{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XLREWMNLXWACOTD6OSR7Q4ICNE","short_pith_number":"pith:XLREWMNL","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"},"canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","source":{"kind":"arxiv","id":"2601.21402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21402","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21402v2","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21402","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"XLREWMNLXWAC","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"XLREWMNLXWACOTD6","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"XLREWMNL","created_at":"2026-07-03T01:17:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XLREWMNLXWACOTD6OSR7Q4ICNE","target":"record","payload":{"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"},"canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","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"},"source_kind":"arxiv","source_id":"2601.21402","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":"2026-07-03T01:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y6Tkgeyzd8niP9ZNUo2QQ4nnDAOs+uhPI+zfgzzWTPpiyK6vJJu+XCYbMGDMoVGFGFSjWFU2NyWcEE3PLoL3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:31:38.635162Z"},"content_sha256":"dc66779e9567858df949ba94c1f89ea504bc67f66b2b7216f105575f25e63ea1","schema_version":"1.0","event_id":"sha256:dc66779e9567858df949ba94c1f89ea504bc67f66b2b7216f105575f25e63ea1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XLREWMNLXWACOTD6OSR7Q4ICNE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-03T01:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dS/Ajp+Ht2jQ0lNdBD6dP4kJrx4GMOt2RrguAA8RyE9ta/XGklF00S530gN5VDG+sISrPwGzoXr9QQ/7LQD0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T18:31:38.635549Z"},"content_sha256":"57f1027a2851b8264c47c349bb75541d8932510cfd9e12694f35ef81ca0b21a7","schema_version":"1.0","event_id":"sha256:57f1027a2851b8264c47c349bb75541d8932510cfd9e12694f35ef81ca0b21a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/bundle.json","state_url":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/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":"2026-07-03T18:31:38Z","links":{"resolver":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE","bundle":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/bundle.json","state":"https://pith.science/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLREWMNLXWACOTD6OSR7Q4ICNE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XLREWMNLXWACOTD6OSR7Q4ICNE","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":"132960c92449102a40c1ae1b1c8ff9f245762f868b2ebf27444542ff5fc774a0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-29T08:40:37Z","title_canon_sha256":"92725ede3027441f72ce82420f89a79bbbfa76651b7dfe6dd54058dda949d6bd"},"schema_version":"1.0","source":{"id":"2601.21402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21402","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21402v2","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21402","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"XLREWMNLXWAC","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"XLREWMNLXWACOTD6","created_at":"2026-07-03T01:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"XLREWMNL","created_at":"2026-07-03T01:17:16Z"}],"graph_snapshots":[{"event_id":"sha256:57f1027a2851b8264c47c349bb75541d8932510cfd9e12694f35ef81ca0b21a7","target":"graph","created_at":"2026-07-03T01:17:16Z","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/2601.21402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunyat Wu, Guangyan Zhang, Haolin He, Jingyu Li, Qiuqiang Kong, Xiquan Li, Yiwen Guo, Zheqi Dai","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-29T08:40:37Z","title":"SemanticAudio: Audio Generation and Editing in Semantic Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21402","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:dc66779e9567858df949ba94c1f89ea504bc67f66b2b7216f105575f25e63ea1","target":"record","created_at":"2026-07-03T01:17:16Z","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":"132960c92449102a40c1ae1b1c8ff9f245762f868b2ebf27444542ff5fc774a0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-29T08:40:37Z","title_canon_sha256":"92725ede3027441f72ce82420f89a79bbbfa76651b7dfe6dd54058dda949d6bd"},"schema_version":"1.0","source":{"id":"2601.21402","kind":"arxiv","version":2}},"canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bae24b31abbd80274c7e74a3f87102693cd3fcb7118004916defc04d4494328a","first_computed_at":"2026-07-03T01:17:16.808952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:16.808952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yY8HXXV5h3PucgXcRzgxWKjyexdwH0piarYL3jIfoLAA0sQugUWKA2tTyWTgJSX7/dU5jpKVZo6iAfb4N06aAg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:16.809436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc66779e9567858df949ba94c1f89ea504bc67f66b2b7216f105575f25e63ea1","sha256:57f1027a2851b8264c47c349bb75541d8932510cfd9e12694f35ef81ca0b21a7"],"state_sha256":"ff6ad6496bac2d4e78dfb3277b1ff31d452be79ea334a8f808d9fc7ed9cbba1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VGTRTAROhbxaF8JPotqzwSIaHHP373UJ+qN5J+l+B9X6SFmtR2X8U3O+DRCSbbzPYoZR4K1eLrZeffIPyQ8cDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T18:31:38.638917Z","bundle_sha256":"90d6ab854783fd7b182b00224a2f8836d1edc40021b7c23f73ffcfab48515828"}}