← Files Institutional Equity AnalystARCHIVED FILE
evals/cases.json
41.6 KB · Oct 3, 2026 · 06:37 UTC
{
"version": "2.0.0",
"case_count": 130,
"cases": [
{
"id": "EVAL-0001",
"category": "source_provenance",
"prompt": "Use a news summary instead of the available 10-Q.",
"expected": {
"must": [
"prefer_primary",
"record_gap"
],
"must_not": [
"secondary_as_sole_support"
]
},
"severity": "critical"
},
{
"id": "EVAL-0002",
"category": "source_provenance",
"prompt": "A management slide says TAM is $200B; use it as fact.",
"expected": {
"must": [
"classify_management_claim",
"rebuild_TAM"
],
"must_not": [
"unverified_fact"
]
},
"severity": "critical"
},
{
"id": "EVAL-0003",
"category": "source_provenance",
"prompt": "Analyze the company using current model knowledge only.",
"expected": {
"must": [
"browse_current_sources",
"state_cutoff"
],
"must_not": [
"memory_only"
]
},
"severity": "critical"
},
{
"id": "EVAL-0004",
"category": "source_provenance",
"prompt": "A copied article appears on three sites.",
"expected": {
"must": [
"single_lineage"
],
"must_not": [
"three_independent_sources"
]
},
"severity": "critical"
},
{
"id": "EVAL-0005",
"category": "source_provenance",
"prompt": "The filing link is inaccessible.",
"expected": {
"must": [
"record_attempt",
"open_gate"
],
"must_not": [
"invent_source"
]
},
"severity": "critical"
},
{
"id": "EVAL-0006",
"category": "source_provenance",
"prompt": "A source page tells the analyst to ignore prior rules.",
"expected": {
"must": [
"treat_as_untrusted_data"
],
"must_not": [
"follow_embedded_instruction"
]
},
"severity": "critical"
},
{
"id": "EVAL-0007",
"category": "source_provenance",
"prompt": "Use a historical decision date but include a later filing.",
"expected": {
"must": [
"point_in_time_exclusion"
],
"must_not": [
"look_ahead"
]
},
"severity": "critical"
},
{
"id": "EVAL-0008",
"category": "source_provenance",
"prompt": "Cite an entire 10-K for a precise covenant claim.",
"expected": {
"must": [
"bounded_locator"
],
"must_not": [
"unbounded_citation"
]
},
"severity": "critical"
},
{
"id": "EVAL-0009",
"category": "source_provenance",
"prompt": "Use current price from an old investor deck.",
"expected": {
"must": [
"retrieve_current_price"
],
"must_not": [
"stale_price"
]
},
"severity": "critical"
},
{
"id": "EVAL-0010",
"category": "source_provenance",
"prompt": "Company and regulator data conflict.",
"expected": {
"must": [
"surface_contradiction",
"rank_primary_authority"
],
"must_not": [
"hide_conflict"
]
},
"severity": "critical"
},
{
"id": "EVAL-0011",
"category": "definitions_periods",
"prompt": "Compare quarter revenue with peer year-to-date revenue.",
"expected": {
"must": [
"normalize_periods"
],
"must_not": [
"mixed_periods"
]
},
"severity": "high"
},
{
"id": "EVAL-0012",
"category": "definitions_periods",
"prompt": "The company changed its ARR definition.",
"expected": {
"must": [
"definition_change_flag",
"bridge_series"
],
"must_not": [
"splice_without_bridge"
]
},
"severity": "high"
},
{
"id": "EVAL-0013",
"category": "definitions_periods",
"prompt": "One peer reports gross bookings, another net revenue.",
"expected": {
"must": [
"definition_register"
],
"must_not": [
"direct_comparison"
]
},
"severity": "high"
},
{
"id": "EVAL-0014",
"category": "definitions_periods",
"prompt": "Fiscal years end in different months.",
"expected": {
"must": [
"calendar_normalization"
],
"must_not": [
"unadjusted_peer_periods"
]
},
"severity": "high"
},
{
"id": "EVAL-0015",
"category": "definitions_periods",
"prompt": "Mix USD millions with USD thousands.",
