{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKYKIWBZA4H3GPZYVYC443QMCW","short_pith_number":"pith:UKYKIWBZ","schema_version":"1.0","canonical_sha256":"a2b0a45839070fb33f38ae05ce6e0c15ad4581d4d24591a6232039578f9ebdd2","source":{"kind":"arxiv","id":"2408.07547","version":1},"attestation_state":"computed","paper":{"title":"PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2024-08-14T13:36:17Z","abstract_excerpt":"Recently, universal waveform generation tasks have been investigated conditioned on various out-of-distribution scenarios. Although GAN-based methods have shown their strength in fast waveform generation, they are vulnerable to train-inference mismatch scenarios such as two-stage text-to-speech. Meanwhile, diffusion-based models have shown their powerful generative performance in other domains; however, they stay out of the limelight due to slow inference speed in waveform generation tasks. Above all, there is no generator architecture that can explicitly disentangle the natural periodic featu"},"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":"2408.07547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-14T13:36:17Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"786884b809b03f9d62e9f4b534cb4e234276e6e4df10114f5054d04d80438747","abstract_canon_sha256":"9c84ebe26d4bb6ee43799f7a8c5edee39ab92cfde74fbcd3bb44399403bc5977"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:26.854485Z","signature_b64":"0/LOzCxbkXITmoQw8FIr+YoQy9lBNW7glQ/KeEp7O9+ebTxOnI4XFlEKX6QYFbz+gcelucu0vBMbaQsWPkxWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2b0a45839070fb33f38ae05ce6e0c15ad4581d4d24591a6232039578f9ebdd2","last_reissued_at":"2026-07-05T08:55:26.854073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:26.854073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee","submitted_at":"2024-08-14T13:36:17Z","abstract_excerpt":"Recently, universal waveform generation tasks have been investigated conditioned on various out-of-distribution scenarios. Although GAN-based methods have shown their strength in fast waveform generation, they are vulnerable to train-inference mismatch scenarios such as two-stage text-to-speech. Meanwhile, diffusion-based models have shown their powerful generative performance in other domains; however, they stay out of the limelight due to slow inference speed in waveform generation tasks. Above all, there is no generator architecture that can explicitly disentangle the natural periodic featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07547","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/2408.07547/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":"2408.07547","created_at":"2026-07-05T08:55:26.854129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.07547v1","created_at":"2026-07-05T08:55:26.854129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07547","created_at":"2026-07-05T08:55:26.854129+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKYKIWBZA4H3","created_at":"2026-07-05T08:55:26.854129+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKYKIWBZA4H3GPZY","created_at":"2026-07-05T08:55:26.854129+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKYKIWBZ","created_at":"2026-07-05T08:55:26.854129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10491","citing_title":"FlowECG: Using Flow Matching to Create a More Efficient ECG Signal Generator","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW","json":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW.json","graph_json":"https://pith.science/api/pith-number/UKYKIWBZA4H3GPZYVYC443QMCW/graph.json","events_json":"https://pith.science/api/pith-number/UKYKIWBZA4H3GPZYVYC443QMCW/events.json","paper":"https://pith.science/paper/UKYKIWBZ"},"agent_actions":{"view_html":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW","download_json":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW.json","view_paper":"https://pith.science/paper/UKYKIWBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.07547&json=true","fetch_graph":"https://pith.science/api/pith-number/UKYKIWBZA4H3GPZYVYC443QMCW/graph.json","fetch_events":"https://pith.science/api/pith-number/UKYKIWBZA4H3GPZYVYC443QMCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW/action/storage_attestation","attest_author":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW/action/author_attestation","sign_citation":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW/action/citation_signature","submit_replication":"https://pith.science/pith/UKYKIWBZA4H3GPZYVYC443QMCW/action/replication_record"}},"created_at":"2026-07-05T08:55:26.854129+00:00","updated_at":"2026-07-05T08:55:26.854129+00:00"}