{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5CWVUD7IV7NA76FDK2P5WUS7LR","short_pith_number":"pith:5CWVUD7I","schema_version":"1.0","canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","source":{"kind":"arxiv","id":"2407.02869","version":2},"attestation_state":"computed","paper":{"title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Mengyue Wu, Xuenan Xu, Zeyu Xie, Zhizheng Wu","submitted_at":"2024-07-03T07:33:14Z","abstract_excerpt":"Recently, audio generation tasks have attracted considerable research interests. Precise temporal controllability is essential to integrate audio generation with real applications. In this work, we propose a temporal controlled audio generation framework, PicoAudio. PicoAudio integrates temporal information to guide audio generation through tailored model design. It leverages data crawling, segmentation, filtering, and simulation of fine-grained temporally-aligned audio-text data. Both subjective and objective evaluations demonstrate that PicoAudio dramantically surpasses current state-of-the-"},"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":"2407.02869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T07:33:14Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9f1497a7e798457e6a90a7086d9a741acec2540e5dbebee7fcd42379f057208f","abstract_canon_sha256":"93523ce405c19c4f61ee7df0acffb7bdb2387ab60d1fd856ad6f74eeb92b2218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:55.647050Z","signature_b64":"6Gd9RXdOa12Euc40osNOHdo5g86A86iNVVX53hNAeYZEFRg5yQwz2r/K5dwv8E4F2n/S/fOn10lz87/RFcmQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","last_reissued_at":"2026-07-05T08:44:55.646665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:55.646665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Mengyue Wu, Xuenan Xu, Zeyu Xie, Zhizheng Wu","submitted_at":"2024-07-03T07:33:14Z","abstract_excerpt":"Recently, audio generation tasks have attracted considerable research interests. Precise temporal controllability is essential to integrate audio generation with real applications. In this work, we propose a temporal controlled audio generation framework, PicoAudio. PicoAudio integrates temporal information to guide audio generation through tailored model design. It leverages data crawling, segmentation, filtering, and simulation of fine-grained temporally-aligned audio-text data. Both subjective and objective evaluations demonstrate that PicoAudio dramantically surpasses current state-of-the-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02869","kind":"arxiv","version":2},"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/2407.02869/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":"2407.02869","created_at":"2026-07-05T08:44:55.646723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02869v2","created_at":"2026-07-05T08:44:55.646723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02869","created_at":"2026-07-05T08:44:55.646723+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CWVUD7IV7NA","created_at":"2026-07-05T08:44:55.646723+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CWVUD7IV7NA76FD","created_at":"2026-07-05T08:44:55.646723+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CWVUD7I","created_at":"2026-07-05T08:44:55.646723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR","json":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR.json","graph_json":"https://pith.science/api/pith-number/5CWVUD7IV7NA76FDK2P5WUS7LR/graph.json","events_json":"https://pith.science/api/pith-number/5CWVUD7IV7NA76FDK2P5WUS7LR/events.json","paper":"https://pith.science/paper/5CWVUD7I"},"agent_actions":{"view_html":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR","download_json":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR.json","view_paper":"https://pith.science/paper/5CWVUD7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02869&json=true","fetch_graph":"https://pith.science/api/pith-number/5CWVUD7IV7NA76FDK2P5WUS7LR/graph.json","fetch_events":"https://pith.science/api/pith-number/5CWVUD7IV7NA76FDK2P5WUS7LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/action/storage_attestation","attest_author":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/action/author_attestation","sign_citation":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/action/citation_signature","submit_replication":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/action/replication_record"}},"created_at":"2026-07-05T08:44:55.646723+00:00","updated_at":"2026-07-05T08:44:55.646723+00:00"}