{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7H47QJAJPPW2EAY35YBL6MVTIY","short_pith_number":"pith:7H47QJAJ","canonical_record":{"source":{"id":"2607.06405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T15:34:43Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6779e68d5a2a24bd4623e5516365eab582a6949d88e1ac515359075bd84d0186","abstract_canon_sha256":"e1b44366350712c771f16a1fb3ac44288fda2f74dbec39de444c72f9e3661e41"},"schema_version":"1.0"},"canonical_sha256":"f9f9f824097beda2031bee02bf32b346052a4cdcc418ec123a48b713a6bbe715","source":{"kind":"arxiv","id":"2607.06405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06405","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06405v1","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06405","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"7H47QJAJPPW2","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"7H47QJAJPPW2EAY3","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"7H47QJAJ","created_at":"2026-07-08T01:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7H47QJAJPPW2EAY35YBL6MVTIY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.06405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T15:34:43Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6779e68d5a2a24bd4623e5516365eab582a6949d88e1ac515359075bd84d0186","abstract_canon_sha256":"e1b44366350712c771f16a1fb3ac44288fda2f74dbec39de444c72f9e3661e41"},"schema_version":"1.0"},"canonical_sha256":"f9f9f824097beda2031bee02bf32b346052a4cdcc418ec123a48b713a6bbe715","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:24.515329Z","signature_b64":"qsAOZb9kuow9q9FSI18nslSY/p5sTzfjwN2CIQ9P2o1AP8i9Jyrs4ZNlODdkJLNwZ3MtJJanGZecgzeZQLb9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f9f824097beda2031bee02bf32b346052a4cdcc418ec123a48b713a6bbe715","last_reissued_at":"2026-07-08T01:19:24.514901Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:24.514901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.06405","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":"2026-07-08T01:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcSe7aX/kA0Er6Cdh40+IXwUeJ4cCJ+Hoh/ZuCFwCr7Ar216lCKZ+1K/lpoeXIsk9RKJ13Ku6YtpUaVyZkdEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:19:54.045832Z"},"content_sha256":"465694e3ba75a16cd56a7197bebff09e021b4fa84d4e372dea2f21e1a4aa397e","schema_version":"1.0","event_id":"sha256:465694e3ba75a16cd56a7197bebff09e021b4fa84d4e372dea2f21e1a4aa397e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7H47QJAJPPW2EAY35YBL6MVTIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.MM","authors_text":"Long-Khanh Pham, Luong Tran, Ngoc-Son Nguyen, Paarth Neekhara, Shezheen Hussain, Thanh V. T. Tran, Van Nguyen","submitted_at":"2026-07-07T15:34:43Z","abstract_excerpt":"Video-to-audio (V2A) generation aims to synthesize realistic audio that is both semantically consistent with and temporally synchronized to a silent video. Despite recent progress, many methods still rely on multi-stage training, resulting in high computational costs and long runtimes, or transform visual input into text to leverage pretrained text-to-audio models, sacrificing fine-grained temporal cues. To overcome these limitations, we propose Flowley, an end-to-end, single-stage training architecture that produces soundtracks by combining visual features with textual prompts. Crucially, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06405","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/2607.06405/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":"2026-07-08T01:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UzsoaPaTUBjCWMMUV1f2XBnBl8gQds5KE9hPEv+hZbt/UuRJq5SYSd9DG4dzViMvVqimGWeXioELE0MVkaogCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:19:54.046800Z"},"content_sha256":"dfcd089b120852ffc320ced4c829cfa80d29bd464c2d88e713e1efffa26512df","schema_version":"1.0","event_id":"sha256:dfcd089b120852ffc320ced4c829cfa80d29bd464c2d88e713e1efffa26512df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7H47QJAJPPW2EAY35YBL6MVTIY/bundle.json","state_url":"https://pith.science/pith/7H47QJAJPPW2EAY35YBL6MVTIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7H47QJAJPPW2EAY35YBL6MVTIY/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":"2026-08-15T04:19:54Z","links":{"resolver":"https://pith.science/pith/7H47QJAJPPW2EAY35YBL6MVTIY","bundle":"https://pith.science/pith/7H47QJAJPPW2EAY35YBL6MVTIY/bundle.json","state":"https://pith.science/pith/7H47QJAJPPW2EAY35YBL6MVTIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7H47QJAJPPW2EAY35YBL6MVTIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7H47QJAJPPW2EAY35YBL6MVTIY","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":"e1b44366350712c771f16a1fb3ac44288fda2f74dbec39de444c72f9e3661e41","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T15:34:43Z","title_canon_sha256":"6779e68d5a2a24bd4623e5516365eab582a6949d88e1ac515359075bd84d0186"},"schema_version":"1.0","source":{"id":"2607.06405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06405","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06405v1","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06405","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"7H47QJAJPPW2","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"7H47QJAJPPW2EAY3","created_at":"2026-07-08T01:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"7H47QJAJ","created_at":"2026-07-08T01:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:dfcd089b120852ffc320ced4c829cfa80d29bd464c2d88e713e1efffa26512df","target":"graph","created_at":"2026-07-08T01:19:24Z","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/2607.06405/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 realistic audio that is both semantically consistent with and temporally synchronized to a silent video. Despite recent progress, many methods still rely on multi-stage training, resulting in high computational costs and long runtimes, or transform visual input into text to leverage pretrained text-to-audio models, sacrificing fine-grained temporal cues. To overcome these limitations, we propose Flowley, an end-to-end, single-stage training architecture that produces soundtracks by combining visual features with textual prompts. Crucially, we ","authors_text":"Long-Khanh Pham, Luong Tran, Ngoc-Son Nguyen, Paarth Neekhara, Shezheen Hussain, Thanh V. T. Tran, Van Nguyen","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T15:34:43Z","title":"Precise Video-to-Audio Generation with Cross-Modal Alignment in Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06405","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":"sha256:465694e3ba75a16cd56a7197bebff09e021b4fa84d4e372dea2f21e1a4aa397e","target":"record","created_at":"2026-07-08T01:19:24Z","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":"e1b44366350712c771f16a1fb3ac44288fda2f74dbec39de444c72f9e3661e41","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2026-07-07T15:34:43Z","title_canon_sha256":"6779e68d5a2a24bd4623e5516365eab582a6949d88e1ac515359075bd84d0186"},"schema_version":"1.0","source":{"id":"2607.06405","kind":"arxiv","version":1}},"canonical_sha256":"f9f9f824097beda2031bee02bf32b346052a4cdcc418ec123a48b713a6bbe715","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9f9f824097beda2031bee02bf32b346052a4cdcc418ec123a48b713a6bbe715","first_computed_at":"2026-07-08T01:19:24.514901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:24.514901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qsAOZb9kuow9q9FSI18nslSY/p5sTzfjwN2CIQ9P2o1AP8i9Jyrs4ZNlODdkJLNwZ3MtJJanGZecgzeZQLb9Bg==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:24.515329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:465694e3ba75a16cd56a7197bebff09e021b4fa84d4e372dea2f21e1a4aa397e","sha256:dfcd089b120852ffc320ced4c829cfa80d29bd464c2d88e713e1efffa26512df"],"state_sha256":"426e431ebfd54d0f4a7efef2ab8b2be64cab87687c54e14bd0217acb8f592aff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHkR0SaI3O4yarDIYK3H2NO25pwKcuWdz0LN67NIgMXYQOUNH9gK+Z54wUsU8R4wAw3G3YwY7yFn5bwiw3JeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:19:54.053300Z","bundle_sha256":"8926fb44150ab4f3f6608090e24b2eb1fe4dde098ee90db0d68978da87e2716a"}}