graph_block_shuffle — CONNGRAPH `dimension` op

• Data kinds: conn_graph × labels → conn_graph

• Call: import fullseye as fs; fs.ledger.graph_block_shuffle(W: 'Any', labels: 'Any', seed: 'int' = 0) -> 'np.ndarray' (to call the implementation directly, import conngraph; conngraph.graph_block_shuffle(W: 'Any', labels: 'Any', seed: 'int' = 0) -> 'np.ndarray'; from the registry, opsconngraph.get("graph_block_shuffle"))

Usage

> This operator's description has not been translated yet. The original text follows as it is.

層(ラベル)のブロックごとに送り手を混ぜた対照の `conn_graph`: 各受け手が受ける重みの多重集合と

層間の総結線量は保ったまま、「誰から」だけを壊す。

`graph_degree_preserving_shuffle` が全体の次数列を保つのに対し、こちらは層構造を保つ(脳 → 首 → 腹髄 →

筋のブロックは動かさず、ブロックの中で行を並べ替える)。層の大きさと収束(fan-in)の効果を残して

「配線の特異性」だけを消した対照として使う。同じ `seed` で再現。

Detailed usage guide

• conngraph family guide

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

• The canonical algorithm (author, year) and its uses are named in the family usage guide above.

Runnable examples (verified samples that actually call this op)

• poc_connectome_motor_bottleneck — py -3.11 examples/poc_connectome_motor_bottleneck.py

Ops the type connects to (they accept `conn_graph` as input)

graph_degree_preserving_shuffle · graph_binarize · graph_degree_table · graph_clustering_coefficient · graph_betweenness · graph_laplacian_spectrum · graph_spectral_radius · graph_components

Same category (`dimension`)

graph_layer_propagate · states_participation_ratio · states_layer_dimension

*Provenance: conngraph.py — CONNGRAPH operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

graph_block_shuffle — CONNGRAPH dimension op