{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KWWE55OVTBMXVEFXWUQZMU5DXN","short_pith_number":"pith:KWWE55OV","schema_version":"1.0","canonical_sha256":"55ac4ef5d598597a90b7b5219653a3bb5ca230c33ad018d541eb9147a2046399","source":{"kind":"arxiv","id":"2605.13404","version":1},"attestation_state":"computed","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"},"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":true,"formal_links_present":true},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13404","created_at":"2026-05-18T02:44:47.547744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13404v1","created_at":"2026-05-18T02:44:47.547744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13404","created_at":"2026-05-18T02:44:47.547744+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWWE55OVTBMX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWWE55OVTBMXVEFX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWWE55OV","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN","json":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN.json","graph_json":"https://pith.science/api/pith-number/KWWE55OVTBMXVEFXWUQZMU5DXN/graph.json","events_json":"https://pith.science/api/pith-number/KWWE55OVTBMXVEFXWUQZMU5DXN/events.json","paper":"https://pith.science/paper/KWWE55OV"},"agent_actions":{"view_html":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN","download_json":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN.json","view_paper":"https://pith.science/paper/KWWE55OV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13404&json=true","fetch_graph":"https://pith.science/api/pith-number/KWWE55OVTBMXVEFXWUQZMU5DXN/graph.json","fetch_events":"https://pith.science/api/pith-number/KWWE55OVTBMXVEFXWUQZMU5DXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/action/storage_attestation","attest_author":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/action/author_attestation","sign_citation":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/action/citation_signature","submit_replication":"https://pith.science/pith/KWWE55OVTBMXVEFXWUQZMU5DXN/action/replication_record"}},"created_at":"2026-05-18T02:44:47.547744+00:00","updated_at":"2026-05-18T02:44:47.547744+00:00"}