{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MWWN5IWMQAMHUA5N7Y7VHVVZPZ","short_pith_number":"pith:MWWN5IWM","schema_version":"1.0","canonical_sha256":"65acdea2cc80187a03adfe3f53d6b97e59ded7715e00f5f1b99c1a0a50de5cab","source":{"kind":"arxiv","id":"2409.02845","version":3},"attestation_state":"computed","paper":{"title":"Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerard Assayag, Ke Chen, Mohammad Rasool Izadi, Shlomo Dubnov, Tornike Karchkhadze","submitted_at":"2024-09-04T16:17:41Z","abstract_excerpt":"Diffusion models have shown promising results in cross-modal generation tasks involving audio and music, such as text-to-sound and text-to-music generation. These text-controlled music generation models typically focus on generating music by capturing global musical attributes like genre and mood. However, music composition is a complex, multilayered task that often involves musical arrangement as an integral part of the process. This process involves composing each instrument to align with existing ones in terms of beat, dynamics, harmony, and melody, requiring greater precision and control o"},"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":"2409.02845","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-04T16:17:41Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"4faf0dc82f7c7ab0568d14546686117a7e7c179a36f644047e945fcd60c2017d","abstract_canon_sha256":"eb3e90af1a2feb8c777d0e06d122150bd46e747e8e065b95fbcfe4abbff42261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:38.210686Z","signature_b64":"8xQXsIZ20NzRKq+Kgb7ezTNFbnER7kdKxK+j+cnAAJAOm4/NRWQNmpCC5lDJ1lixQGgVXcMx18MtvkzOfB2IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65acdea2cc80187a03adfe3f53d6b97e59ded7715e00f5f1b99c1a0a50de5cab","last_reissued_at":"2026-07-05T09:24:38.210179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:38.210179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Track MusicLDM: Towards Versatile Music Generation with Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerard Assayag, Ke Chen, Mohammad Rasool Izadi, Shlomo Dubnov, Tornike Karchkhadze","submitted_at":"2024-09-04T16:17:41Z","abstract_excerpt":"Diffusion models have shown promising results in cross-modal generation tasks involving audio and music, such as text-to-sound and text-to-music generation. These text-controlled music generation models typically focus on generating music by capturing global musical attributes like genre and mood. However, music composition is a complex, multilayered task that often involves musical arrangement as an integral part of the process. This process involves composing each instrument to align with existing ones in terms of beat, dynamics, harmony, and melody, requiring greater precision and control o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02845","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.02845/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":"2409.02845","created_at":"2026-07-05T09:24:38.210240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02845v3","created_at":"2026-07-05T09:24:38.210240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02845","created_at":"2026-07-05T09:24:38.210240+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWWN5IWMQAMH","created_at":"2026-07-05T09:24:38.210240+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWWN5IWMQAMHUA5N","created_at":"2026-07-05T09:24:38.210240+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWWN5IWM","created_at":"2026-07-05T09:24:38.210240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12573","citing_title":"Video-Guided Text-to-Music Generation Using Public Domain Movie Collections","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ","json":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ.json","graph_json":"https://pith.science/api/pith-number/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/graph.json","events_json":"https://pith.science/api/pith-number/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/events.json","paper":"https://pith.science/paper/MWWN5IWM"},"agent_actions":{"view_html":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ","download_json":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ.json","view_paper":"https://pith.science/paper/MWWN5IWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02845&json=true","fetch_graph":"https://pith.science/api/pith-number/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/action/storage_attestation","attest_author":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/action/author_attestation","sign_citation":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/action/citation_signature","submit_replication":"https://pith.science/pith/MWWN5IWMQAMHUA5N7Y7VHVVZPZ/action/replication_record"}},"created_at":"2026-07-05T09:24:38.210240+00:00","updated_at":"2026-07-05T09:24:38.210240+00:00"}