{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U5PLZ5XT5N7PK45SYIA6W76VCH","short_pith_number":"pith:U5PLZ5XT","schema_version":"1.0","canonical_sha256":"a75ebcf6f3eb7ef573b2c201eb7fd511c80b70fa8235d352d10e5e4efe822da8","source":{"kind":"arxiv","id":"2208.11671","version":1},"attestation_state":"computed","paper":{"title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Junyan Jiang, Simon Dixon, Yixiao Zhang","submitted_at":"2022-08-24T17:07:37Z","abstract_excerpt":"Lyric interpretations can help people understand songs and their lyrics quickly, and can also make it easier to manage, retrieve and discover songs efficiently from the growing mass of music archives. In this paper we propose BART-fusion, a novel model for generating lyric interpretations from lyrics and music audio that combines a large-scale pre-trained language model with an audio encoder. We employ a cross-modal attention module to incorporate the audio representation into the lyrics representation to help the pre-trained language model understand the song from an audio perspective, while "},"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":"2208.11671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-08-24T17:07:37Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"6cc8100fd106ddeb2fe6f94d0c2231746b040fb394c7c8098faf1e6055561103","abstract_canon_sha256":"e973478fdf87f6599765cbafef2ced89b34f4bb27b8b7756e331b1887ce78c6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:17.833363Z","signature_b64":"JXGq9Qvi+CvDQ9dsuT996AJV6c/E+uDtetfUb0LtdtYuxm5iU1yIkn0/PZg67Y3j2KE7vloKt/79isBu0CXsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75ebcf6f3eb7ef573b2c201eb7fd511c80b70fa8235d352d10e5e4efe822da8","last_reissued_at":"2026-07-05T04:51:17.832925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:17.832925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting Song Lyrics with an Audio-Informed Pre-trained Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gus Xia, Junyan Jiang, Simon Dixon, Yixiao Zhang","submitted_at":"2022-08-24T17:07:37Z","abstract_excerpt":"Lyric interpretations can help people understand songs and their lyrics quickly, and can also make it easier to manage, retrieve and discover songs efficiently from the growing mass of music archives. In this paper we propose BART-fusion, a novel model for generating lyric interpretations from lyrics and music audio that combines a large-scale pre-trained language model with an audio encoder. We employ a cross-modal attention module to incorporate the audio representation into the lyrics representation to help the pre-trained language model understand the song from an audio perspective, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11671","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/2208.11671/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":"2208.11671","created_at":"2026-07-05T04:51:17.833005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11671v1","created_at":"2026-07-05T04:51:17.833005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11671","created_at":"2026-07-05T04:51:17.833005+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5PLZ5XT5N7P","created_at":"2026-07-05T04:51:17.833005+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5PLZ5XT5N7PK45S","created_at":"2026-07-05T04:51:17.833005+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5PLZ5XT","created_at":"2026-07-05T04:51:17.833005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02282","citing_title":"Content filtering methods for music recommendation: A review","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH","json":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH.json","graph_json":"https://pith.science/api/pith-number/U5PLZ5XT5N7PK45SYIA6W76VCH/graph.json","events_json":"https://pith.science/api/pith-number/U5PLZ5XT5N7PK45SYIA6W76VCH/events.json","paper":"https://pith.science/paper/U5PLZ5XT"},"agent_actions":{"view_html":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH","download_json":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH.json","view_paper":"https://pith.science/paper/U5PLZ5XT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11671&json=true","fetch_graph":"https://pith.science/api/pith-number/U5PLZ5XT5N7PK45SYIA6W76VCH/graph.json","fetch_events":"https://pith.science/api/pith-number/U5PLZ5XT5N7PK45SYIA6W76VCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH/action/storage_attestation","attest_author":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH/action/author_attestation","sign_citation":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH/action/citation_signature","submit_replication":"https://pith.science/pith/U5PLZ5XT5N7PK45SYIA6W76VCH/action/replication_record"}},"created_at":"2026-07-05T04:51:17.833005+00:00","updated_at":"2026-07-05T04:51:17.833005+00:00"}