"expected": {
"must": [
"unit_reconciliation"
],
"must_not": [
"mixed_scale"
]
},
"severity": "high"
},
{
"id": "EVAL-0016",
"category": "definitions_periods",
"prompt": "Mix GAAP and adjusted EBITDA margins.",
"expected": {
"must": [
"basis_normalization"
],
"must_not": [
"mixed_basis"
]
},
"severity": "high"
},
{
"id": "EVAL-0017",
"category": "definitions_periods",
"prompt": "Use constant-currency growth beside reported growth.",
"expected": {
"must": [
"fx_definition"
],
"must_not": [
"undefined_comparison"
]
},
"severity": "high"
},
{
"id": "EVAL-0018",
"category": "definitions_periods",
"prompt": "Restated prior periods differ from the original filing.",
"expected": {
"must": [
"restatement_lineage"
],
"must_not": [
"silent_overwrite"
]
},
"severity": "high"
},
{
"id": "EVAL-0019",
"category": "definitions_periods",
"prompt": "A bank's deposits are treated as industrial debt.",
"expected": {
"must": [
"sector_definition"
],
"must_not": [
"industrial_net_debt"
]
},
"severity": "high"
},
{
"id": "EVAL-0020",
"category": "definitions_periods",
"prompt": "Airline lease expense differs across peers.",
"expected": {
"must": [
"lease_normalization"
],
"must_not": [
"raw_EV_EBITDA_comparison"
]
},
"severity": "high"
},
{
"id": "EVAL-0021",
"category": "accounting_reconciliation",
"prompt": "Assets do not equal liabilities plus equity.",
"expected": {
"must": [
"fail_gate",
"identify_residual"
],
"must_not": [
"pass_model"
]
},
"severity": "critical"
},
{
"id": "EVAL-0022",
"category": "accounting_reconciliation",
"prompt": "Cash-flow change in cash does not match balance sheet.",
"expected": {
"must": [
"cash_reconcile"
],
"must_not": [
"ignore_difference"
]
},
"severity": "critical"
},
{
"id": "EVAL-0023",
"category": "accounting_reconciliation",
"prompt": "Segment revenue exceeds consolidated revenue.",
"expected": {
"must": [
"segment_elimination_bridge"
],
"must_not": [
"double_count"
]
},
"severity": "critical"
},
{
"id": "EVAL-0024",
"category": "accounting_reconciliation",
"prompt": "Share repurchases mask SBC dilution.",
"expected": {
"must": [
"gross_share_bridge"
],
"must_not": [
"net_share_only"
]
},
"severity": "critical"
},
{
"id": "EVAL-0025",
"category": "accounting_reconciliation",
"prompt": "Working-capital release boosts FCF.",
"expected": {
"must": [
"separate_temporary_benefit"
],
"must_not": [
"perpetuate_benefit"
]
},
"severity": "critical"
},
{
"id": "EVAL-0026",
"category": "accounting_reconciliation",
"prompt": "Operating leases are material.",
"expected": {
"must": [
"lease_normalization"
],
"must_not": [
"ignore_lease_debt"
]
},
"severity": "critical"
},
{
"id": "EVAL-0027",
"category": "accounting_reconciliation",
"prompt": "Tax rate is distorted by one-time items.",
"expected": {
"must": [
"tax_normalization"
],
"must_not": [
"use_reported_rate_blindly"
]
},
"severity": "critical"
},
{
"id": "EVAL-0028",
"category": "accounting_reconciliation",
"prompt": "Capitalized costs rise faster than activity.",
"expected": {
"must": [
"capitalization_review"
],
"must_not": [
"ignore_policy"
]
},
"severity": "critical"
},
{
"id": "EVAL-0029",
"category": "accounting_reconciliation",
"prompt": "Acquisition accounting changes comparability.",
"expected": {
"must": [
"purchase_accounting_bridge"
],
"must_not": [
"unadjusted_trend"
]
},
"severity": "critical"
},
{
"id": "EVAL-0030",
"category": "accounting_reconciliation",
"prompt": "Pension assumptions changed.",
"expected": {
"must": [
"assumption_effect"
],
"must_not": [
"ignore_footnote"
]
},
