{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ESJDN4XYCYL7OLMD3SP7PMNQTH","short_pith_number":"pith:ESJDN4XY","schema_version":"1.0","canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","source":{"kind":"arxiv","id":"2408.02711","version":1},"attestation_state":"computed","paper":{"title":"Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"James McDermott, Pushkar Jajoria","submitted_at":"2024-08-05T13:23:05Z","abstract_excerpt":"This study introduces a text-conditioned approach to generating drumbeats with Latent Diffusion Models (LDMs). It uses informative conditioning text extracted from training data filenames. By pretraining a text and drumbeat encoder through contrastive learning within a multimodal network, aligned following CLIP, we align the modalities of text and music closely. Additionally, we examine an alternative text encoder based on multihot text encodings. Inspired by musics multi-resolution nature, we propose a novel LSTM variant, MultiResolutionLSTM, designed to operate at various resolutions indepen"},"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":"2408.02711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-05T13:23:05Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"7c12d055e24e9c7fbbe5d9865e9609640039f8dcdaa85dd8259560c83f68811c","abstract_canon_sha256":"ea5a56c0b389c901138366853a1613240a947542c69bfac8470f6bed5563f16e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:38.998468Z","signature_b64":"wrNACa7h+KHoi+A2NXw5UD/c2KPxKmaeunQOTfgAWfiIGQmd3pL2IPIsQqKDMtYg0/jiyvsam4O4HvarHsqtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","last_reissued_at":"2026-07-05T08:52:38.997989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:38.997989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"James McDermott, Pushkar Jajoria","submitted_at":"2024-08-05T13:23:05Z","abstract_excerpt":"This study introduces a text-conditioned approach to generating drumbeats with Latent Diffusion Models (LDMs). It uses informative conditioning text extracted from training data filenames. By pretraining a text and drumbeat encoder through contrastive learning within a multimodal network, aligned following CLIP, we align the modalities of text and music closely. Additionally, we examine an alternative text encoder based on multihot text encodings. Inspired by musics multi-resolution nature, we propose a novel LSTM variant, MultiResolutionLSTM, designed to operate at various resolutions indepen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02711","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/2408.02711/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":"2408.02711","created_at":"2026-07-05T08:52:38.998049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02711v1","created_at":"2026-07-05T08:52:38.998049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02711","created_at":"2026-07-05T08:52:38.998049+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESJDN4XYCYL7","created_at":"2026-07-05T08:52:38.998049+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESJDN4XYCYL7OLMD","created_at":"2026-07-05T08:52:38.998049+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESJDN4XY","created_at":"2026-07-05T08:52:38.998049+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13404","citing_title":"Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH","json":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH.json","graph_json":"https://pith.science/api/pith-number/ESJDN4XYCYL7OLMD3SP7PMNQTH/graph.json","events_json":"https://pith.science/api/pith-number/ESJDN4XYCYL7OLMD3SP7PMNQTH/events.json","paper":"https://pith.science/paper/ESJDN4XY"},"agent_actions":{"view_html":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH","download_json":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH.json","view_paper":"https://pith.science/paper/ESJDN4XY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02711&json=true","fetch_graph":"https://pith.science/api/pith-number/ESJDN4XYCYL7OLMD3SP7PMNQTH/graph.json","fetch_events":"https://pith.science/api/pith-number/ESJDN4XYCYL7OLMD3SP7PMNQTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/action/storage_attestation","attest_author":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/action/author_attestation","sign_citation":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/action/citation_signature","submit_replication":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/action/replication_record"}},"created_at":"2026-07-05T08:52:38.998049+00:00","updated_at":"2026-07-05T08:52:38.998049+00:00"}