{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TZGGVWPFZPTV3VVDHGIZAAZ2ZD","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":"c2121934cef6cd78c8dc3096781add4b2e1a95686f08c343e544e583ed57fdbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T16:01:04Z","title_canon_sha256":"f038a43293b8021bff0c05229b469e535d3ad0d2cbfeeb04a65b616b962a6b0a"},"schema_version":"1.0","source":{"id":"2606.29473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29473","created_at":"2026-06-30T01:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29473v1","created_at":"2026-06-30T01:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29473","created_at":"2026-06-30T01:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"TZGGVWPFZPTV","created_at":"2026-06-30T01:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"TZGGVWPFZPTV3VVD","created_at":"2026-06-30T01:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"TZGGVWPF","created_at":"2026-06-30T01:18:07Z"}],"graph_snapshots":[{"event_id":"sha256:d62e71b12a5bab4150b694cbd28b03463a053f9e760c49138937f18544750173","target":"graph","created_at":"2026-06-30T01:18:07Z","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/2606.29473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boxin Shi, Jing Wang, Kaiqi Liu, Kun Gai, Pengfei Wan, Qiulin Wang, Shuchen Weng, Xintao Wang, Yunyao Mao, Zheng Geng, Ziqi Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T16:01:04Z","title":"MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29473","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:f41e7bcca2cfc35b24e9ab00c063a8a81bd2809b428b4a6b9a02ea7c1c14cea8","target":"record","created_at":"2026-06-30T01:18:07Z","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":"c2121934cef6cd78c8dc3096781add4b2e1a95686f08c343e544e583ed57fdbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T16:01:04Z","title_canon_sha256":"f038a43293b8021bff0c05229b469e535d3ad0d2cbfeeb04a65b616b962a6b0a"},"schema_version":"1.0","source":{"id":"2606.29473","kind":"arxiv","version":1}},"canonical_sha256":"9e4c6ad9e5cbe75dd6a3399190033ac8edff3231f670ea8ebb4d06e5c68c176b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e4c6ad9e5cbe75dd6a3399190033ac8edff3231f670ea8ebb4d06e5c68c176b","first_computed_at":"2026-06-30T01:18:07.892467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:07.892467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EULDjLuKxq/j7rXuI7X09z7mVXyorl0WBgF1ZX4zEEPKszLoYZjXQWdRZax79Oo8jpniflVvM0XopdI39WW+Aw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:07.893247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f41e7bcca2cfc35b24e9ab00c063a8a81bd2809b428b4a6b9a02ea7c1c14cea8","sha256:d62e71b12a5bab4150b694cbd28b03463a053f9e760c49138937f18544750173"],"state_sha256":"65aa4c1c9edc892dbc3d5bc409cd21c9cc463d015226c5083f086dc16499e1b0"}