{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4HDEKCP25MQPVKHSGUVRAX464O","short_pith_number":"pith:4HDEKCP2","canonical_record":{"source":{"id":"2406.00320","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-01T06:40:22Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"39e981a05372a9acaeb99bd74c8d5088d59c1653e53c2bbadb6fc71e4f65fdf3","abstract_canon_sha256":"2b995192a3fb5c6b5986c5608833127c887405f4b6301996c56f352a6c8d8e3d"},"schema_version":"1.0"},"canonical_sha256":"e1c64509faeb20faa8f2352b105f9ee3928ebda0350ade90ab7f093dcb2f1efd","source":{"kind":"arxiv","id":"2406.00320","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00320","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00320v4","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00320","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"4HDEKCP25MQP","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"4HDEKCP25MQPVKHS","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"4HDEKCP2","created_at":"2026-07-05T09:56:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4HDEKCP25MQPVKHSGUVRAX464O","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00320","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-01T06:40:22Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"39e981a05372a9acaeb99bd74c8d5088d59c1653e53c2bbadb6fc71e4f65fdf3","abstract_canon_sha256":"2b995192a3fb5c6b5986c5608833127c887405f4b6301996c56f352a6c8d8e3d"},"schema_version":"1.0"},"canonical_sha256":"e1c64509faeb20faa8f2352b105f9ee3928ebda0350ade90ab7f093dcb2f1efd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:51.967625Z","signature_b64":"boBG7OnCCLRS3+VBop0JGs5nqQHZA6Co7ySa/PRdjbcofUZB2NxVK8I+9z45eEMJ5hF0UgsInkWL5I6/GrZyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1c64509faeb20faa8f2352b105f9ee3928ebda0350ade90ab7f093dcb2f1efd","last_reissued_at":"2026-07-05T09:56:51.967123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:51.967123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00320","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIT3HGNzrVqsl4Jhyc6FI2ataaUviPaFxC0N4aqfTAfltrr3Pv6AFhnORQcoIq/tWn1ez3R8YKxZmbnp1qviDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:05:32.351117Z"},"content_sha256":"ea0ef88fa922cf118eaecb28072f4a9aff6ec8ca4fc807034c9adf2a45b23eae","schema_version":"1.0","event_id":"sha256:ea0ef88fa922cf118eaecb28072f4a9aff6ec8ca4fc807034c9adf2a45b23eae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4HDEKCP25MQPVKHSGUVRAX464O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fuming You, Jiawei Huang, Rongjie Huang, Ruiqi Li, Wenxiang Guo, Yongqi Wang, Zehan Wang, Zhou Zhao","submitted_at":"2024-06-01T06:40:22Z","abstract_excerpt":"Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00320","kind":"arxiv","version":4},"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/2406.00320/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":"2026-07-05T09:56:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWGBlRlLJv1jTfsvR5TSoE0CYu/+f3RJS8/zBrVlc3qlMzeqJql29NgulguxAAXeALsbrT8KFiqwbLksjOYbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:05:32.351623Z"},"content_sha256":"d2f1a1bbe95ac73c4403fa2d1ba0f981ad1be6f67adb61678187ed78a17b84b6","schema_version":"1.0","event_id":"sha256:d2f1a1bbe95ac73c4403fa2d1ba0f981ad1be6f67adb61678187ed78a17b84b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HDEKCP25MQPVKHSGUVRAX464O/bundle.json","state_url":"https://pith.science/pith/4HDEKCP25MQPVKHSGUVRAX464O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HDEKCP25MQPVKHSGUVRAX464O/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":"2026-08-19T23:05:32Z","links":{"resolver":"https://pith.science/pith/4HDEKCP25MQPVKHSGUVRAX464O","bundle":"https://pith.science/pith/4HDEKCP25MQPVKHSGUVRAX464O/bundle.json","state":"https://pith.science/pith/4HDEKCP25MQPVKHSGUVRAX464O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HDEKCP25MQPVKHSGUVRAX464O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4HDEKCP25MQPVKHSGUVRAX464O","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":"2b995192a3fb5c6b5986c5608833127c887405f4b6301996c56f352a6c8d8e3d","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-01T06:40:22Z","title_canon_sha256":"39e981a05372a9acaeb99bd74c8d5088d59c1653e53c2bbadb6fc71e4f65fdf3"},"schema_version":"1.0","source":{"id":"2406.00320","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00320","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00320v4","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00320","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"4HDEKCP25MQP","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"4HDEKCP25MQPVKHS","created_at":"2026-07-05T09:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"4HDEKCP2","created_at":"2026-07-05T09:56:51Z"}],"graph_snapshots":[{"event_id":"sha256:d2f1a1bbe95ac73c4403fa2d1ba0f981ad1be6f67adb61678187ed78a17b84b6","target":"graph","created_at":"2026-07-05T09:56:51Z","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/2406.00320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video, and it remains challenging to build V2A models with high generation quality, efficiency, and visual-audio temporal synchrony. We propose Frieren, a V2A model based on rectified flow matching. Frieren regresses the conditional transport vector field from noise to spectrogram latent with straight paths and conducts sampling by solving ODE, outperforming autoregressive and score-based models in terms of audio quality. By employing a non-autoregressive vector field estimator based on a feed-forward transfo","authors_text":"Fuming You, Jiawei Huang, Rongjie Huang, Ruiqi Li, Wenxiang Guo, Yongqi Wang, Zehan Wang, Zhou Zhao","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-01T06:40:22Z","title":"Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00320","kind":"arxiv","version":4},"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:ea0ef88fa922cf118eaecb28072f4a9aff6ec8ca4fc807034c9adf2a45b23eae","target":"record","created_at":"2026-07-05T09:56:51Z","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":"2b995192a3fb5c6b5986c5608833127c887405f4b6301996c56f352a6c8d8e3d","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-01T06:40:22Z","title_canon_sha256":"39e981a05372a9acaeb99bd74c8d5088d59c1653e53c2bbadb6fc71e4f65fdf3"},"schema_version":"1.0","source":{"id":"2406.00320","kind":"arxiv","version":4}},"canonical_sha256":"e1c64509faeb20faa8f2352b105f9ee3928ebda0350ade90ab7f093dcb2f1efd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1c64509faeb20faa8f2352b105f9ee3928ebda0350ade90ab7f093dcb2f1efd","first_computed_at":"2026-07-05T09:56:51.967123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:51.967123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"boBG7OnCCLRS3+VBop0JGs5nqQHZA6Co7ySa/PRdjbcofUZB2NxVK8I+9z45eEMJ5hF0UgsInkWL5I6/GrZyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:51.967625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00320","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea0ef88fa922cf118eaecb28072f4a9aff6ec8ca4fc807034c9adf2a45b23eae","sha256:d2f1a1bbe95ac73c4403fa2d1ba0f981ad1be6f67adb61678187ed78a17b84b6"],"state_sha256":"263056149b8b255d781712299fba68eb983a5bb29b54640e1b45ced9d2352210"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJAJOdEF7MQ0rSpkxj5WOBuZf+kYdumzveZgmrXXpZbBsUq6MHmlmGDbogIor4lHwZS3XkhZwXynYV3FED4eCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:05:32.356806Z","bundle_sha256":"54dea712b14317b4507d2bce3e8af3d29fdcaeccecf093a05fb9814fefa5801b"}}