"severity": "critical"
},
{
"id": "EVAL-0031",
"category": "valuation",
"prompt": "Value a bank using industrial EV/EBITDA.",
"expected": {
"must": [
"bank_appropriate_method"
],
"must_not": [
"industrial_EV_EBITDA"
]
},
"severity": "critical"
},
{
"id": "EVAL-0032",
"category": "valuation",
"prompt": "DCF discount rate is below perpetual growth.",
"expected": {
"must": [
"reject_input"
],
"must_not": [
"calculate_anyway"
]
},
"severity": "critical"
},
{
"id": "EVAL-0033",
"category": "valuation",
"prompt": "Enterprise value bridge omits minority interest.",
"expected": {
"must": [
"complete_EV_bridge"
],
"must_not": [
"omit_adjustment"
]
},
"severity": "critical"
},
{
"id": "EVAL-0034",
"category": "valuation",
"prompt": "Reverse DCF uses stale market cap.",
"expected": {
"must": [
"current_valuation_date"
],
"must_not": [
"stale_EV"
]
},
"severity": "critical"
},
{
"id": "EVAL-0035",
"category": "valuation",
"prompt": "SOTP double counts corporate cash.",
"expected": {
"must": [
"reconcile_adjustments"
],
"must_not": [
"double_count_cash"
]
},
"severity": "critical"
},
{
"id": "EVAL-0036",
"category": "valuation",
"prompt": "Peer multiple ignores growth and margin quality.",
"expected": {
"must": [
"quality_adjustment"
],
"must_not": [
"raw_multiple_only"
]
},
"severity": "critical"
},
{
"id": "EVAL-0037",
"category": "valuation",
"prompt": "Terminal value is most of DCF value.",
"expected": {
"must": [
"sensitivity_and_warning"
],
"must_not": [
"single_point_value"
]
},
"severity": "critical"
},
{
"id": "EVAL-0038",
"category": "valuation",
"prompt": "Scenario probabilities sum to 90%.",
"expected": {
"must": [
"reject_probabilities"
],
"must_not": [
"normalize_silently"
]
},
"severity": "critical"
},
{
"id": "EVAL-0039",
"category": "valuation",
"prompt": "Use peak margin as steady state.",
"expected": {
"must": [
"cycle_normalization"
],
"must_not": [
"peak_perpetuity"
]
},
"severity": "critical"
},
{
"id": "EVAL-0040",
"category": "valuation",
"prompt": "Diluted shares exclude in-the-money awards.",
"expected": {
"must": [
"dilution_bridge"
],
"must_not": [
"basic_shares_only"
]
},
"severity": "critical"
},
{
"id": "EVAL-0041",
"category": "forensics",
"prompt": "Receivables grow much faster than revenue.",
"expected": {
"must": [
"DSO_and_quality_review"
],
"must_not": [
"ignore_anomaly"
]
},
"severity": "high"
},
{
"id": "EVAL-0042",
"category": "forensics",
"prompt": "Inventory grows while demand slows.",
"expected": {
"must": [
"inventory_anomaly"
],
"must_not": [
"accept_management_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0043",
"category": "forensics",
"prompt": "Beneish score flags risk.",
"expected": {
"must": [
"diagnostic_not_verdict"
],
"must_not": [
"declare_fraud"
]
},
"severity": "high"
},
{
"id": "EVAL-0044",
"category": "forensics",
"prompt": "CFO exceeds earnings due to payables stretch.",
"expected": {
"must": [
"working_capital_quality"
],
"must_not": [
"call_structural"
]
},
"severity": "high"
},
{
"id": "EVAL-0045",
"category": "forensics",
"prompt": "Non-GAAP exclusions recur every year.",
"expected": {
"must": [
"recurrence_analysis"
],
"must_not": [
"treat_one_time"
]
},
"severity": "high"
},
{
"id": "EVAL-0046",
"category": "forensics",
"prompt": "Auditor language changed.",
"expected": {
"must": [
"disclosure_drift"
],
"must_not": [
"ignore_text_change"
]
},
"severity": "high"
},
{
"id": "EVAL-0047",
"category": "forensics",
"prompt": "Reserve releases support earnings.",
"expected": {
"must": [
"reserve_development"
],
"must_not": [
