{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5CWVUD7IV7NA76FDK2P5WUS7LR","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":"93523ce405c19c4f61ee7df0acffb7bdb2387ab60d1fd856ad6f74eeb92b2218","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T07:33:14Z","title_canon_sha256":"9f1497a7e798457e6a90a7086d9a741acec2540e5dbebee7fcd42379f057208f"},"schema_version":"1.0","source":{"id":"2407.02869","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02869","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02869v2","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02869","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"5CWVUD7IV7NA","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"5CWVUD7IV7NA76FD","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"5CWVUD7I","created_at":"2026-07-05T08:44:55Z"}],"graph_snapshots":[{"event_id":"sha256:ffffa9f43ab89c68d62de3969a2448ae406e2451efe44dba7eb1a92d7f6e063f","target":"graph","created_at":"2026-07-05T08:44:55Z","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/2407.02869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Mengyue Wu, Xuenan Xu, Zeyu Xie, Zhizheng Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T07:33:14Z","title":"PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02869","kind":"arxiv","version":2},"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":"sha256:7440022a45632277d16f72d93d14e0d49b194cc24116f201046bbbeaa2b76180","target":"record","created_at":"2026-07-05T08:44:55Z","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":"93523ce405c19c4f61ee7df0acffb7bdb2387ab60d1fd856ad6f74eeb92b2218","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-03T07:33:14Z","title_canon_sha256":"9f1497a7e798457e6a90a7086d9a741acec2540e5dbebee7fcd42379f057208f"},"schema_version":"1.0","source":{"id":"2407.02869","kind":"arxiv","version":2}},"canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","first_computed_at":"2026-07-05T08:44:55.646665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:55.646665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Gd9RXdOa12Euc40osNOHdo5g86A86iNVVX53hNAeYZEFRg5yQwz2r/K5dwv8E4F2n/S/fOn10lz87/RFcmQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:55.647050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02869","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7440022a45632277d16f72d93d14e0d49b194cc24116f201046bbbeaa2b76180","sha256:ffffa9f43ab89c68d62de3969a2448ae406e2451efe44dba7eb1a92d7f6e063f"],"state_sha256":"c1d0034bfdd196519f164573d781398444ad715d2d77338be4a5a468cf1ce5a9"}