// BURT-IMMA Constraint Graph
// Visualize with: dot -Tpng constraint_graph.dot -o constraint_graph.png
// Or: dot -Tsvg constraint_graph.dot -o constraint_graph.svg

digraph BURT_IMMA {
    // Global graph attributes
    rankdir=TB;
    fontname="Helvetica";
    fontsize=12;
    label="BURT-IMMA Constraint Graph\nProject: BURT-IMMA | Contact: jessica@collectivekitty.com | License: BSL-1.1";
    labelloc=t;
    compound=true;
    nodesep=0.8;
    ranksep=1.0;

    // Node defaults
    node [
        shape=box,
        style="rounded,filled",
        fontname="Helvetica",
        fontsize=10,
        fillcolor="#E8F4FD",
        color="#2C3E50"
    ];

    // Edge defaults
    edge [
        fontname="Helvetica",
        fontsize=8,
        color="#34495E"
    ];

    // =============================================
    // Subgraph: Feature Extraction
    // =============================================
    subgraph cluster_feature_extraction {
        label="Feature Extraction";
        style="rounded,dashed";
        color="#3498DB";
        fontcolor="#3498DB";
        fontsize=11;

        Input [
            label="Input\n[batch, seq_len]",
            shape=ellipse,
            fillcolor="#AED6F1"
        ];

        SmoothLeaky [
            label="SmoothLeaky\nActivation\n\nk=1.0, alpha=0.01\nSmooth for EP",
            fillcolor="#D4EFDF"
        ];

        GatesNorm [
            label="GatesNorm\nNormalization\n\ngamma, beta learnable\nPer-expert dim",
            fillcolor="#D4EFDF"
        ];
    }

    // =============================================
    // Subgraph: Memory System
    // =============================================
    subgraph cluster_memory_system {
        label="Memory System";
        style="rounded,dashed";
        color="#E74C3C";
        fontcolor="#E74C3C";
        fontsize=11;

        CIFGMemory [
            label="CIFGMemory\n\nC_global: [d, d]\nC_expert: [K, d_e, d_e]\nf = sigma(W_f * [h,x])\nC_new = f*C + (1-f)*candidate",
            fillcolor="#FADBD8",
            shape=box3d
        ];
    }

    // =============================================
    // Subgraph: Routing
    // =============================================
    subgraph cluster_routing {
        label="Routing (Sparse MoE)";
        style="rounded,dashed";
        color="#F39C12";
        fontcolor="#F39C12";
        fontsize=11;

        GatesRouter [
            label="GatesRouter\n\ntop_k=2\nentropy_bound=0.20\nL1 sparsity",
            fillcolor="#FEF9E7"
        ];

        Expert1 [
            label="Expert 1\n[d_expert=256]",
            fillcolor="#FDF2E9"
        ];

        Expert2 [
            label="Expert 2\n[d_expert=256]",
            fillcolor="#FDF2E9"
        ];

        Expert3 [
            label="Expert 3\n[d_expert=256]",
            fillcolor="#FDF2E9"
        ];

        Expert4 [
            label="Expert 4\n[d_expert=256]",
            fillcolor="#FDF2E9"
        ];
    }

    // =============================================
    // Subgraph: Output Head
    // =============================================
    subgraph cluster_output_head {
        label="Output Head";
        style="rounded,dashed";
        color="#8E44AD";
        fontcolor="#8E44AD";
        fontsize=11;

        InductionHeads [
            label="Superpositioned\nInduction Heads\n\nnum_heads=8\nCopy pattern detection\nMemory superposition",
            fillcolor="#E8DAEF"
        ];

        QInterference [
            label="Quantum\nInterference\nResolver\n\nAmplitude combination\nConstructive/destructive",
            fillcolor="#E8DAEF"
        ];

        Output [
            label="Output\n[batch, seq_len, vocab]\n\nConstrained Softmax\nentropy <= 0.20",
            shape=ellipse,
            fillcolor="#D2B4DE"
        ];
    }

    // =============================================
    // Data Flow Edges
    // =============================================

    // Feature extraction flow
    Input -> SmoothLeaky [
        label="embed + pos_encode"
    ];

    SmoothLeaky -> GatesNorm [
        label="activated features"
    ];

    // Memory interaction
    GatesNorm -> CIFGMemory [
        label="h (hidden state)",
        style=bold
    ];

