{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XLREWMNLXWACOTD6OSR7Q4ICNE","short_pith_number":"pith:XLREWMNL","schema_version":"1.0","canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","source":{"kind":"arxiv","id":"2601.21402","version":2},"attestation_state":"computed","paper":{"title":"SemanticAudio: Audio Generation and Editing in Semantic Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Xiquan Li, Yiwen Guo, Zheqi Dai","submitted_at":"2026-01-29T08:40:37Z","abstract_excerpt":"In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, existing models predominantly operate directly in the acoustic latent space of a Variational Autoencoder (VAE), often leading to suboptimal alignment between generated audio and textual descriptions. In this paper, we introduce SemanticAudio, a novel framework that conducts both audio generation and editing directly in a high-level semantic space. We define this semantic space as a compact representation capturing the gl"},"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":"2601.21402","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-29T08:40:37Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"92725ede3027441f72ce82420f89a79bbbfa76651b7dfe6dd54058dda949d6bd","abstract_canon_sha256":"132960c92449102a40c1ae1b1c8ff9f245762f868b2ebf27444542ff5fc774a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:16.809436Z","signature_b64":"yY8HXXV5h3PucgXcRzgxWKjyexdwH0piarYL3jIfoLAA0sQugUWKA2tTyWTgJSX7/dU5jpKVZo6iAfb4N06aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","last_reissued_at":"2026-07-03T01:17:16.808952Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:16.808952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemanticAudio: Audio Generation and Editing in Semantic Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Xiquan Li, Yiwen Guo, Zheqi Dai","submitted_at":"2026-01-29T08:40:37Z","abstract_excerpt":"In recent years, Text-to-Audio Generation has achieved remarkable progress, offering sound creators powerful tools to transform textual inspirations into vivid audio. However, existing models predominantly operate directly in the acoustic latent space of a Variational Autoencoder (VAE), often leading to suboptimal alignment between generated audio and textual descriptions. In this paper, we introduce SemanticAudio, a novel framework that conducts both audio generation and editing directly in a high-level semantic space. We define this semantic space as a compact representation capturing the gl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21402","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/2601.21402/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":"2601.21402","created_at":"2026-07-03T01:17:16.809009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21402v2","created_at":"2026-07-03T01:17:16.809009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21402","created_at":"2026-07-03T01:17:16.809009+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLREWMNLXWAC","created_at":"2026-07-03T01:17:16.809009+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLREWMNLXWACOTD6","created_at":"2026-07-03T01:17:16.809009+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLREWMNL","created_at":"2026-07-03T01:17:16.809009+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/XLREWMNLXWACOTD6OSR7Q4ICNE","json":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE.json","graph_json":"https://pith.science/api/pith-number/XLREWMNLXWACOTD6OSR7Q4ICNE/graph.json","events_json":"https://pith.science/api/pith-number/XLREWMNLXWACOTD6OSR7Q4ICNE/events.json","paper":"https://pith.science/paper/XLREWMNL"},"agent_actions":{"view_html":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE","download_json":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE.json","view_paper":"https://pith.science/paper/XLREWMNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21402&json=true","fetch_graph":"https://pith.science/api/pith-number/XLREWMNLXWACOTD6OSR7Q4ICNE/graph.json","fetch_events":"https://pith.science/api/pith-number/XLREWMNLXWACOTD6OSR7Q4ICNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/action/storage_attestation","attest_author":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/action/author_attestation","sign_citation":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/action/citation_signature","submit_replication":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/action/replication_record"}},"created_at":"2026-07-03T01:17:16.809009+00:00","updated_at":"2026-07-03T01:17:16.809009+00:00"}