{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KWWE55OVTBMXVEFXWUQZMU5DXN","short_pith_number":"pith:KWWE55OV","canonical_record":{"source":{"id":"2605.13404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T11:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"d8776fa4f40c70e8c5f041221fda928eb31219689dd0ff0788e3a75ced7d892d","abstract_canon_sha256":"639fb56052a11e305ba9aba92395e9a5e1ef502b756579901ec7f778e7212b51"},"schema_version":"1.0"},"canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","source":{"kind":"arxiv","id":"2605.13404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13404","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13404v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13404","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"KWWE55OVTBMX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KWWE55OVTBMXVEFX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KWWE55OV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KWWE55OVTBMXVEFXWUQZMU5DXN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T11:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"d8776fa4f40c70e8c5f041221fda928eb31219689dd0ff0788e3a75ced7d892d","abstract_canon_sha256":"639fb56052a11e305ba9aba92395e9a5e1ef502b756579901ec7f778e7212b51"},"schema_version":"1.0"},"canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.548202Z","signature_b64":"14k/H0vp/Ymm8SHLq9H5T/a3r6QK/2QkuLYRaZvi5e36dAZM1j+C8mkQnnJJ3TpQKJ9qY1q6j9yvR8nZmenUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","last_reissued_at":"2026-05-18T02:44:47.547674Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.547674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13404","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":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8XNnslDRdifyGmkFsiO/2nCbwckOQDXh8Iz8nMCESx8gcdAYfppllJJtBO4D/OldddAZvPIqRi90AO7NwgrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:00:06.811758Z"},"content_sha256":"649ac036fa70a46023988e767e2b49df2ffa9ad2aafc2bc4fc0072d0b2e7dc52","schema_version":"1.0","event_id":"sha256:649ac036fa70a46023988e767e2b49df2ffa9ad2aafc2bc4fc0072d0b2e7dc52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KWWE55OVTBMXVEFXWUQZMU5DXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression.","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Dimos Makris, Konstantinos Soiledis, Konstantinos Tsamis, Maximos Kaliakatsos Papakostas","submitted_at":"2026-05-13T11:59:41Z","abstract_excerpt":"Symbolic-control drum generation requires preserving explicit event timing and dynamics while synthesizing acoustically plausible waveforms. We present Sec2Drum-DAC, a conditional latent-diffusion model for symbolic-to-audio drum rendering. The model conditions on event features sampled in physical time at codec-frame locations and predicts standardized principal-component coordinates of frozen DAC summed-codebook embeddings rather than waveform samples. In the evaluated DAC configuration, 72 principal components capture the observed training-frame summed-latent subspace under the stated SVD t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 72 principal components derived from training data via SVD threshold sufficiently represent the variations needed for high-quality reconstruction of held-out drum audio when decoded through the frozen DAC.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sec2Drum-DAC renders drum audio from symbolic inputs via diffusion on PCA-reduced DAC latents, improving spectral and transient metrics over regression baselines on 1733 held-out windows.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e7baf641c8e43eb57167bff6ec85ff68b330d1434a56b9d15cdbe6ec86c83b2f"},"source":{"id":"2605.13404","kind":"arxiv","version":1},"verdict":{"id":"5091d3f7-5eae-4fe9-8d0c-1c5d12760882","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:34:08.695480Z","strongest_claim":"Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1.","one_line_summary":"Sec2Drum-DAC renders drum audio from symbolic inputs via diffusion on PCA-reduced DAC latents, improving spectral and transient metrics over regression baselines on 1733 held-out windows.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 72 principal components derived from training data via SVD threshold sufficiently represent the variations needed for high-quality reconstruction of held-out drum audio when decoded through the frozen DAC.","pith_extraction_headline":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression."},"references":{"count":33,"sample":[{"doi":"","year":1906,"title":"Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, and David Ha","work_id":"4acd1abb-5322-43c7-b701-6718c3d52b72","ref_index":1,"cited_arxiv_id":"1906.02569","is_internal_anchor":true},{"doi":"","year":2023,"title":"MusicLM: Generating Music From Text","work_id":"15e6566e-1c36-468f-966e-823248cbf87f","ref_index":2,"cited_arxiv_id":"2301.11325","is_internal_anchor":true},{"doi":"","year":2016,"title":"madmom: A new Python audio and music signal processing library","work_id":"d95aeaf7-c243-4347-80f8-87171845aa3a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"AudioLM: A language modeling approach to audio generation.IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2523–2533, 2023","work_id":"9f88e30d-7bc1-4391-b8f2-d0925e784600","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"DARC: Drum accompaniment generation with fine-grained rhythm control","work_id":"8124ea20-a88f-4d9b-bee4-834478e9d0bf","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"2a2bc55b4e087647d2f6c756741672d55372f60b3efb4bdc05bc3543f169e799","internal_anchors":4},"formal_canon":{"evidence_count":1,"snapshot_sha256":"a516c148e5b2ab5fc5d787375119a8634b20f4cd815ff8ff929da5bf4ed12a66"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5091d3f7-5eae-4fe9-8d0c-1c5d12760882"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsUpVmnlqAioiTlp8cUyJ9/HTB9Fm74a2U/vM0qZ4XkxujqlJ7YliUKcNs9uh7f1VTPgRBboSzY0uZStLNMUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:00:06.812408Z"},"content_sha256":"751dcc7a9b54ce7e5828be3d38e6e5661a008f9e233005188ddb4d945bbaeb76","schema_version":"1.0","event_id":"sha256:751dcc7a9b54ce7e5828be3d38e6e5661a008f9e233005188ddb4d945bbaeb76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/bundle.json","state_url":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/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":"2026-06-02T04:00:06Z","links":{"resolver":