    CIFGMemory -> InductionHeads [
        label="memory context\nC_global @ h",
        color="#E74C3C"
    ];

    // Routing flow
    GatesNorm -> GatesRouter [
        label="routing logits"
    ];

    GatesRouter -> Expert1 [
        label="alpha_1",
        style=dashed,
        constraint=false
    ];

    GatesRouter -> Expert2 [
        label="alpha_2",
        style=dashed,
        constraint=false
    ];

    GatesRouter -> Expert3 [
        label="alpha_3",
        style=dashed,
        constraint=false
    ];

    GatesRouter -> Expert4 [
        label="alpha_4",
        style=dashed,
        constraint=false
    ];

    // Expert to interference
    Expert1 -> QInterference [
        label="out_1"
    ];

    Expert2 -> QInterference [
        label="out_2"
    ];

    Expert3 -> QInterference [
        label="out_3"
    ];

    Expert4 -> QInterference [
        label="out_4"
    ];

    // Expert memory update
    Expert1 -> CIFGMemory [
        label="update C_expert[1]",
        style=dotted,
        color="#E74C3C",
        constraint=false
    ];

    Expert2 -> CIFGMemory [
        label="update C_expert[2]",
        style=dotted,
        color="#E74C3C",
        constraint=false
    ];

    // Induction heads
    GatesNorm -> InductionHeads [
        label="Q, K, V projections"
    ];

    // Output assembly
    InductionHeads -> QInterference [
        label="attention output",
        style=bold
    ];

    QInterference -> Output [
        label="resolved output",
        style=bold
    ];

    // Feedback (memory write from output)
    Output -> CIFGMemory [
        label="memory write\n(CIFG gated)",
        style=dotted,
        color="#E74C3C",
        dir=back,
        constraint=false
    ];

    // =============================================
    // Constraint Annotations
    // =============================================

    // Constraint nodes (diamond shape)
    node [
        shape=diamond,
        fillcolor="#FDEBD0",
        color="#D35400",
        fontsize=9,
        width=1.5,
        height=0.8
    ];

    C_entropy [
        label="ENTROPY\n<= 0.20 nats"
    ];

    C_spectral [
        label="SPECTRAL\nsigma_max <= 0.95"
    ];

    C_huntington [
        label="HUNTINGTON\nPostulates"
    ];

    // Constraint edges
    C_entropy -> GatesRouter [
        style=bold,
        color="#D35400",
        label="enforced",
        dir=both
    ];

    C_entropy -> Output [
        style=bold,
        color="#D35400",
        label="enforced",
        dir=both
    ];

    C_spectral -> CIFGMemory [
        style=bold,
        color="#D35400",
        label="sigma_max(C)",
        dir=both
    ];

    C_spectral -> Expert1 [
        style=bold,
        color="#D35400",
        label="sigma_max(W)",
        dir=both
    ];

    C_spectral -> InductionHeads [
        style=bold,
        color="#D35400",
        label="sigma_max(W_QKV)",
        dir=both
    ];

    C_huntington -> QInterference [
        style=bold,
        color="#D35400",
        label="Boolean lattice",
        dir=both
    ];

    // =============================================
    // Legend
    // =============================================
    subgraph cluster_legend {
        label="Legend";
        style="rounded";
        color="#7F8C8D";
        fontcolor="#7F8C8D";
        fontsize=10;

        node [shape=plaintext, fillcolor=white, fontsize=8];

        legend [label=<
            <TABLE BORDER="0" CELLBORDER="1" CELLSPACING="0" CELLPADDING="4">
                <TR><TD COLSPAN="2"><B>Edge Styles</B></TD></TR>
                <TR><TD>Solid bold</TD><TD>Primary data flow</TD></TR>
                <TR><TD>Dashed</TD><TD>Routing decisions</TD></TR>
                <TR><TD>Dotted (red)</TD><TD>Memory updates</TD></TR>
                <TR><TD>Bold (orange)</TD><TD>Constraint enforcement</TD></TR>
                <TR><TD COLSPAN="2"><B>Constraints</B></TD></TR>
                <TR><TD>entropy_bound</TD><TD>0.20 nats</TD></TR>
                <TR><TD>lambda_max</TD><TD>0.95</TD></TR>
                <TR><TD>huntington</TD><TD>true (all postulates)</TD></TR>
            </TABLE>
        >];
    }
}