{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5TLMBXSKQXAFQNAM6QCCJIZTKN","short_pith_number":"pith:5TLMBXSK","canonical_record":{"source":{"id":"2607.27011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T15:06:58Z","cross_cats_sorted":[],"title_canon_sha256":"14f064a82ed822117570d8eca76d21a422527890d368944a609e64f446f57815","abstract_canon_sha256":"5bb31f7a0cbdbd0e215d1790894d8ed23bd04d2641582d4e105b1bf4905746ad"},"schema_version":"1.0"},"canonical_sha256":"ecd6c0de4a85c058340cf40424a333534b1ec7cae708e39c008ab103c681afb1","source":{"kind":"arxiv","id":"2607.27011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27011","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27011v1","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27011","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"5TLMBXSKQXAF","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"5TLMBXSKQXAFQNAM","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"5TLMBXSK","created_at":"2026-07-30T01:23:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5TLMBXSKQXAFQNAM6QCCJIZTKN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T15:06:58Z","cross_cats_sorted":[],"title_canon_sha256":"14f064a82ed822117570d8eca76d21a422527890d368944a609e64f446f57815","abstract_canon_sha256":"5bb31f7a0cbdbd0e215d1790894d8ed23bd04d2641582d4e105b1bf4905746ad"},"schema_version":"1.0"},"canonical_sha256":"ecd6c0de4a85c058340cf40424a333534b1ec7cae708e39c008ab103c681afb1","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd6c0de4a85c058340cf40424a333534b1ec7cae708e39c008ab103c681afb1","last_reissued_at":"2026-07-30T01:23:20.094309Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:20.094309Z"},"source_kind":"arxiv","source_id":"2607.27011","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":"2026-07-30T01:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/EO7DPaIlExE6ux4Lmd8EdLDu9r0g4rcQb3kpXmSAcFw6YjjRRqsizPmispmQweug+LvGQwS97jJhtj+I+tAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:05:45.145401Z"},"content_sha256":"6aa2bc09cf7101e1be0c736aa1c8a6b81c62f3a701cf162835b640471c8f1dbf","schema_version":"1.0","event_id":"sha256:6aa2bc09cf7101e1be0c736aa1c8a6b81c62f3a701cf162835b640471c8f1dbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5TLMBXSKQXAFQNAM6QCCJIZTKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Qwen-Audio-3.0-Gen-Preview Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bajian Xiang, Cheng Wen, Han Zhao, Huaicheng Zhang, Junyu Dai, Lejun Min, Menglin Wu, Ruichen Zheng, Xiangang Li, Xiaoyue Duan, Xingchen Song, Xinyue Fan, Yihan Feng, Yiran Wang, Yufei Shi, Yunjia Li","submitted_at":"2026-07-29T15:06:58Z","abstract_excerpt":"Existing single-domain and multi-task audio systems remain limited in directly organizing speech, music, sound effects, ambience, and multiple roles into long-form temporal scenes. We present Qwen-Audio-3.0-Gen-Preview, a unified non-autoregressive framework that uses a Diffusion Transformer (DiT) and a shared variational autoencoder (VAE) to generate the complete mixed waveform. Prompt enhancement converts free-form requests into structured temporal records that are rendered as textual conditions, while a two-stage data curriculum and semantic conditional views train the proposed model to use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27011","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/2607.27011/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":"2026-07-30T01:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTNpJ7jxkY8FH29fzcoOYbWCe2tTfm70TZ758w59Lk4S4Fil7iC6qiX45yseQZABxKETzlfLkjJ17oXi8AcEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:05:45.146141Z"},"content_sha256":"036584fb5f6e027731e47ecc5a8b9c6a53375b47ea8efc40e4cb755b8f42e4a3","schema_version":"1.0","event_id":"sha256:036584fb5f6e027731e47ecc5a8b9c6a53375b47ea8efc40e4cb755b8f42e4a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/bundle.json","state_url":"https://pith.science/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/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":"2026-07-31T21:05:45Z","links":{"resolver":"https://pith.science/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN","bundle":"https://pith.science/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/bundle.json","state":"https://pith.science/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5TLMBXSKQXAFQNAM6QCCJIZTKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5TLMBXSKQXAFQNAM6QCCJIZTKN","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":"5bb31f7a0cbdbd0e215d1790894d8ed23bd04d2641582d4e105b1bf4905746ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T15:06:58Z","title_canon_sha256":"14f064a82ed822117570d8eca76d21a422527890d368944a609e64f446f57815"},"schema_version":"1.0","source":{"id":"2607.27011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27011","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27011v1","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27011","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"5TLMBXSKQXAF","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"5TLMBXSKQXAFQNAM","created_at":"2026-07-30T01:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"5TLMBXSK","created_at":"2026-07-30T01:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:036584fb5f6e027731e47ecc5a8b9c6a53375b47ea8efc40e4cb755b8f42e4a3","target":"graph","created_at":"2026-07-30T01:23:20Z","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/2607.27011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing single-domain and multi-task audio systems remain limited in directly organizing speech, music, sound effects, ambience, and multiple roles into long-form temporal scenes. We present Qwen-Audio-3.0-Gen-Preview, a unified non-autoregressive framework that uses a Diffusion Transformer (DiT) and a shared variational autoencoder (VAE) to generate the complete mixed waveform. Prompt enhancement converts free-form requests into structured temporal records that are rendered as textual conditions, while a two-stage data curriculum and semantic conditional views train the proposed model to use","authors_text":"Bajian Xiang, Cheng Wen, Han Zhao, Huaicheng Zhang, Junyu Dai, Lejun Min, Menglin Wu, Ruichen Zheng, Xiangang Li, Xiaoyue Duan, Xingchen Song, Xinyue Fan, Yihan Feng, Yiran Wang, Yufei Shi, Yunjia Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T15:06:58Z","title":"Qwen-Audio-3.0-Gen-Preview Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27011","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":"sha256:6aa2bc09cf7101e1be0c736aa1c8a6b81c62f3a701cf162835b640471c8f1dbf","target":"record","created_at":"2026-07-30T01:23:20Z","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":"5bb31f7a0cbdbd0e215d1790894d8ed23bd04d2641582d4e105b1bf4905746ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T15:06:58Z","title_canon_sha256":"14f064a82ed822117570d8eca76d21a422527890d368944a609e64f446f57815"},"schema_version":"1.0","source":{"id":"2607.27011","kind":"arxiv","version":1}},"canonical_sha256":"ecd6c0de4a85c058340cf40424a333534b1ec7cae708e39c008ab103c681afb1","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecd6c0de4a85c058340cf40424a333534b1ec7cae708e39c008ab103c681afb1","first_computed_at":"2026-07-30T01:23:20.094309Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:20.094309Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aa2bc09cf7101e1be0c736aa1c8a6b81c62f3a701cf162835b640471c8f1dbf","sha256:036584fb5f6e027731e47ecc5a8b9c6a53375b47ea8efc40e4cb755b8f42e4a3"],"state_sha256":"43551c5bb14f9b035a2e2c321eec42205adfb8b7174f722f084a3645f8337c9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sb5Pf79Xn50rH4rWbZM0dUDNfyh5658v688jUoOtd5gEB6eB7xtVu2LJxmC7HZfrBKMy7JqvHPDe0UDSJm9CDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T21:05:45.154690Z","bundle_sha256":"cf4b9f585630d1d233c8f436981d808c9d1d7fbdce59c74e30286e0e4b8b7e95"}}