{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5WSM7JVY6XGNNIVASLQGGDG2KR","short_pith_number":"pith:5WSM7JVY","schema_version":"1.0","canonical_sha256":"eda4cfa6b8f5ccd6a2a092e0630cda54789bf30a29d7ffdba223cddb935003b2","source":{"kind":"arxiv","id":"1906.04972","version":1},"attestation_state":"computed","paper":{"title":"Toward Interpretable Music Tagging with Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Minz Won, Sanghyuk Chun, Xavier Serra","submitted_at":"2019-06-12T07:08:01Z","abstract_excerpt":"Self-attention is an attention mechanism that learns a representation by relating different positions in the sequence. The transformer, which is a sequence model solely based on self-attention, and its variants achieved state-of-the-art results in many natural language processing tasks. Since music composes its semantics based on the relations between components in sparse positions, adopting the self-attention mechanism to solve music information retrieval (MIR) problems can be beneficial. Hence, we propose a self-attention based deep sequence model for music tagging. The proposed architecture"},"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":"1906.04972","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-12T07:08:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5a06fac30bb5f6a45f78b3cfd079b5437fbe22e39609e3865a0d36c2d137ee79","abstract_canon_sha256":"7b8f8923448fad9010536d55522745a6b7aa6e0b2447e13c732306854d3fa26d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.899667Z","signature_b64":"y6aV/NKJmmHFnb3JZdYJBiZJig0EbWWrEUjC6u4Jcl86d/wThp+KynMmwjGS1MWK7+keEWP41fnX8OcQF8/qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eda4cfa6b8f5ccd6a2a092e0630cda54789bf30a29d7ffdba223cddb935003b2","last_reissued_at":"2026-05-17T23:43:29.899209Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.899209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Interpretable Music Tagging with Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Minz Won, Sanghyuk Chun, Xavier Serra","submitted_at":"2019-06-12T07:08:01Z","abstract_excerpt":"Self-attention is an attention mechanism that learns a representation by relating different positions in the sequence. The transformer, which is a sequence model solely based on self-attention, and its variants achieved state-of-the-art results in many natural language processing tasks. Since music composes its semantics based on the relations between components in sparse positions, adopting the self-attention mechanism to solve music information retrieval (MIR) problems can be beneficial. Hence, we propose a self-attention based deep sequence model for music tagging. The proposed architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04972","kind":"arxiv","version":1},"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":"1906.04972","created_at":"2026-05-17T23:43:29.899276+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04972v1","created_at":"2026-05-17T23:43:29.899276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04972","created_at":"2026-05-17T23:43:29.899276+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WSM7JVY6XGN","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WSM7JVY6XGNNIVA","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WSM7JVY","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR","json":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR.json","graph_json":"https://pith.science/api/pith-number/5WSM7JVY6XGNNIVASLQGGDG2KR/graph.json","events_json":"https://pith.science/api/pith-number/5WSM7JVY6XGNNIVASLQGGDG2KR/events.json","paper":"https://pith.science/paper/5WSM7JVY"},"agent_actions":{"view_html":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR","download_json":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR.json","view_paper":"https://pith.science/paper/5WSM7JVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04972&json=true","fetch_graph":"https://pith.science/api/pith-number/5WSM7JVY6XGNNIVASLQGGDG2KR/graph.json","fetch_events":"https://pith.science/api/pith-number/5WSM7JVY6XGNNIVASLQGGDG2KR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR/action/storage_attestation","attest_author":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR/action/author_attestation","sign_citation":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR/action/citation_signature","submit_replication":"https://pith.science/pith/5WSM7JVY6XGNNIVASLQGGDG2KR/action/replication_record"}},"created_at":"2026-05-17T23:43:29.899276+00:00","updated_at":"2026-05-17T23:43:29.899276+00:00"}