메뉴
Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/hiyenwong/ai_collection --skill graphidyom-musical-expectation-modeling명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Physics-aware end-to-end deep reinforcement learning methodology for quadcopter control with actuator dynamics modeling.
Reinforced Dreamer methodology for asymmetric reinforcement learning using latent guidance to improve world model representations and behaviors in model-based RL.
Relay On-Policy Distillation (Relay-OPD) methodology for trajectory-relayed token-level supervision to overcome prefix failure in reasoning models.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | graphidyom-musical-expectation-modeling |
| title | GraphIDyOM: A graph-native Python reimplementation of IDyOM for musical expectation modelling |
| description | Graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis. |
| authors | ["Lluc Bono Rosselló"] |
| arxiv_id | 2607.25787 |
| date | 2026-07-28 |
| categories | ["q-bio.NC","cs.SD","computational-neuroscience","music-cognition","graph-neural-networks"] |
| trigger_words | ["graphidyom","musical expectation","IDyOM","information dynamics music","graph-native music modeling","predictive memory graphs"] |
GraphIDyOM is a graph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model, which provides event-by-event estimates of uncertainty and surprise from symbolic musical sequences. The original Lisp implementation was difficult to integrate with contemporary Python workflows and had inaccessible internal memory structures. GraphIDyOM solves these issues by representing long-term and short-term predictive memories as explicit graph objects while preserving IDyOM's variable-order, multiple-viewpoint architecture.
from graphidyom import GraphIDyOM
# Initialize model with musical viewpoints
model = GraphIDyOM(viewpoints=['pitch', 'duration', 'onset'])
# Train on symbolic music sequences
training_sequences = load_midi_sequences('dataset/')
model.train(training_sequences)
# Get expectation values for new sequence
test_sequence = load_midi_sequence()
info_content, entropy = model.predict(test_sequence)
long_term_graph = model.get_long_term_memory()
short_term_graph = model.get_short_term_memory()
# Analyze learned memory as network
import networkx as nx
memory_graph = model.get_long_term_memory()
centrality_measures = nx.betweenness_centrality(memory_graph)
clustering_coefficients = nx.clustering(memory_graph)
# Project expectation values onto musical networks
expectation_projection = model.project_expectations(
sequence=test_sequence,
graph=external_music_network
)
# Recency-sensitive memory retrieval
recent_patterns = model.retrieve_recent_patterns(
context_window=16, # last 16 events
similarity_threshold=0.8
)
# Start local server for interactive use
model.start_server(port=8080)
# Now accessible via HTTP API:
# GET /predict?sequence=[...]
# GET /memory/long_term
# GET /memory/short_term
# POST /train with JSON sequences
# Convert MIDI files to symbolic sequences
from music21 import converter
import numpy as np
def midi_to_symbolic(midi_path):
score = converter.parse(midi_path)
# Extract pitch, duration, onset features
pitches = [note.pitch.midi for note in score.flat.notes]
durations = [note.duration.quarterLength for note in score.flat.notes]
onsets = [note.offset for note in score.flat.notes]
return list(zip(pitches, durations, onsets))
# Train GraphIDyOM model
sequences = [midi_to_symbolic(f) for f in training_files]
model = GraphIDyOM(viewpoints=['pitch', 'duration'])
model.train(sequences)
# Predict on test sequence
test_seq = midi_to_symbolic('beethoven_sonata.mid')
ic, entropy = model.predict(test_seq)
# Find surprising events (high information content)
surprising_events = np.where(ic > np.percentile(ic, 90))[0]
# Analyze memory structure
memory_graph = model.get_long_term_memory()
print(f"Memory contains {len(memory_graph.nodes)} patterns")
print(f"Average clustering coefficient: {nx.average_clustering(memory_graph):.3f}")
# Visualize expectation projection
projection = model.project_expectations(test_seq, external_network)
plot_network_with_expectations(external_network, projection)