparty risk signal is supported by risk language. No conflict exists between derivatives_epm_only and derivatives_core_strategy flags as core strategy is false and only permission/ancillary evidence is present. The physical replication evidence is direct and consistent. The client-facing JSON is publishable as-is. Suggested repair is to clean upstream source flags and decision rule to reflect the supported derivative permission basis and remove unsupported synthetic_replication flags. Deterministic evidence resolution preserved classification=complex but replaced the unsupported source decision rule strict_etf_synthetic_complex_rule: its decision-driving synthetic_replication signal lacks direct evidence, while derivative_permission is independently supported. The effective decision rule is strict_etf_derivative_permission_complex_rule. Repair the upstream rule/flags; another model rerun is not required.",
            "issues": [
                {
                    "severity": "warn",
                    "code": "source_complex_decision_rule_auto_repaired",
                    "message": "The source assessment is correctly Complex, but decision_rule_applied=strict_etf_synthetic_complex_rule relies on unsupported synthetic_replication. The same product evidence independently supports Complex via derivative_permission, so the validator preserves classification=complex, replaces the effective decision rule with strict_etf_derivative_permission_complex_rule, and treats the unsupported source rule/flags as an evidence-hygiene repair rather than a classification failure."
                }
            ],
            "suggested_repairs": [
                "Repair the upstream source decision rule and remove unsupported source flags so the source assessment points to the Complex feature actually proven by the evidence. No further model rerun is required unless new contradictory evidence is found."
            ]
        }
    }
}