{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NZNIPVSQWVBRNTBWZOJFLBWXIL","short_pith_number":"pith:NZNIPVSQ","canonical_record":{"source":{"id":"2506.08003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b5360a601d773ab31fbce07d544e1387c81913fdd77ef286a23772d4c8e7721","abstract_canon_sha256":"7dcec77450943c246b89f1821bb5fe3992cbb33b1bb7eb64006dc80d7e3e493f"},"schema_version":"1.0"},"canonical_sha256":"6e5a87d650b54316cc36cb925586d742fedc01a012ef94f6a89fea6030ce549c","source":{"kind":"arxiv","id":"2506.08003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08003","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08003v1","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08003","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"NZNIPVSQWVBR","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"NZNIPVSQWVBRNTBW","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"NZNIPVSQ","created_at":"2026-07-05T11:18:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NZNIPVSQWVBRNTBWZOJFLBWXIL","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b5360a601d773ab31fbce07d544e1387c81913fdd77ef286a23772d4c8e7721","abstract_canon_sha256":"7dcec77450943c246b89f1821bb5fe3992cbb33b1bb7eb64006dc80d7e3e493f"},"schema_version":"1.0"},"canonical_sha256":"6e5a87d650b54316cc36cb925586d742fedc01a012ef94f6a89fea6030ce549c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:37.027805Z","signature_b64":"/ZfbAZEJE3S7if03mxIOdw7aM+IFS6qcNfN7i9SNzWJRo/aQKfMGzK2yRtp8MAas5bRp6uAVTAydRjGdaAO7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e5a87d650b54316cc36cb925586d742fedc01a012ef94f6a89fea6030ce549c","last_reissued_at":"2026-07-05T11:18:37.027202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:37.027202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08003","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":"2026-07-05T11:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzbGX4/BvtFKv8pUVCH0oimLujl6GTKxVLZmdhZtbKNz6CZZD0BVy1YHKBXXfZkbFOTVYA138TgYGhqFjChLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:12.854369Z"},"content_sha256":"63673b629c361218a35f32188bc4320dafbcaf2639f64757c75401408bc913a8","schema_version":"1.0","event_id":"sha256:63673b629c361218a35f32188bc4320dafbcaf2639f64757c75401408bc913a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NZNIPVSQWVBRNTBWZOJFLBWXIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boxin Shi, Haojie Zheng, Shuchen Weng, Si Li, Xinlong Wang, Zheng Chang","submitted_at":"2025-06-09T17:59:42Z","abstract_excerpt":"Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08003","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/2506.08003/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":"2026-07-05T11:18:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wz5f9YkXoqwaX4+JvWxP5AP2jD8fPcHdVXElY70KDaD0IZE8a7doAzakRxl8wsGf5TwIG55gwfQreQMJY4eTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:12:12.855138Z"},"content_sha256":"f4c4de364b6f3bba9fcf0552f74799ea5b0aa4af13cb9d78a199d15a93e819ee","schema_version":"1.0","event_id":"sha256:f4c4de364b6f3bba9fcf0552f74799ea5b0aa4af13cb9d78a199d15a93e819ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/bundle.json","state_url":"https://pith.science/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/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":"2026-08-10T03:12:12Z","links":{"resolver":"https://pith.science/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL","bundle":"https://pith.science/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/bundle.json","state":"https://pith.science/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZNIPVSQWVBRNTBWZOJFLBWXIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NZNIPVSQWVBRNTBWZOJFLBWXIL","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":"7dcec77450943c246b89f1821bb5fe3992cbb33b1bb7eb64006dc80d7e3e493f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:42Z","title_canon_sha256":"7b5360a601d773ab31fbce07d544e1387c81913fdd77ef286a23772d4c8e7721"},"schema_version":"1.0","source":{"id":"2506.08003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08003","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08003v1","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08003","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_12","alias_value":"NZNIPVSQWVBR","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_16","alias_value":"NZNIPVSQWVBRNTBW","created_at":"2026-07-05T11:18:37Z"},{"alias_kind":"pith_short_8","alias_value":"NZNIPVSQ","created_at":"2026-07-05T11:18:37Z"}],"graph_snapshots":[{"event_id":"sha256:f4c4de364b6f3bba9fcf0552f74799ea5b0aa4af13cb9d78a199d15a93e819ee","target":"graph","created_at":"2026-07-05T11:18:37Z","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/2506.08003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio is inherently temporal and closely synchronized with the visual world, making it a naturally aligned and expressive control signal for controllable video generation (e.g., movies). Beyond control, directly translating audio into video is essential for understanding and visualizing rich audio narratives (e.g., Podcasts or historical recordings). However, existing approaches fall short in generating high-quality videos with precise audio-visual synchronization, especially across diverse and complex audio types. In this work, we introduce MTV, a versatile framework for audio-sync video gene","authors_text":"Boxin Shi, Haojie Zheng, Shuchen Weng, Si Li, Xinlong Wang, Zheng Chang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:42Z","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08003","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":"sha256:63673b629c361218a35f32188bc4320dafbcaf2639f64757c75401408bc913a8","target":"record","created_at":"2026-07-05T11:18:37Z","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":"7dcec77450943c246b89f1821bb5fe3992cbb33b1bb7eb64006dc80d7e3e493f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:42Z","title_canon_sha256":"7b5360a601d773ab31fbce07d544e1387c81913fdd77ef286a23772d4c8e7721"},"schema_version":"1.0","source":{"id":"2506.08003","kind":"arxiv","version":1}},"canonical_sha256":"6e5a87d650b54316cc36cb925586d742fedc01a012ef94f6a89fea6030ce549c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e5a87d650b54316cc36cb925586d742fedc01a012ef94f6a89fea6030ce549c","first_computed_at":"2026-07-05T11:18:37.027202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:37.027202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ZfbAZEJE3S7if03mxIOdw7aM+IFS6qcNfN7i9SNzWJRo/aQKfMGzK2yRtp8MAas5bRp6uAVTAydRjGdaAO7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:37.027805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63673b629c361218a35f32188bc4320dafbcaf2639f64757c75401408bc913a8","sha256:f4c4de364b6f3bba9fcf0552f74799ea5b0aa4af13cb9d78a199d15a93e819ee"],"state_sha256":"50e50186589c426e147f92d39b4907745dcccdf29fa73eade365745d98d4c911"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OCVEZChFpUwzVtYsegHyNkbKNimKk8eM4CEvw2syrfzmxeWcg9lNbGZpqbtdUh3he56riCg7917YZmk4tCQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:12:12.859861Z","bundle_sha256":"61631721cdf8ff060061eb23cf3988bf861cd2cad04604a33e1b191fcfb6809e"}}