{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5BKIKBA5CU7DE4GEBGTO4I3DGM","short_pith_number":"pith:5BKIKBA5","canonical_record":{"source":{"id":"2305.01980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T08:52:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23af569ee0bf5f24e4a6b92d54cd6dbb56d3646c8910126370895faaf2157705","abstract_canon_sha256":"17fac704a734a96903a3891a93a5723ff17e576772b8be9faf60fab1f772664f"},"schema_version":"1.0"},"canonical_sha256":"e85485041d153e3270c409a6ee2363333204d896dbed9e11bc257c93cccb41b6","source":{"kind":"arxiv","id":"2305.01980","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01980","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01980v1","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01980","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"5BKIKBA5CU7D","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"5BKIKBA5CU7DE4GE","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"5BKIKBA5","created_at":"2026-07-05T06:06:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5BKIKBA5CU7DE4GEBGTO4I3DGM","target":"record","payload":{"canonical_record":{"source":{"id":"2305.01980","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T08:52:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23af569ee0bf5f24e4a6b92d54cd6dbb56d3646c8910126370895faaf2157705","abstract_canon_sha256":"17fac704a734a96903a3891a93a5723ff17e576772b8be9faf60fab1f772664f"},"schema_version":"1.0"},"canonical_sha256":"e85485041d153e3270c409a6ee2363333204d896dbed9e11bc257c93cccb41b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:46.237710Z","signature_b64":"1ViLmNAE4Cd0r15YsZG+U3y0lxPmJOkzFq3by7u8z6XkJVnaeI6qX9xOovMYdQnW5NyGUZ5vAHiEdR3pr4+oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e85485041d153e3270c409a6ee2363333204d896dbed9e11bc257c93cccb41b6","last_reissued_at":"2026-07-05T06:06:46.237269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:46.237269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.01980","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dHcU0ZJg1v8iHI4xN1kJWoiTFrRenN+5Lq3G7eiZwLX7i125cLWFAdnbfNeYpYBRttzA4XtpkXXydJEFgF8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:02:16.795952Z"},"content_sha256":"21cb5759899e5229eb7f057fcd23098769701ccc78f7783e69678db1bcd5f052","schema_version":"1.0","event_id":"sha256:21cb5759899e5229eb7f057fcd23098769701ccc78f7783e69678db1bcd5f052"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5BKIKBA5CU7DE4GEBGTO4I3DGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diverse and Vivid Sound Generation from Text Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guangwei Li, Kai Yu, Lingfeng Dai, Mengyue Wu, Xuenan Xu","submitted_at":"2023-05-03T08:52:40Z","abstract_excerpt":"Previous audio generation mainly focuses on specified sound classes such as speech or music, whose form and content are greatly restricted. In this paper, we go beyond specific audio generation by using natural language description as a clue to generate broad sounds. Unlike visual information, a text description is concise by its nature but has rich hidden meanings beneath, which poses a higher possibility and complexity on the audio to be generated. A Variation-Quantized GAN is used to train a codebook learning discrete representations of spectrograms. For a given text description, its pre-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01980","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/2305.01980/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":"2026-07-05T06:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukWhndiS78mu8d2jqFiXKtf/pi5J0XDPdxSV/SdPo1s/5Q+W9AZ/QjVDdfFsiZJINNj75v3FiPOw7cI+MaZTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:02:16.796504Z"},"content_sha256":"a88e8fb07a0561a64c7ced0548bb78da084f8106ec580cb7d9cb524179ef2a34","schema_version":"1.0","event_id":"sha256:a88e8fb07a0561a64c7ced0548bb78da084f8106ec580cb7d9cb524179ef2a34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/bundle.json","state_url":"https://pith.science/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/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":"2026-08-04T20:02:16Z","links":{"resolver":"https://pith.science/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM","bundle":"https://pith.science/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/bundle.json","state":"https://pith.science/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5BKIKBA5CU7DE4GEBGTO4I3DGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5BKIKBA5CU7DE4GEBGTO4I3DGM","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":"17fac704a734a96903a3891a93a5723ff17e576772b8be9faf60fab1f772664f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T08:52:40Z","title_canon_sha256":"23af569ee0bf5f24e4a6b92d54cd6dbb56d3646c8910126370895faaf2157705"},"schema_version":"1.0","source":{"id":"2305.01980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01980","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01980v1","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01980","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"5BKIKBA5CU7D","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"5BKIKBA5CU7DE4GE","created_at":"2026-07-05T06:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"5BKIKBA5","created_at":"2026-07-05T06:06:46Z"}],"graph_snapshots":[{"event_id":"sha256:a88e8fb07a0561a64c7ced0548bb78da084f8106ec580cb7d9cb524179ef2a34","target":"graph","created_at":"2026-07-05T06:06:46Z","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/2305.01980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous audio generation mainly focuses on specified sound classes such as speech or music, whose form and content are greatly restricted. In this paper, we go beyond specific audio generation by using natural language description as a clue to generate broad sounds. Unlike visual information, a text description is concise by its nature but has rich hidden meanings beneath, which poses a higher possibility and complexity on the audio to be generated. A Variation-Quantized GAN is used to train a codebook learning discrete representations of spectrograms. For a given text description, its pre-tr","authors_text":"Guangwei Li, Kai Yu, Lingfeng Dai, Mengyue Wu, Xuenan Xu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T08:52:40Z","title":"Diverse and Vivid Sound Generation from Text Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01980","kind":"arxiv","version":1},"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":"sha256:21cb5759899e5229eb7f057fcd23098769701ccc78f7783e69678db1bcd5f052","target":"record","created_at":"2026-07-05T06:06:46Z","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":"17fac704a734a96903a3891a93a5723ff17e576772b8be9faf60fab1f772664f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T08:52:40Z","title_canon_sha256":"23af569ee0bf5f24e4a6b92d54cd6dbb56d3646c8910126370895faaf2157705"},"schema_version":"1.0","source":{"id":"2305.01980","kind":"arxiv","version":1}},"canonical_sha256":"e85485041d153e3270c409a6ee2363333204d896dbed9e11bc257c93cccb41b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e85485041d153e3270c409a6ee2363333204d896dbed9e11bc257c93cccb41b6","first_computed_at":"2026-07-05T06:06:46.237269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:06:46.237269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ViLmNAE4Cd0r15YsZG+U3y0lxPmJOkzFq3by7u8z6XkJVnaeI6qX9xOovMYdQnW5NyGUZ5vAHiEdR3pr4+oDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:06:46.237710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21cb5759899e5229eb7f057fcd23098769701ccc78f7783e69678db1bcd5f052","sha256:a88e8fb07a0561a64c7ced0548bb78da084f8106ec580cb7d9cb524179ef2a34"],"state_sha256":"9d7422a7fe0720b8119c4bd2c5e5631a7c9c85529a1fdb7efddd1d24a17869ca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"037E36AV/jbwoFnw3gKOxG3JQZUnQWgB7ARKweeP+JMR5qGRulvzVIb19Jor1S//OkcIlCODKA/vdgZhzoPGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:02:16.801868Z","bundle_sha256":"cad412b544064e41e8101e177df5e9d6ed2f20b34aff64a58d6579746cacc690"}}