{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IMC6GS737QUDIGDTA3P2NLC76W","short_pith_number":"pith:IMC6GS73","schema_version":"1.0","canonical_sha256":"4305e34bfbfc2834187306dfa6ac5ff59f7901db2d3d4afcded980353b142060","source":{"kind":"arxiv","id":"2606.20101","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Dongyu Wang, Jean-Yves Guillemaut, Liting Gao, Shubin Zhang, Wenwu Wang, Yaru Chen, Yonggang Zhu, Zhenbo Li","submitted_at":"2026-06-18T11:20:08Z","abstract_excerpt":"Audio editing aims to modify specific content in an existing audio clip according to a natural language instruction while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion transformers provide stronger global modeling and multimodal fusion, but existing editing architecture"},"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":"2606.20101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T11:20:08Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"4c60186f2a6f55cd484c7fd3bea850171b823a17529d6ca9defd4176f2fceb70","abstract_canon_sha256":"2af5de162fec6603401c1f6693787153d080dfa90156884b9a04cf93e6dc99e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:02.911233Z","signature_b64":"KDmku+XbRleAR3FN7D8FTzGB0t/TSADA80Hia9+kSSbIP7viKfe8gtgAzSRJBkx02mHGqvX51euoJCKEXocbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4305e34bfbfc2834187306dfa6ac5ff59f7901db2d3d4afcded980353b142060","last_reissued_at":"2026-06-19T16:13:02.910843Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:02.910843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.SD","authors_text":"Dongyu Wang, Jean-Yves Guillemaut, Liting Gao, Shubin Zhang, Wenwu Wang, Yaru Chen, Yonggang Zhu, Zhenbo Li","submitted_at":"2026-06-18T11:20:08Z","abstract_excerpt":"Audio editing aims to modify specific content in an existing audio clip according to a natural language instruction while preserving the remaining acoustic content. Despite the remarkable progress of diffusion models, existing training-based editing methods mainly rely on the local inductive biases and cross-attention interaction in convolutional U-Net backbones, which often hinder long-range semantic alignment and precise understanding and localization of instructions. In contrast, diffusion transformers provide stronger global modeling and multimodal fusion, but existing editing architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20101","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/2606.20101/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":"2606.20101","created_at":"2026-06-19T16:13:02.910915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20101v1","created_at":"2026-06-19T16:13:02.910915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20101","created_at":"2026-06-19T16:13:02.910915+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMC6GS737QUD","created_at":"2026-06-19T16:13:02.910915+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMC6GS737QUDIGDT","created_at":"2026-06-19T16:13:02.910915+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMC6GS73","created_at":"2026-06-19T16:13:02.910915+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/IMC6GS737QUDIGDTA3P2NLC76W","json":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W.json","graph_json":"https://pith.science/api/pith-number/IMC6GS737QUDIGDTA3P2NLC76W/graph.json","events_json":"https://pith.science/api/pith-number/IMC6GS737QUDIGDTA3P2NLC76W/events.json","paper":"https://pith.science/paper/IMC6GS73"},"agent_actions":{"view_html":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W","download_json":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W.json","view_paper":"https://pith.science/paper/IMC6GS73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20101&json=true","fetch_graph":"https://pith.science/api/pith-number/IMC6GS737QUDIGDTA3P2NLC76W/graph.json","fetch_events":"https://pith.science/api/pith-number/IMC6GS737QUDIGDTA3P2NLC76W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W/action/storage_attestation","attest_author":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W/action/author_attestation","sign_citation":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W/action/citation_signature","submit_replication":"https://pith.science/pith/IMC6GS737QUDIGDTA3P2NLC76W/action/replication_record"}},"created_at":"2026-06-19T16:13:02.910915+00:00","updated_at":"2026-06-19T16:13:02.910915+00:00"}