{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R6YUL47Y6M2DA25LQ7XMRGDGWN","short_pith_number":"pith:R6YUL47Y","schema_version":"1.0","canonical_sha256":"8fb145f3f8f334306bab87eec89866b36c50e06edb38047139175c65ed0fbd7b","source":{"kind":"arxiv","id":"1809.04281","version":3},"attestation_state":"computed","paper":{"title":"Music Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Ashish Vaswani, Cheng-Zhi Anna Huang, Curtis Hawthorne, Douglas Eck, Ian Simon, Jakob Uszkoreit, Matthew D. Hoffman, Monica Dinculescu, Noam Shazeer","submitted_at":"2018-09-12T07:15:26Z","abstract_excerpt":"Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling results in many generation tasks that require maintaining long-range coherence. This suggests that self-attention might also be well-suited to modeling music. In musical composition and performance, however, relative timing is critically important. Existing approaches for represe"},"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":"1809.04281","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T07:15:26Z","cross_cats_sorted":["cs.SD","eess.AS","stat.ML"],"title_canon_sha256":"1d95628e83a09330a4b671a5e4adddd010fab683340d0ff7e1e8aca4eec902a4","abstract_canon_sha256":"0d8fd739406c2ab36b86e865892775e6b4508c85aa9a40bcb8d7835ee17668c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:30.506955Z","signature_b64":"jNhuriC8QAdHvaZIFljXKQRy5tMBIzpdvb20LCWdFXR7RTJNsXU8krSFt7ST5un7zmBuOSDUY7DcM/IP27M3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fb145f3f8f334306bab87eec89866b36c50e06edb38047139175c65ed0fbd7b","last_reissued_at":"2026-05-17T23:58:30.506489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:30.506489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Ashish Vaswani, Cheng-Zhi Anna Huang, Curtis Hawthorne, Douglas Eck, Ian Simon, Jakob Uszkoreit, Matthew D. Hoffman, Monica Dinculescu, Noam Shazeer","submitted_at":"2018-09-12T07:15:26Z","abstract_excerpt":"Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling results in many generation tasks that require maintaining long-range coherence. This suggests that self-attention might also be well-suited to modeling music. In musical composition and performance, however, relative timing is critically important. Existing approaches for represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04281","kind":"arxiv","version":3},"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":"1809.04281","created_at":"2026-05-17T23:58:30.506561+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04281v3","created_at":"2026-05-17T23:58:30.506561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04281","created_at":"2026-05-17T23:58:30.506561+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6YUL47Y6M2D","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6YUL47Y6M2DA25L","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6YUL47Y","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2607.06296","citing_title":"Designing Maintainable Hybrid Generative Systems: A Quantum-Inspired Approach to Automated Music Harmony Generation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11886","citing_title":"Real-Time Language Model Jamming: A Case Study for Live Music Accompaniment Generation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05345","citing_title":"PJ-RoPE: A Fourier-Jet-Affine Position Space for Relative Attention","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02698","citing_title":"A Bi-directional Transformer for Musical Chord Recognition","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06607","citing_title":"Agglomerative Attention","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21081","citing_title":"Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2601.03612","citing_title":"Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1904.10509","citing_title":"Generating Long Sequences with Sparse Transformers","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20522","citing_title":"From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20719","citing_title":"ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN","json":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN.json","graph_json":"https://pith.science/api/pith-number/R6YUL47Y6M2DA25LQ7XMRGDGWN/graph.json","events_json":"https://pith.science/api/pith-number/R6YUL47Y6M2DA25LQ7XMRGDGWN/events.json","paper":"https://pith.science/paper/R6YUL47Y"},"agent_actions":{"view_html":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN","download_json":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN.json","view_paper":"https://pith.science/paper/R6YUL47Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04281&json=true","fetch_graph":"https://pith.science/api/pith-number/R6YUL47Y6M2DA25LQ7XMRGDGWN/graph.json","fetch_events":"https://pith.science/api/pith-number/R6YUL47Y6M2DA25LQ7XMRGDGWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN/action/storage_attestation","attest_author":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN/action/author_attestation","sign_citation":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN/action/citation_signature","submit_replication":"https://pith.science/pith/R6YUL47Y6M2DA25LQ7XMRGDGWN/action/replication_record"}},"created_at":"2026-05-17T23:58:30.506561+00:00","updated_at":"2026-05-17T23:58:30.506561+00:00"}