{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ESJDN4XYCYL7OLMD3SP7PMNQTH","short_pith_number":"pith:ESJDN4XY","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"},"canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","source":{"kind":"arxiv","id":"2408.02711","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ESJDN4XYCYL7OLMD3SP7PMNQTH","target":"record","payload":{"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"},"canonical_sha256":"249236f2f81617f72d83dc9ff7b1b099d0eb4cba297b45724e471870cd65252e","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"},"source_kind":"arxiv","source_id":"2408.02711","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bWzhmkJbue+EtEbwF9n3Ml4ubGwglD+NROZOfGKGpZ8yjh5/iTOuIztWrsuQrGD3GDU0ZPu0IwaWJHTut64Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:51:27.908278Z"},"content_sha256":"f384591e2a6a5fa369bff1b12d1bd796249aeaaa8dd7b69b478bc19af49ba905","schema_version":"1.0","event_id":"sha256:f384591e2a6a5fa369bff1b12d1bd796249aeaaa8dd7b69b478bc19af49ba905"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ESJDN4XYCYL7OLMD3SP7PMNQTH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lJBnzNAaivIR1dkgXYlAkzlmXo5VgrdVAOZ1tj/SR5eD7dA0SJtQSHa+MS43B0yKpmX828GWQ0uJ1VpdugyrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:51:27.908912Z"},"content_sha256":"9350f9f7e14a67be9921587f22309668ae4a25e4e9422ae688e5a4edf92df232","schema_version":"1.0","event_id":"sha256:9350f9f7e14a67be9921587f22309668ae4a25e4e9422ae688e5a4edf92df232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/bundle.json","state_url":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T07:51:27Z","links":{"resolver":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH","bundle":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/bundle.json","state":"https://pith.science/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ESJDN4XYCYL7OLMD3SP7PMNQTH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PF3RTKKqXQD5KKO2CgT5MYfRLStdTdqjHBscLFCTkrsOWxavQqwbuLPhxTieahUpR51tlH1qesJaYWwjRqbBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:51:27.915131Z","bundle_sha256":"142f163a44cab8d7a65f96c987445eac87e814df2fda4c8da64ba1deb86c14d7"}}