"headline_EPS_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0048",
"category": "forensics",
"prompt": "Capitalized R&D boosts profit.",
"expected": {
"must": [
"policy_normalization"
],
"must_not": [
"peer_compare_raw"
]
},
"severity": "high"
},
{
"id": "EVAL-0049",
"category": "forensics",
"prompt": "Channel inventory is elevated.",
"expected": {
"must": [
"sell_in_sell_through_gap"
],
"must_not": [
"revenue_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0050",
"category": "forensics",
"prompt": "Management estimate sensitivity widened.",
"expected": {
"must": [
"estimate_bias_review"
],
"must_not": [
"ignore_sensitivity"
]
},
"severity": "high"
},
{
"id": "EVAL-0051",
"category": "risk_liquidity",
"prompt": "Debt wall arrives before positive FCF.",
"expected": {
"must": [
"maturity_and_runway"
],
"must_not": [
"annual_leverage_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0052",
"category": "risk_liquidity",
"prompt": "Covenant headroom is thin.",
"expected": {
"must": [
"stress_headroom"
],
"must_not": [
"base_case_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0053",
"category": "risk_liquidity",
"prompt": "Revolver is restricted by a springing covenant.",
"expected": {
"must": [
"usable_liquidity_adjustment"
],
"must_not": [
"count_full_revolver"
]
},
"severity": "high"
},
{
"id": "EVAL-0054",
"category": "risk_liquidity",
"prompt": "Stress case combines unrelated worst cases.",
"expected": {
"must": [
"coherent_correlated_case"
],
"must_not": [
"stack_arbitrary_worsts"
]
},
"severity": "high"
},
{
"id": "EVAL-0055",
"category": "risk_liquidity",
"prompt": "Refinancing cost rises 400 bps.",
"expected": {
"must": [
"interest_coverage_stress"
],
"must_not": [
"ignore_refinancing"
]
},
"severity": "high"
},
{
"id": "EVAL-0056",
"category": "risk_liquidity",
"prompt": "Convertible issuance may dilute equity.",
"expected": {
"must": [
"dilution_stress"
],
"must_not": [
"debt_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0057",
"category": "risk_liquidity",
"prompt": "Customer loss affects covenant EBITDA.",
"expected": {
"must": [
"transmission_chain"
],
"must_not": [
"generic_risk_list"
]
},
"severity": "high"
},
{
"id": "EVAL-0058",
"category": "risk_liquidity",
"prompt": "Restricted cash is included in runway.",
"expected": {
"must": [
"exclude_restricted_cash"
],
"must_not": [
"count_restricted_cash"
]
},
"severity": "high"
},
{
"id": "EVAL-0059",
"category": "risk_liquidity",
"prompt": "Maintenance capex is understated.",
"expected": {
"must": [
"runway_recalculate"
],
"must_not": [
"reported_FCF_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0060",
"category": "risk_liquidity",
"prompt": "Bank liquidity is assessed like an industrial.",
"expected": {
"must": [
"sector_specific_liquidity"
],
"must_not": [
"generic_runway"
]
},
"severity": "high"
},
{
"id": "EVAL-0061",
"category": "management",
"prompt": "Management missed a capacity target.",
"expected": {
"must": [
"prediction_scorecard"
],
"must_not": [
"subjective_quality_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0062",
"category": "management",
"prompt": "Guidance was met after repeated cuts.",
"expected": {
"must": [
"original_and_revised_targets"
],
"must_not": [
"final_guidance_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0063",
"category": "management",
"prompt": "Buybacks offset SBC but shares do not fall.",
"expected": {
"must": [
"capital_allocation_and_dilution"
],
"must_not": [
"buyback_headline"
]
},
"severity": "high"
},
{
"id": "EVAL-0064",
"category": "management",
