{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J4TCRQG7Q65MVYJYJPSLQFCF3G","short_pith_number":"pith:J4TCRQG7","schema_version":"1.0","canonical_sha256":"4f2628c0df87bacae1384be4b81445d9bd1c1a04803d3279d832e7c2685e3237","source":{"kind":"arxiv","id":"2104.11984","version":1},"attestation_state":"computed","paper":{"title":"MusCaps: Generating Captions for Music Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Emmanouil Benetos, Gyorgy Fazekas, Ilaria Manco","submitted_at":"2021-04-24T16:34:47Z","abstract_excerpt":"Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convo"},"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":"2104.11984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-24T16:34:47Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"74c260bbda7c4f1b54f072123360e5543c567c6a7117036cc55d7dec15ca2f7b","abstract_canon_sha256":"9293aac815bf82082227e93275fbffc42c2e844a309caa8aeed455c77a5d9273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:59.792987Z","signature_b64":"TVTIZmHBJgiXRE2WAIBFL55KVrkEJBhMXk3n4yTvrwKcf31ghTN1TODSg5glOIJ2HUD2WVnkn/WYhpizicHTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f2628c0df87bacae1384be4b81445d9bd1c1a04803d3279d832e7c2685e3237","last_reissued_at":"2026-07-05T03:38:59.792625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:59.792625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MusCaps: Generating Captions for Music Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Elio Quinton, Emmanouil Benetos, Gyorgy Fazekas, Ilaria Manco","submitted_at":"2021-04-24T16:34:47Z","abstract_excerpt":"Content-based music information retrieval has seen rapid progress with the adoption of deep learning. Current approaches to high-level music description typically make use of classification models, such as in auto-tagging or genre and mood classification. In this work, we propose to address music description via audio captioning, defined as the task of generating a natural language description of music audio content in a human-like manner. To this end, we present the first music audio captioning model, MusCaps, consisting of an encoder-decoder with temporal attention. Our method combines convo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11984","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.11984/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2104.11984","created_at":"2026-07-05T03:38:59.792684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11984v1","created_at":"2026-07-05T03:38:59.792684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11984","created_at":"2026-07-05T03:38:59.792684+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4TCRQG7Q65M","created_at":"2026-07-05T03:38:59.792684+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4TCRQG7Q65MVYJY","created_at":"2026-07-05T03:38:59.792684+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4TCRQG7","created_at":"2026-07-05T03:38:59.792684+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/J4TCRQG7Q65MVYJYJPSLQFCF3G","json":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G.json","graph_json":"https://pith.science/api/pith-number/J4TCRQG7Q65MVYJYJPSLQFCF3G/graph.json","events_json":"https://pith.science/api/pith-number/J4TCRQG7Q65MVYJYJPSLQFCF3G/events.json","paper":"https://pith.science/paper/J4TCRQG7"},"agent_actions":{"view_html":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G","download_json":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G.json","view_paper":"https://pith.science/paper/J4TCRQG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11984&json=true","fetch_graph":"https://pith.science/api/pith-number/J4TCRQG7Q65MVYJYJPSLQFCF3G/graph.json","fetch_events":"https://pith.science/api/pith-number/J4TCRQG7Q65MVYJYJPSLQFCF3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G/action/storage_attestation","attest_author":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G/action/author_attestation","sign_citation":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G/action/citation_signature","submit_replication":"https://pith.science/pith/J4TCRQG7Q65MVYJYJPSLQFCF3G/action/replication_record"}},"created_at":"2026-07-05T03:38:59.792684+00:00","updated_at":"2026-07-05T03:38:59.792684+00:00"}