{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TZGGVWPFZPTV3VVDHGIZAAZ2ZD","short_pith_number":"pith:TZGGVWPF","schema_version":"1.0","canonical_sha256":"9e4c6ad9e5cbe75dd6a3399190033ac8edff3231f670ea8ebb4d06e5c68c176b","source":{"kind":"arxiv","id":"2606.29473","version":1},"attestation_state":"computed","paper":{"title":"MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Jing Wang, Kaiqi Liu, Kun Gai, Pengfei Wan, Qiulin Wang, Shuchen Weng, Xintao Wang, Yunyao Mao, Zheng Geng, Ziqi Cai","submitted_at":"2026-06-28T16:01:04Z","abstract_excerpt":"While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing methods suffer from temporal misalignment, limited controllability, and incomplete scripting. In this paper, we propose MAVIN, the first framework for multi-shot audio-visual generation with customized narrative control. To resolve temporal misalignment, we propose boundary-aware attention, which leverages hierarchical captions and boundary-aware token routing to render audio-visual elements within their respective temp"},"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":"2606.29473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T16:01:04Z","cross_cats_sorted":[],"title_canon_sha256":"f038a43293b8021bff0c05229b469e535d3ad0d2cbfeeb04a65b616b962a6b0a","abstract_canon_sha256":"c2121934cef6cd78c8dc3096781add4b2e1a95686f08c343e544e583ed57fdbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:07.893247Z","signature_b64":"EULDjLuKxq/j7rXuI7X09z7mVXyorl0WBgF1ZX4zEEPKszLoYZjXQWdRZax79Oo8jpniflVvM0XopdI39WW+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e4c6ad9e5cbe75dd6a3399190033ac8edff3231f670ea8ebb4d06e5c68c176b","last_reissued_at":"2026-06-30T01:18:07.892467Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:07.892467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Jing Wang, Kaiqi Liu, Kun Gai, Pengfei Wan, Qiulin Wang, Shuchen Weng, Xintao Wang, Yunyao Mao, Zheng Geng, Ziqi Cai","submitted_at":"2026-06-28T16:01:04Z","abstract_excerpt":"While recent generative models produce high-fidelity videos, they struggle with the complex narrative control required for coherent multi-shot audio-visual generation. Existing methods suffer from temporal misalignment, limited controllability, and incomplete scripting. In this paper, we propose MAVIN, the first framework for multi-shot audio-visual generation with customized narrative control. To resolve temporal misalignment, we propose boundary-aware attention, which leverages hierarchical captions and boundary-aware token routing to render audio-visual elements within their respective temp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29473","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/2606.29473/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":"2606.29473","created_at":"2026-06-30T01:18:07.892615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29473v1","created_at":"2026-06-30T01:18:07.892615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29473","created_at":"2026-06-30T01:18:07.892615+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZGGVWPFZPTV","created_at":"2026-06-30T01:18:07.892615+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZGGVWPFZPTV3VVD","created_at":"2026-06-30T01:18:07.892615+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZGGVWPF","created_at":"2026-06-30T01:18:07.892615+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/TZGGVWPFZPTV3VVDHGIZAAZ2ZD","json":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD.json","graph_json":"https://pith.science/api/pith-number/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/graph.json","events_json":"https://pith.science/api/pith-number/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/events.json","paper":"https://pith.science/paper/TZGGVWPF"},"agent_actions":{"view_html":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD","download_json":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD.json","view_paper":"https://pith.science/paper/TZGGVWPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29473&json=true","fetch_graph":"https://pith.science/api/pith-number/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/graph.json","fetch_events":"https://pith.science/api/pith-number/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/action/storage_attestation","attest_author":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/action/author_attestation","sign_citation":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/action/citation_signature","submit_replication":"https://pith.science/pith/TZGGVWPFZPTV3VVDHGIZAAZ2ZD/action/replication_record"}},"created_at":"2026-06-30T01:18:07.892615+00:00","updated_at":"2026-06-30T01:18:07.892615+00:00"}