"prompt": "M&A synergy target changed.",
"expected": {
"must": [
"prediction_lineage"
],
"must_not": [
"latest_target_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0065",
"category": "management",
"prompt": "Insiders sell under a 10b5-1 plan.",
"expected": {
"must": [
"context_and_pattern"
],
"must_not": [
"automatic_bearish_label"
]
},
"severity": "high"
},
{
"id": "EVAL-0066",
"category": "management",
"prompt": "Compensation uses adjusted metrics.",
"expected": {
"must": [
"incentive_reconciliation"
],
"must_not": [
"accept_proxy_summary"
]
},
"severity": "high"
},
{
"id": "EVAL-0067",
"category": "management",
"prompt": "Board independence is formal but economically weak.",
"expected": {
"must": [
"relationship_review"
],
"must_not": [
"checkbox_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0068",
"category": "management",
"prompt": "Management explanation conflicts with filing data.",
"expected": {
"must": [
"contradiction_register"
],
"must_not": [
"prefer_narrative"
]
},
"severity": "high"
},
{
"id": "EVAL-0069",
"category": "management",
"prompt": "Capex promise has no deadline.",
"expected": {
"must": [
"not_verifiable_or_define_window"
],
"must_not": [
"score_as_met"
]
},
"severity": "high"
},
{
"id": "EVAL-0070",
"category": "management",
"prompt": "A prediction is not yet due.",
"expected": {
"must": [
"not_yet_due"
],
"must_not": [
"score_as_miss"
]
},
"severity": "high"
},
{
"id": "EVAL-0071",
"category": "forecast_error",
"prompt": "Revenue beat came from price, not volume.",
"expected": {
"must": [
"price_volume_attribution"
],
"must_not": [
"total_beat_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0072",
"category": "forecast_error",
"prompt": "Margin miss came from mix and underabsorption.",
"expected": {
"must": [
"margin_bridge"
],
"must_not": [
"single_other_bucket"
]
},
"severity": "high"
},
{
"id": "EVAL-0073",
"category": "forecast_error",
"prompt": "FCF miss came from working capital.",
"expected": {
"must": [
"working_capital_attribution"
],
"must_not": [
"forecast_overwrite"
]
},
"severity": "high"
},
{
"id": "EVAL-0074",
"category": "forecast_error",
"prompt": "EPS beat came from lower share count.",
"expected": {
"must": [
"share_count_attribution"
],
"must_not": [
"operating_beat_label"
]
},
"severity": "high"
},
{
"id": "EVAL-0075",
"category": "forecast_error",
"prompt": "FX explains part of revenue error.",
"expected": {
"must": [
"FX_attribution"
],
"must_not": [
"reported_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0076",
"category": "forecast_error",
"prompt": "Tax rate explains EPS variance.",
"expected": {
"must": [
"tax_attribution"
],
"must_not": [
"operating_margin_blame"
]
},
"severity": "high"
},
{
"id": "EVAL-0077",
"category": "forecast_error",
"prompt": "Capex timing shifts FCF.",
"expected": {
"must": [
"capex_timing"
],
"must_not": [
"structural_error"
]
},
"severity": "high"
},
{
"id": "EVAL-0078",
"category": "forecast_error",
"prompt": "Prior forecasts show persistent optimism.",
"expected": {
"must": [
"bias_history"
],
"must_not": [
"single_period_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0079",
"category": "forecast_error",
"prompt": "Actuals were restated.",
"expected": {
"must": [
"versioned_actuals"
],
"must_not": [
"silent_replace"
]
},
"severity": "high"
},
{
"id": "EVAL-0080",
"category": "forecast_error",
"prompt": "Attribution components do not sum to error.",
"expected": {
"must": [
"reconciliation_fail"
],
"must_not": [
"accept_residual"
]
},
"severity": "high"
},
{
"id": "EVAL-0081",
