Critique: Multi-Lens Dialectical Refinement

Mode Selection

Automatic Mode Detection

def select_mode(query: str) -> Mode:
    """
    Select critique depth based on query characteristics.
    
    QUICK:  Simple claims, factual questions, narrow scope
    STANDARD: Moderate complexity, clear domain, some nuance
    FULL:   Complex arguments, multiple stakeholders, high stakes
    """
    indicators = {
        "quick": [
            len(query) < 200,
            single_claim(query),
            factual_verifiable(query),
            low_controversy(query)
        ],
        "full": [
            len(query) > 1000,
            multi_stakeholder(query),
            ethical_implications(query),
            policy_recommendation(query),
            high_stakes_decision(query)
        ]
    }
    
    if sum(indicators["quick"]) >= 3:
        return Mode.QUICK
    elif sum(indicators["full"]) >= 2:
        return Mode.FULL
    else:
        return Mode.STANDARD

Mode Specifications

Manual Triggers

Evaluative Lenses

Five orthogonal perspectives designed for comprehensive coverage with minimal overlap:

Lens Independence Validation

Lenses target distinct failure modes:

• S catches: invalid inference, circular reasoning, equivocation
• E catches: weak evidence, unfalsifiable claims, cherry-picking
• O catches: overgeneralization, edge cases, context dependence
• A catches: stronger alternatives, unconsidered objections
• P catches: implementation barriers, unintended consequences

Overlap detection: If two lenses identify the same issue, it's either a genuine high-priority concern (reinforce) or a lens calibration problem (investigate).

Execution Protocol

Φ0: Classification & Mode Selection

def classify_and_configure(query: str) -> Config:
    mode = select_mode(query)
    
    configs = {
        Mode.QUICK: {
            "lenses": ["S", "E", "A"],
            "cross_eval": False,
            "cycles": 1,
            "threshold": 0.85,
            "token_budget": 800
        },
        Mode.STANDARD: {
            "lenses": ["S", "E", "O", "A", "P"],
            "cross_eval": "selective",  # 10 highest-value cells
            "cycles": 2,
            "threshold": 0.92,
            "token_budget": 2000
        },
        Mode.FULL: {
            "lenses": ["S", "E", "O", "A", "P"],
            "cross_eval": "complete",   # All 25 cells
            "cycles": 3,
            "threshold": 0.96,
            "token_budget": 4000
        }
    }
    
    return Config(**configs[mode], mode=mode)

Output: [CRITIQUE:Φ0|mode={m}|lenses={n}|cross={type}|budget={t}]

Φ1: Thesis Generation

Generate committed response with explicit claim DAG.

Requirements:

1. State positions with falsifiable specificity
2. Build claim graph with stability ordering:
   • F (FOUNDATIONAL) — axioms, definitions (immutable after Φ1)
   • S (STRUCTURAL) — derived claims (attackable)
   • P (PERIPHERAL) — applications (most vulnerable)
3. Verify acyclicity (DAG enforcement)
4. Compute initial topology metrics

Schema: