{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ESJDN4XYCYL7OLMD3SP7PMNQTH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ea5a56c0b389c901138366853a1613240a947542c69bfac8470f6bed5563f16e","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-05T13:23:05Z","title_canon_sha256":"7c12d055e24e9c7fbbe5d9865e9609640039f8dcdaa85dd8259560c83f68811c"},"schema_version":"1.0","source":{"id":"2408.02711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02711","created_at":"2026-07-05T08:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02711v1","created_at":"2026-07-05T08:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02711","created_at":"2026-07-05T08:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"ESJDN4XYCYL7","created_at":"2026-07-05T08:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"ESJDN4XYCYL7OLMD","created_at":"2026-07-05T08:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"ESJDN4XY","created_at":"2026-07-05T08:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:9350f9f7e14a67be9921587f22309668ae4a25e4e9422ae688e5a4edf92df232","target":"graph","created_at":"2026-07-05T08:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.02711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"James McDermott, Pushkar Jajoria","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-05T13:23:05Z","title":"Text Conditioned Symbolic Drumbeat Generation using Latent Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02711","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f384591e2a6a5fa369bff1b12d1bd796249aeaaa8dd7b69b478bc19af49ba905","target":"record","created_at":"2026-07-05T08:52:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ea5a56c0b389c901138366853a1613240a947542c69bfac8470f6bed5563f16e","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-05T13:23:05Z","title_canon_sha256":"7c12d055e24e9c7fbbe5d9865e9609640039f8dcdaa85dd8259560c83f68811c"},"schema_version":"1.0","source":{"id":"2408.02711","kind":"arxiv","version":1}},"canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","first_computed_at":"2026-07-05T08:52:38.997989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:38.997989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wrNACa7h+KHoi+A2NXw5UD/c2KPxKmaeunQOTfgAWfiIGQmd3pL2IPIsQqKDMtYg0/jiyvsam4O4HvarHsqtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:38.998468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f384591e2a6a5fa369bff1b12d1bd796249aeaaa8dd7b69b478bc19af49ba905","sha256:9350f9f7e14a67be9921587f22309668ae4a25e4e9422ae688e5a4edf92df232"],"state_sha256":"a982809bf841754f185ee796a754317d6fb4405a2dd14d14d5d043e164c03de6"}