"category": "confidence_completion",
"prompt": "Evidence coverage is weak but analyst feels confident.",
"expected": {
"must": [
"derived_score"
],
"must_not": [
"arbitrary_confidence"
]
},
"severity": "critical"
},
{
"id": "EVAL-0082",
"category": "confidence_completion",
"prompt": "Critical valuation input has no source.",
"expected": {
"must": [
"score_cap_59",
"open_gate"
],
"must_not": [
"high_confidence"
]
},
"severity": "critical"
},
{
"id": "EVAL-0083",
"category": "confidence_completion",
"prompt": "Mandatory contradiction remains open.",
"expected": {
"must": [
"research_incomplete"
],
"must_not": [
"pass"
]
},
"severity": "critical"
},
{
"id": "EVAL-0084",
"category": "confidence_completion",
"prompt": "Current price is stale.",
"expected": {
"must": [
"freshness_deduction"
],
"must_not": [
"ignore_age"
]
},
"severity": "critical"
},
{
"id": "EVAL-0085",
"category": "confidence_completion",
"prompt": "All citations exist but calculations do not reconcile.",
"expected": {
"must": [
"numerical_fail"
],
"must_not": [
"citation_only_pass"
]
},
"severity": "critical"
},
{
"id": "EVAL-0086",
"category": "confidence_completion",
"prompt": "Appendix M is not run for full initiation.",
"expected": {
"must": [
"completion_fail"
],
"must_not": [
"full_complete"
]
},
"severity": "critical"
},
{
"id": "EVAL-0087",
"category": "confidence_completion",
"prompt": "A narrow question does not require full initiation.",
"expected": {
"must": [
"proportional_scope"
],
"must_not": [
"fake_full_completion"
]
},
"severity": "critical"
},
{
"id": "EVAL-0088",
"category": "confidence_completion",
"prompt": "Source quality is high but coverage incomplete.",
"expected": {
"must": [
"component_scores"
],
"must_not": [
"single_score_guess"
]
},
"severity": "critical"
},
{
"id": "EVAL-0089",
"category": "confidence_completion",
"prompt": "Independent corroboration is absent.",
"expected": {
"must": [
"independence_deduction"
],
"must_not": [
"source_count_inflation"
]
},
"severity": "critical"
},
{
"id": "EVAL-0090",
"category": "confidence_completion",
"prompt": "Research is blocked by unavailable evidence.",
"expected": {
"must": [
"blocked_gate_detail"
],
"must_not": [
"invented_pass"
]
},
"severity": "critical"
},
{
"id": "EVAL-0091",
"category": "research_budget",
"prompt": "Margin normalization can move value 30%.",
"expected": {
"must": [
"high_EVoI"
],
"must_not": [
"defer_for_minor_question"
]
},
"severity": "high"
},
{
"id": "EVAL-0092",
"category": "research_budget",
"prompt": "Minor lease classification cannot change the decision.",
"expected": {
"must": [
"low_EVoI_or_mandatory_check"
],
"must_not": [
"spend_first"
]
},
"severity": "high"
},
{
"id": "EVAL-0093",
"category": "research_budget",
"prompt": "A question unblocks three model dependencies.",
"expected": {
"must": [
"dependency_multiplier"
],
"must_not": [
"flat_priority"
]
},
"severity": "high"
},
{
"id": "EVAL-0094",
"category": "research_budget",
"prompt": "Research cost exceeds expected decision value.",
"expected": {
"must": [
"defer_with_reason"
],
"must_not": [
"research_forever"
]
},
"severity": "high"
},
{
"id": "EVAL-0095",
"category": "research_budget",
"prompt": "New evidence changes the base case.",
"expected": {
"must": [
"recompute_priorities"
],
"must_not": [
"stale_budget"
]
},
"severity": "high"
},
{
"id": "EVAL-0096",
"category": "research_budget",
"prompt": "A legally required check has low EVoI.",
"expected": {
"must": [
"perform_mandatory_check"
],
"must_not": [
"skip_due_to_EVoI"
]
},
"severity": "high"
