{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TRAAY2B4VIE5X4UGO4QV4PWKO2","short_pith_number":"pith:TRAAY2B4","canonical_record":{"source":{"id":"2407.10387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-15T01:49:59Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"226f7d5d0bf1832151dd501f9b7ac38af143b7bc5cea9187c227a558fcfefaec","abstract_canon_sha256":"84fd287e3a58e8b7ee5724544dda19df8d68fdc7e6bd9ccb64f73f5f67309282"},"schema_version":"1.0"},"canonical_sha256":"9c400c683caa09dbf28677215e3eca76a6db124bfd9ad4d7005d21ac68ce97da","source":{"kind":"arxiv","id":"2407.10387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10387","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10387v1","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10387","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"TRAAY2B4VIE5","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"TRAAY2B4VIE5X4UG","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"TRAAY2B4","created_at":"2026-07-05T08:43:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TRAAY2B4VIE5X4UGO4QV4PWKO2","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-15T01:49:59Z","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"title_canon_sha256":"226f7d5d0bf1832151dd501f9b7ac38af143b7bc5cea9187c227a558fcfefaec","abstract_canon_sha256":"84fd287e3a58e8b7ee5724544dda19df8d68fdc7e6bd9ccb64f73f5f67309282"},"schema_version":"1.0"},"canonical_sha256":"9c400c683caa09dbf28677215e3eca76a6db124bfd9ad4d7005d21ac68ce97da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:58.941805Z","signature_b64":"gpdP0ZD0ogAEP8xS3OwUONY6V8L1DYH+bkoQ09wav8NmjIpnrO+EpmgzG7KiZEqreM/H5TUz9NUeXncGT34jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c400c683caa09dbf28677215e3eca76a6db124bfd9ad4d7005d21ac68ce97da","last_reissued_at":"2026-07-05T08:43:58.941390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:58.941390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10387","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":"2026-07-05T08:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJM7RJbazEm0uFROcweFMMfFqII1+HLkwrhnRdIgMHx0+LbBzJuFHB+37DH59unmv0YGLCZ+yY19fXxa3b9kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:58:55.123374Z"},"content_sha256":"8c9cf42a78d01e2819ccfffad01f0445b901fed0aac8a2a7f2131342eb2cd6cf","schema_version":"1.0","event_id":"sha256:8c9cf42a78d01e2819ccfffad01f0445b901fed0aac8a2a7f2131342eb2cd6cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TRAAY2B4VIE5X4UGO4QV4PWKO2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chunghsin Yeh, Ioannis Tsiamas, Joan Serr\\`a, Santiago Pascual","submitted_at":"2024-07-15T01:49:59Z","abstract_excerpt":"Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural synchronization artifacts arise. Recent works have explored the progression of conditioning sound generators on still images and then video features, focusing on quality and semantic matching while ignoring synchronization, or by sacrificing some amount of quality to focus on improving synchronization only. In this work, we propose a V2A generative model, name"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10387","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/2407.10387/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":"2026-07-05T08:43:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lObpGRmYGOPFlMLFDUZNzNqSki2GTSyd9vEWNi9zrwiJjI82kMEFA1x6MNY+MIwJPFfgnxSVNcaKdvQTMKCeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:58:55.123918Z"},"content_sha256":"0eed714e37d0e3370094ea0ab06b81423fc121fcf23c6f1855cdc67f1d683eaa","schema_version":"1.0","event_id":"sha256:0eed714e37d0e3370094ea0ab06b81423fc121fcf23c6f1855cdc67f1d683eaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/bundle.json","state_url":"https://pith.science/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/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":"2026-08-10T03:58:55Z","links":{"resolver":"https://pith.science/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2","bundle":"https://pith.science/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/bundle.json","state":"https://pith.science/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TRAAY2B4VIE5X4UGO4QV4PWKO2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TRAAY2B4VIE5X4UGO4QV4PWKO2","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":"84fd287e3a58e8b7ee5724544dda19df8d68fdc7e6bd9ccb64f73f5f67309282","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-15T01:49:59Z","title_canon_sha256":"226f7d5d0bf1832151dd501f9b7ac38af143b7bc5cea9187c227a558fcfefaec"},"schema_version":"1.0","source":{"id":"2407.10387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10387","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10387v1","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10387","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"TRAAY2B4VIE5","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"TRAAY2B4VIE5X4UG","created_at":"2026-07-05T08:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"TRAAY2B4","created_at":"2026-07-05T08:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:0eed714e37d0e3370094ea0ab06b81423fc121fcf23c6f1855cdc67f1d683eaa","target":"graph","created_at":"2026-07-05T08:43:58Z","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/2407.10387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural synchronization artifacts arise. Recent works have explored the progression of conditioning sound generators on still images and then video features, focusing on quality and semantic matching while ignoring synchronization, or by sacrificing some amount of quality to focus on improving synchronization only. In this work, we propose a V2A generative model, name","authors_text":"Chunghsin Yeh, Ioannis Tsiamas, Joan Serr\\`a, Santiago Pascual","cross_cats":["cs.AI","cs.CV","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-15T01:49:59Z","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10387","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":"sha256:8c9cf42a78d01e2819ccfffad01f0445b901fed0aac8a2a7f2131342eb2cd6cf","target":"record","created_at":"2026-07-05T08:43:58Z","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":"84fd287e3a58e8b7ee5724544dda19df8d68fdc7e6bd9ccb64f73f5f67309282","cross_cats_sorted":["cs.AI","cs.CV","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-15T01:49:59Z","title_canon_sha256":"226f7d5d0bf1832151dd501f9b7ac38af143b7bc5cea9187c227a558fcfefaec"},"schema_version":"1.0","source":{"id":"2407.10387","kind":"arxiv","version":1}},"canonical_sha256":"9c400c683caa09dbf28677215e3eca76a6db124bfd9ad4d7005d21ac68ce97da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c400c683caa09dbf28677215e3eca76a6db124bfd9ad4d7005d21ac68ce97da","first_computed_at":"2026-07-05T08:43:58.941390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:58.941390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gpdP0ZD0ogAEP8xS3OwUONY6V8L1DYH+bkoQ09wav8NmjIpnrO+EpmgzG7KiZEqreM/H5TUz9NUeXncGT34jCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:58.941805Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c9cf42a78d01e2819ccfffad01f0445b901fed0aac8a2a7f2131342eb2cd6cf","sha256:0eed714e37d0e3370094ea0ab06b81423fc121fcf23c6f1855cdc67f1d683eaa"],"state_sha256":"1c86e29931b872c05a04d46cfb349b56e4d8aab1678cdae712541d2dc3bcdea8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MxT5w90mVfjNMdOX6aDJnqz08eIQ2DF+IzV+VDcLF+MBHxAfAQIWahNnNr9NOfOhFCUxLXuNptqsMzwLDrBuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:58:55.129117Z","bundle_sha256":"28c111a612da9fe666215042a47deef939f5e997a881f841a48c9bfbef84a4cd"}}