{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IPXISVEZXFA3JIBEDQFQSNKGSQ","short_pith_number":"pith:IPXISVEZ","schema_version":"1.0","canonical_sha256":"43ee895499b941b4a0241c0b09354694191f79699a594d76aafa6fe6f0a63d83","source":{"kind":"arxiv","id":"2509.06155","version":1},"attestation_state":"computed","paper":{"title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojie Li, Daxin Jiang, Deyu Zhou, Duomin Wang, Gang Yu, Ling-Hao Chen, Wei Zuo, Xili Dai, Xinyao Liao, Zixin Yin","submitted_at":"2025-09-07T17:55:03Z","abstract_excerpt":"We introduce UniVerse-1, a unified, Veo-3-like model capable of simultaneously generating coordinated audio and video. To enhance training efficiency, we bypass training from scratch and instead employ a stitching of experts (SoE) technique. This approach deeply fuses the corresponding blocks of pre-trained video and music generation experts models, thereby fully leveraging their foundational capabilities. To ensure accurate annotations and temporal alignment for both ambient sounds and speech with video content, we developed an online annotation pipeline that processes the required training d"},"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":"2509.06155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T17:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"aa6c30a95b1b42d3a52371df0c09f75997bc5f1a28bc181dd14c3e7ccfcb4395","abstract_canon_sha256":"50616309c7d9d6d02dfba852f4f44434df78576dc5c99134fa9f2e3ad01bdc35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:30.715951Z","signature_b64":"eqtifPOXcVpNjKZ5yPctnee5BiMQp5nXsfsxAHrQrWhG0AHV1KH8kkc392CJf/zMUA9hXpw8WViyisB1xzCFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ee895499b941b4a0241c0b09354694191f79699a594d76aafa6fe6f0a63d83","last_reissued_at":"2026-07-05T12:06:30.715454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:30.715454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojie Li, Daxin Jiang, Deyu Zhou, Duomin Wang, Gang Yu, Ling-Hao Chen, Wei Zuo, Xili Dai, Xinyao Liao, Zixin Yin","submitted_at":"2025-09-07T17:55:03Z","abstract_excerpt":"We introduce UniVerse-1, a unified, Veo-3-like model capable of simultaneously generating coordinated audio and video. To enhance training efficiency, we bypass training from scratch and instead employ a stitching of experts (SoE) technique. This approach deeply fuses the corresponding blocks of pre-trained video and music generation experts models, thereby fully leveraging their foundational capabilities. To ensure accurate annotations and temporal alignment for both ambient sounds and speech with video content, we developed an online annotation pipeline that processes the required training d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06155","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/2509.06155/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":"2509.06155","created_at":"2026-07-05T12:06:30.715508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06155v1","created_at":"2026-07-05T12:06:30.715508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06155","created_at":"2026-07-05T12:06:30.715508+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPXISVEZXFA3","created_at":"2026-07-05T12:06:30.715508+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPXISVEZXFA3JIBE","created_at":"2026-07-05T12:06:30.715508+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPXISVEZ","created_at":"2026-07-05T12:06:30.715508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07061","citing_title":"Do Joint Audio-Video Generation Models Understand Physics?","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29473","citing_title":"MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28035","citing_title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30073","citing_title":"Native Audio-Visual Alignment for Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17488","citing_title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18467","citing_title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12179","citing_title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12480","citing_title":"OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08729","citing_title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25819","citing_title":"Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23586","citing_title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23632","citing_title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19679","citing_title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11244","citing_title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12856","citing_title":"PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07061","citing_title":"Do Joint Audio-Video Generation Models Understand Physics?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ","json":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ.json","graph_json":"https://pith.science/api/pith-number/IPXISVEZXFA3JIBEDQFQSNKGSQ/graph.json","events_json":"https://pith.science/api/pith-number/IPXISVEZXFA3JIBEDQFQSNKGSQ/events.json","paper":"https://pith.science/paper/IPXISVEZ"},"agent_actions":{"view_html":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ","download_json":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ.json","view_paper":"https://pith.science/paper/IPXISVEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06155&json=true","fetch_graph":"https://pith.science/api/pith-number/IPXISVEZXFA3JIBEDQFQSNKGSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IPXISVEZXFA3JIBEDQFQSNKGSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ/action/storage_attestation","attest_author":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ/action/author_attestation","sign_citation":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ/action/citation_signature","submit_replication":"https://pith.science/pith/IPXISVEZXFA3JIBEDQFQSNKGSQ/action/replication_record"}},"created_at":"2026-07-05T12:06:30.715508+00:00","updated_at":"2026-07-05T12:06:30.715508+00:00"}