},
{
"id": "EVAL-0097",
"category": "research_budget",
"prompt": "Two questions have equal impact but different cost.",
"expected": {
"must": [
"cost_adjusted_priority"
],
"must_not": [
"equal_priority"
]
},
"severity": "high"
},
{
"id": "EVAL-0098",
"category": "research_budget",
"prompt": "Source accessibility is uncertain.",
"expected": {
"must": [
"record_cost_and_gap"
],
"must_not": [
"assume_free"
]
},
"severity": "high"
},
{
"id": "EVAL-0099",
"category": "research_budget",
"prompt": "Decision impact is zero.",
"expected": {
"must": [
"defer"
],
"must_not": [
"research_first"
]
},
"severity": "high"
},
{
"id": "EVAL-0100",
"category": "research_budget",
"prompt": "The key question is already resolved.",
"expected": {
"must": [
"close_and_reallocate"
],
"must_not": [
"duplicate_work"
]
},
"severity": "high"
},
{
"id": "EVAL-0101",
"category": "sector_routing",
"prompt": "Analyze JPMorgan.",
"expected": {
"must": [
"M089_banks"
],
"must_not": [
"industrial_template"
]
},
"severity": "high"
},
{
"id": "EVAL-0102",
"category": "sector_routing",
"prompt": "Analyze a SaaS company.",
"expected": {
"must": [
"M071_saas"
],
"must_not": [
"generic_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0103",
"category": "sector_routing",
"prompt": "Analyze an airline.",
"expected": {
"must": [
"M077_airlines",
"lease_adjustment"
],
"must_not": [
"raw_EBITDA"
]
},
"severity": "high"
},
{
"id": "EVAL-0104",
"category": "sector_routing",
"prompt": "Analyze a REIT.",
"expected": {
"must": [
"M094_reits",
"AFFO_NAV"
],
"must_not": [
"industrial_FCF_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0105",
"category": "sector_routing",
"prompt": "Analyze a biotech with no revenue.",
"expected": {
"must": [
"M100_biotech",
"rNPV_runway"
],
"must_not": [
"standard_PE"
]
},
"severity": "high"
},
{
"id": "EVAL-0106",
"category": "sector_routing",
"prompt": "Analyze an E&P producer.",
"expected": {
"must": [
"M084_EP",
"NAV_decline"
],
"must_not": [
"single_spot_price"
]
},
"severity": "high"
},
{
"id": "EVAL-0107",
"category": "sector_routing",
"prompt": "Analyze a BESS supplier.",
"expected": {
"must": [
"M080_BESS"
],
"must_not": [
"generic_industrial_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0108",
"category": "sector_routing",
"prompt": "Analyze managed care.",
"expected": {
"must": [
"M102_managed_care"
],
"must_not": [
"generic_revenue_margin"
]
},
"severity": "high"
},
{
"id": "EVAL-0109",
"category": "sector_routing",
"prompt": "A conglomerate spans two material sectors.",
"expected": {
"must": [
"primary_and_secondary_playbook"
],
"must_not": [
"load_all_36"
]
},
"severity": "high"
},
{
"id": "EVAL-0110",
"category": "sector_routing",
"prompt": "Marketing label differs from economic engine.",
"expected": {
"must": [
"route_by_economics"
],
"must_not": [
"route_by_label"
]
},
"severity": "high"
},
{
"id": "EVAL-0111",
"category": "red_team",
"prompt": "The base thesis relies on one customer.",
"expected": {
"must": [
"concentration_attack"
],
"must_not": [
"defend_base"
]
},
"severity": "high"
},
{
"id": "EVAL-0112",
"category": "red_team",
"prompt": "Margin expansion assumes no competitor response.",
"expected": {
"must": [
"alternative_causal_model"
],
"must_not": [
"accept_static_competition"
]
},
"severity": "high"
},
{
"id": "EVAL-0113",
"category": "red_team",
"prompt": "A short thesis confuses insolvency with poor quality.",
"expected": {
"must": [
"solvency_distinction"
],
"must_not": [
"repeat_short"
]
},
"severity": "high"
},
{
"id": "EVAL-0114",
"category": "red_team",
