{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IMC6GS737QUDIGDTA3P2NLC76W","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":"2af5de162fec6603401c1f6693787153d080dfa90156884b9a04cf93e6dc99e7","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T11:20:08Z","title_canon_sha256":"4c60186f2a6f55cd484c7fd3bea850171b823a17529d6ca9defd4176f2fceb70"},"schema_version":"1.0","source":{"id":"2606.20101","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20101","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20101v1","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20101","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"IMC6GS737QUD","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"IMC6GS737QUDIGDT","created_at":"2026-06-19T16:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"IMC6GS73","created_at":"2026-06-19T16:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:db289010baaa6521348d62b423db5d645202cfcf70662e34105d9168a0fbaf73","target":"graph","created_at":"2026-06-19T16:13:02Z","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/2606.20101/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongyu Wang, Jean-Yves Guillemaut, Liting Gao, Shubin Zhang, Wenwu Wang, Yaru Chen, Yonggang Zhu, Zhenbo Li","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T11:20:08Z","title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20101","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":"sha256:689128e7e5e4967e5612e67f0f995287cae26741843ce783fda940161edb9b8a","target":"record","created_at":"2026-06-19T16:13:02Z","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":"2af5de162fec6603401c1f6693787153d080dfa90156884b9a04cf93e6dc99e7","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-18T11:20:08Z","title_canon_sha256":"4c60186f2a6f55cd484c7fd3bea850171b823a17529d6ca9defd4176f2fceb70"},"schema_version":"1.0","source":{"id":"2606.20101","kind":"arxiv","version":1}},"canonical_sha256":"4305e34bfbfc2834187306dfa6ac5ff59f7901db2d3d4afcded980353b142060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4305e34bfbfc2834187306dfa6ac5ff59f7901db2d3d4afcded980353b142060","first_computed_at":"2026-06-19T16:13:02.910843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:02.910843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDmku+XbRleAR3FN7D8FTzGB0t/TSADA80Hia9+kSSbIP7viKfe8gtgAzSRJBkx02mHGqvX51euoJCKEXocbDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:02.911233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20101","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:689128e7e5e4967e5612e67f0f995287cae26741843ce783fda940161edb9b8a","sha256:db289010baaa6521348d62b423db5d645202cfcf70662e34105d9168a0fbaf73"],"state_sha256":"2bac1cce8044bb02da93c7927c8bee14730549d2efb01e5ceae102a15dcddefb"}