{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NMDGLB7TSVDXGO74ERHBOKKMWM","short_pith_number":"pith:NMDGLB7T","schema_version":"1.0","canonical_sha256":"6b066587f39547733bfc244e17294cb3190ec872278de5daed1e2d0bf70c03af","source":{"kind":"arxiv","id":"1703.10847","version":2},"attestation_state":"computed","paper":{"title":"MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Li-Chia Yang, Szu-Yu Chou, Yi-Hsuan Yang","submitted_at":"2017-03-31T10:59:58Z","abstract_excerpt":"Most existing neural network models for music generation use recurrent neural networks. However, the recent WaveNet model proposed by DeepMind shows that convolutional neural networks (CNNs) can also generate realistic musical waveforms in the audio domain. Following this light, we investigate using CNNs for generating melody (a series of MIDI notes) one bar after another in the symbolic domain. In addition to the generator, we use a discriminator to learn the distributions of melodies, making it a generative adversarial network (GAN). Moreover, we propose a novel conditional mechanism to expl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.10847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-31T10:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2dd55f15aa32aeabc7db1616ffb0a05c9d3ee0419a2a159e84d4655be02c354","abstract_canon_sha256":"7ce44b93128ad32ab4e3157f9bd0b809a5d3db45f41d2c288c406085917b2524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:06.500942Z","signature_b64":"9kghumHVsydB3gO1HduCIBe2z57Dqjx2HlwCYuHHnUEP9b9Qe2N2AtHAHNQ5wZueVFGl40bDbEUtDTpWxfjUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b066587f39547733bfc244e17294cb3190ec872278de5daed1e2d0bf70c03af","last_reissued_at":"2026-05-18T00:40:06.500327Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:06.500327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Li-Chia Yang, Szu-Yu Chou, Yi-Hsuan Yang","submitted_at":"2017-03-31T10:59:58Z","abstract_excerpt":"Most existing neural network models for music generation use recurrent neural networks. However, the recent WaveNet model proposed by DeepMind shows that convolutional neural networks (CNNs) can also generate realistic musical waveforms in the audio domain. Following this light, we investigate using CNNs for generating melody (a series of MIDI notes) one bar after another in the symbolic domain. In addition to the generator, we use a discriminator to learn the distributions of melodies, making it a generative adversarial network (GAN). Moreover, we propose a novel conditional mechanism to expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10847","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.10847","created_at":"2026-05-18T00:40:06.500427+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10847v2","created_at":"2026-05-18T00:40:06.500427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10847","created_at":"2026-05-18T00:40:06.500427+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMDGLB7TSVDX","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMDGLB7TSVDXGO74","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMDGLB7T","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1906.09972","citing_title":"Classical Music Prediction and Composition by means of Variational Autoencoders","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01607","citing_title":"MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21081","citing_title":"Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03612","citing_title":"Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM","json":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM.json","graph_json":"https://pith.science/api/pith-number/NMDGLB7TSVDXGO74ERHBOKKMWM/graph.json","events_json":"https://pith.science/api/pith-number/NMDGLB7TSVDXGO74ERHBOKKMWM/events.json","paper":"https://pith.science/paper/NMDGLB7T"},"agent_actions":{"view_html":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM","download_json":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM.json","view_paper":"https://pith.science/paper/NMDGLB7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10847&json=true","fetch_graph":"https://pith.science/api/pith-number/NMDGLB7TSVDXGO74ERHBOKKMWM/graph.json","fetch_events":"https://pith.science/api/pith-number/NMDGLB7TSVDXGO74ERHBOKKMWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM/action/storage_attestation","attest_author":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM/action/author_attestation","sign_citation":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM/action/citation_signature","submit_replication":"https://pith.science/pith/NMDGLB7TSVDXGO74ERHBOKKMWM/action/replication_record"}},"created_at":"2026-05-18T00:40:06.500427+00:00","updated_at":"2026-05-18T00:40:06.500427+00:00"}