{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5CWVUD7IV7NA76FDK2P5WUS7LR","short_pith_number":"pith:5CWVUD7I","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"},"canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","source":{"kind":"arxiv","id":"2407.02869","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5CWVUD7IV7NA76FDK2P5WUS7LR","target":"record","payload":{"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"},"canonical_sha256":"e8ad5a0fe8afda0ff8a3569fdb525f5c77bac8abdde0e35c0532f2008d03175b","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"},"source_kind":"arxiv","source_id":"2407.02869","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukV+cDAo6952GI8ulMDv/Y2hLvM1PLOiRqApV9kPMud85loPwgzGC6POa7ZECDhBT2ApzxwJkmGUMFXyCRthBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T18:29:41.350481Z"},"content_sha256":"7440022a45632277d16f72d93d14e0d49b194cc24116f201046bbbeaa2b76180","schema_version":"1.0","event_id":"sha256:7440022a45632277d16f72d93d14e0d49b194cc24116f201046bbbeaa2b76180"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5CWVUD7IV7NA76FDK2P5WUS7LR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:44:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNaY7wjSqX8JGqb3yGFs1QOOuzMPoxINRGTesP9rTG0d0J4TvriSgINmlPRV8Skud9A1VNCFm96D/aGXWdzTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T18:29:41.350858Z"},"content_sha256":"ffffa9f43ab89c68d62de3969a2448ae406e2451efe44dba7eb1a92d7f6e063f","schema_version":"1.0","event_id":"sha256:ffffa9f43ab89c68d62de3969a2448ae406e2451efe44dba7eb1a92d7f6e063f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/bundle.json","state_url":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/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":"2026-07-10T18:29:41Z","links":{"resolver":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR","bundle":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/bundle.json","state":"https://pith.science/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CWVUD7IV7NA76FDK2P5WUS7LR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gDwydmTNpLQ5HfZ24lkrTxVagdO1d+NdViwQLNWpjdQc8JH5UTQ8KTn76yxBD87NrQ4DBh+k3VtQrBwSWuRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T18:29:41.352834Z","bundle_sha256":"1e42caa606ba1bb677492e3e319848aba7cfff8e383492d631b0c08d50049529"}}