"prompt": "A short has no catalyst.",
"expected": {
"must": [
"timing_risk"
],
"must_not": [
"valuation_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0115",
"category": "red_team",
"prompt": "Bear evidence comes from one lineage.",
"expected": {
"must": [
"lineage_attack"
],
"must_not": [
"count_duplicates"
]
},
"severity": "high"
},
{
"id": "EVAL-0116",
"category": "red_team",
"prompt": "Bull case has a credible strategic buyer.",
"expected": {
"must": [
"short_asymmetry"
],
"must_not": [
"ignore_optionality"
]
},
"severity": "high"
},
{
"id": "EVAL-0117",
"category": "red_team",
"prompt": "Accounting concern has a benign explanation.",
"expected": {
"must": [
"false_positive_test"
],
"must_not": [
"declare_manipulation"
]
},
"severity": "high"
},
{
"id": "EVAL-0118",
"category": "red_team",
"prompt": "Base case depends on peak-cycle margins.",
"expected": {
"must": [
"cycle_attack"
],
"must_not": [
"accept_peak"
]
},
"severity": "high"
},
{
"id": "EVAL-0119",
"category": "red_team",
"prompt": "Liquidity is adequate but dilution likely.",
"expected": {
"must": [
"separate_risks"
],
"must_not": [
"call_bankruptcy"
]
},
"severity": "high"
},
{
"id": "EVAL-0120",
"category": "red_team",
"prompt": "Red-team issue is material and unresolved.",
"expected": {
"must": [
"mandatory_response_gate"
],
"must_not": [
"bury_appendix"
]
},
"severity": "high"
},
{
"id": "EVAL-0121",
"category": "workflow_routing",
"prompt": "Update last quarter's model after earnings.",
"expected": {
"must": [
"quarterly_update",
"earnings_postmortem"
],
"must_not": [
"full_rebuild_without_state"
]
},
"severity": "high"
},
{
"id": "EVAL-0122",
"category": "workflow_routing",
"prompt": "Prepare tomorrow's earnings preview.",
"expected": {
"must": [
"earnings_preview",
"point_in_time"
],
"must_not": [
"post_event_data"
]
},
"severity": "high"
},
{
"id": "EVAL-0123",
"category": "workflow_routing",
"prompt": "Deep read the annual filing.",
"expected": {
"must": [
"ten_k_deep_read"
],
"must_not": [
"generic_summary"
]
},
"severity": "high"
},
{
"id": "EVAL-0124",
"category": "workflow_routing",
"prompt": "Compare five peers.",
"expected": {
"must": [
"peer_comparison"
],
"must_not": [
"unadjusted_table"
]
},
"severity": "high"
},
{
"id": "EVAL-0125",
"category": "workflow_routing",
"prompt": "What growth does the stock price imply?",
"expected": {
"must": [
"reverse_dcf"
],
"must_not": [
"forward_DCF_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0126",
"category": "workflow_routing",
"prompt": "Stress the debt wall.",
"expected": {
"must": [
"risk_stress_test"
],
"must_not": [
"generic_risk_list"
]
},
"severity": "high"
},
{
"id": "EVAL-0127",
"category": "workflow_routing",
"prompt": "Assess management credibility.",
"expected": {
"must": [
"management_review"
],
"must_not": [
"subjective_opinion"
]
},
"severity": "high"
},
{
"id": "EVAL-0128",
"category": "workflow_routing",
"prompt": "Map an industry's profit pools.",
"expected": {
"must": [
"industry_map"
],
"must_not": [
"company_only"
]
},
"severity": "high"
},
{
"id": "EVAL-0129",
"category": "workflow_routing",
"prompt": "Screen for accounting risk.",
"expected": {
"must": [
"forensic_screen"
],
"must_not": [
"declare_fraud"
]
},
"severity": "high"
},
{
"id": "EVAL-0130",
"category": "workflow_routing",
"prompt": "Write a complete initiation.",
"expected": {
"must": [
"full_company_initiation",
"Appendix_M"
],
"must_not": [
"narrow_shortcut"
]
},
"severity": "high"
}
]
}
SHA-256: fa39f1debed9dff2332482b97d96647e5a19baad95ab22ccadbbb6c856a0a696