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN","bundle":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/bundle.json","state":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KWWE55OVTBMXVEFXWUQZMU5DXN","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":"639fb56052a11e305ba9aba92395e9a5e1ef502b756579901ec7f778e7212b51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T11:59:41Z","title_canon_sha256":"d8776fa4f40c70e8c5f041221fda928eb31219689dd0ff0788e3a75ced7d892d"},"schema_version":"1.0","source":{"id":"2605.13404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13404","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13404v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13404","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"KWWE55OVTBMX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KWWE55OVTBMXVEFX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KWWE55OV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:751dcc7a9b54ce7e5828be3d38e6e5661a008f9e233005188ddb4d945bbaeb76","target":"graph","created_at":"2026-05-18T02:44:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 72 principal components derived from training data via SVD threshold sufficiently represent the variations needed for high-quality reconstruction of held-out drum audio when decoded through the frozen DAC."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sec2Drum-DAC renders drum audio from symbolic inputs via diffusion on PCA-reduced DAC latents, improving spectral and transient metrics over regression baselines on 1733 held-out windows."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression."}],"snapshot_sha256":"e7baf641c8e43eb57167bff6ec85ff68b330d1434a56b9d15cdbe6ec86c83b2f"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"a516c148e5b2ab5fc5d787375119a8634b20f4cd815ff8ff929da5bf4ed12a66"},"paper":{"abstract_excerpt":"Symbolic-control drum generation requires preserving explicit event timing and dynamics while synthesizing acoustically plausible waveforms. We present Sec2Drum-DAC, a conditional latent-diffusion model for symbolic-to-audio drum rendering. The model conditions on event features sampled in physical time at codec-frame locations and predicts standardized principal-component coordinates of frozen DAC summed-codebook embeddings rather than waveform samples. In the evaluated DAC configuration, 72 principal components capture the observed training-frame summed-latent subspace under the stated SVD t","authors_text":"Dimos Makris, Konstantinos Soiledis, Konstantinos Tsamis, Maximos Kaliakatsos Papakostas","cross_cats":[],"headline":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T11:59:41Z","title":"Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering"},"references":{"count":33,"internal_anchors":4,"resolved_work":33,"sample":[{"cited_arxiv_id":"1906.02569","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, and David Ha","work_id":"4acd1abb-5322-43c7-b701-6718c3d52b72","year":1906},{"cited_arxiv_id":"2301.11325","doi":"","is_internal_anchor":true,"ref_index":2,"title":"MusicLM: Generating Music From Text","work_id":"15e6566e-1c36-468f-966e-823248cbf87f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"madmom: A new Python audio and music signal processing library","work_id":"d95aeaf7-c243-4347-80f8-87171845aa3a","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"AudioLM: A language modeling approach to audio generation.IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2523–2533, 2023","work_id":"9f88e30d-7bc1-4391-b8f2-d0925e784600","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"DARC: Drum accompaniment generation with fine-grained rhythm control","work_id":"8124ea20-a88f-4d9b-bee4-834478e9d0bf","year":2026}],"snapshot_sha256":"2a2bc55b4e087647d2f6c756741672d55372f60b3efb4bdc05bc3543f169e799"},"source":{"id":"2605.13404","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:34:08.695480Z","id":"5091d3f7-5eae-4fe9-8d0c-1c5d12760882","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sec2Drum-DAC renders drum audio from symbolic inputs via diffusion on PCA-reduced DAC latents, improving spectral and transient metrics over regression baselines on 1733 held-out windows.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A latent diffusion model predicts principal-component coordinates of a frozen audio codec to render drum audio from symbolic timing with better spectral and transient accuracy than regression.","strongest_claim":"Across 1,733 held-out four-beat windows, PCA diffusion improves paired spectral and transient metrics over deterministic PCA regression and a symbolic rendering baseline, while direct regression remains stronger on phase-sensitive waveform L1.","weakest_assumption":"That the 72 principal components derived from training data via SVD threshold sufficiently represent the variations needed for high-quality reconstruction of held-out drum audio when decoded through the frozen DAC."}},"verdict_id":"5091d3f7-5eae-4fe9-8d0c-1c5d12760882"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:649ac036fa70a46023988e767e2b49df2ffa9ad2aafc2bc4fc0072d0b2e7dc52","target":"record","created_at":"2026-05-18T02:44:47Z","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":"639fb56052a11e305ba9aba92395e9a5e1ef502b756579901ec7f778e7212b51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-13T11:59:41Z","title_canon_sha256":"d8776fa4f40c70e8c5f041221fda928eb31219689dd0ff0788e3a75ced7d892d"},"schema_version":"1.0","source":{"id":"2605.13404","kind":"arxiv","version":1}},"canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","first_computed_at":"2026-05-18T02:44:47.547674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:47.547674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"14k/H0vp/Ymm8SHLq9H5T/a3r6QK/2QkuLYRaZvi5e36dAZM1j+C8mkQnnJJ3TpQKJ9qY1q6j9yvR8nZmenUAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:47.548202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:649ac036fa70a46023988e767e2b49df2ffa9ad2aafc2bc4fc0072d0b2e7dc52","sha256:751dcc7a9b54ce7e5828be3d38e6e5661a008f9e233005188ddb4d945bbaeb76"],"state_sha256":"46a77613c147f094e0ca4659d407606828e1642b3d95eb778e4664370146c13c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3lFb9+V89Qh6KWL/h0SGtYmAIu5iM3HMrZj2A66lD3wVVEgAnVpsEEYSeJx/VS9RZp++4cVQHTwAyl2MSjwBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:00:06.815250Z","bundle_sha256":"057db9aa83cdbacd6110961528fb34d05e90e44d0d4ce394c27061ece0b13b51"}}