{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5T6GQ5XKF3BQU6GGJB22KL52A4","short_pith_number":"pith:5T6GQ5XK","canonical_record":{"source":{"id":"2409.15157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-23T16:04:50Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"dd7d0f5f023de496ab3cfc6beb21c22fcdeb64aa27a11518fd917db383db0233","abstract_canon_sha256":"262c132abd7a8d3ea2c640154ac8d60a8d92a3beefe182a9531d29c19152383d"},"schema_version":"1.0"},"canonical_sha256":"ecfc6876ea2ec30a78c64875a52fba073925e5faaa26307adb3c1bc4dc48b7f9","source":{"kind":"arxiv","id":"2409.15157","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15157","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15157v2","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15157","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"5T6GQ5XKF3BQ","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"5T6GQ5XKF3BQU6GG","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"5T6GQ5XK","created_at":"2026-07-05T09:55:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5T6GQ5XKF3BQU6GGJB22KL52A4","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-23T16:04:50Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"dd7d0f5f023de496ab3cfc6beb21c22fcdeb64aa27a11518fd917db383db0233","abstract_canon_sha256":"262c132abd7a8d3ea2c640154ac8d60a8d92a3beefe182a9531d29c19152383d"},"schema_version":"1.0"},"canonical_sha256":"ecfc6876ea2ec30a78c64875a52fba073925e5faaa26307adb3c1bc4dc48b7f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:12.408134Z","signature_b64":"PihIhZVSisiQBULDBaTMsDMK2+VQlRSIXaM5oBdXBH6de0vwhqSHvSdmXk4w8saNb6k4nMXQSrm6GZnllfG/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecfc6876ea2ec30a78c64875a52fba073925e5faaa26307adb3c1bc4dc48b7f9","last_reissued_at":"2026-07-05T09:55:12.407663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:12.407663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15157","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G17b4pzUWMC89Rm0JAayTLPcGU2T0DiNl8NScKeAd+EVVEPKtKgvTuU67WN0JcKSpzCrN5r3jOLA9lMJOB+gAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:23:11.521911Z"},"content_sha256":"62746b92bf55115d479ca536ac9b94ab7e67c3dceb53e54a57d64eca95d90a42","schema_version":"1.0","event_id":"sha256:62746b92bf55115d479ca536ac9b94ab7e67c3dceb53e54a57d64eca95d90a42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5T6GQ5XKF3BQU6GGJB22KL52A4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoVA: Long-form Video-to-Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ruihua Song, Xihua Wang, Xin Cheng, Yihan Wu, Yuyue Wang","submitted_at":"2024-09-23T16:04:50Z","abstract_excerpt":"Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video segment (less than 10 seconds), while giving little attention to the scenario of long-form video inputs. For current UNet-based diffusion V2A models, an inevitable problem when handling long-form audio generation is the inconsistencies within the final concatenated audio. In this paper, we first highlight the importance of long-form V2A problem. Besides, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15157","kind":"arxiv","version":2},"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/2409.15157/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":"2026-07-05T09:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGhiIHxF/o3Cm7iprYWHLip3Ku6j5GO6nQ8swE0dkj8XDJkHRZ68I0Znrh1ZBkHsaIuYUOZTE+zOp2jaGxxYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:23:11.522445Z"},"content_sha256":"783e04240b46fb5e730e8aba4b1c3683b583e4e4b11975322a68c307a1dd0f79","schema_version":"1.0","event_id":"sha256:783e04240b46fb5e730e8aba4b1c3683b583e4e4b11975322a68c307a1dd0f79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/bundle.json","state_url":"https://pith.science/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/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":"2026-08-15T04:23:11Z","links":{"resolver":"https://pith.science/pith/5T6GQ5XKF3BQU6GGJB22KL52A4","bundle":"https://pith.science/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/bundle.json","state":"https://pith.science/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5T6GQ5XKF3BQU6GGJB22KL52A4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5T6GQ5XKF3BQU6GGJB22KL52A4","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":"262c132abd7a8d3ea2c640154ac8d60a8d92a3beefe182a9531d29c19152383d","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-23T16:04:50Z","title_canon_sha256":"dd7d0f5f023de496ab3cfc6beb21c22fcdeb64aa27a11518fd917db383db0233"},"schema_version":"1.0","source":{"id":"2409.15157","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15157","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15157v2","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15157","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"5T6GQ5XKF3BQ","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"5T6GQ5XKF3BQU6GG","created_at":"2026-07-05T09:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"5T6GQ5XK","created_at":"2026-07-05T09:55:12Z"}],"graph_snapshots":[{"event_id":"sha256:783e04240b46fb5e730e8aba4b1c3683b583e4e4b11975322a68c307a1dd0f79","target":"graph","created_at":"2026-07-05T09:55:12Z","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/2409.15157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video segment (less than 10 seconds), while giving little attention to the scenario of long-form video inputs. For current UNet-based diffusion V2A models, an inevitable problem when handling long-form audio generation is the inconsistencies within the final concatenated audio. In this paper, we first highlight the importance of long-form V2A problem. Besides, we propo","authors_text":"Ruihua Song, Xihua Wang, Xin Cheng, Yihan Wu, Yuyue Wang","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-23T16:04:50Z","title":"LoVA: Long-form Video-to-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15157","kind":"arxiv","version":2},"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":"sha256:62746b92bf55115d479ca536ac9b94ab7e67c3dceb53e54a57d64eca95d90a42","target":"record","created_at":"2026-07-05T09:55:12Z","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":"262c132abd7a8d3ea2c640154ac8d60a8d92a3beefe182a9531d29c19152383d","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-23T16:04:50Z","title_canon_sha256":"dd7d0f5f023de496ab3cfc6beb21c22fcdeb64aa27a11518fd917db383db0233"},"schema_version":"1.0","source":{"id":"2409.15157","kind":"arxiv","version":2}},"canonical_sha256":"ecfc6876ea2ec30a78c64875a52fba073925e5faaa26307adb3c1bc4dc48b7f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecfc6876ea2ec30a78c64875a52fba073925e5faaa26307adb3c1bc4dc48b7f9","first_computed_at":"2026-07-05T09:55:12.407663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:12.407663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PihIhZVSisiQBULDBaTMsDMK2+VQlRSIXaM5oBdXBH6de0vwhqSHvSdmXk4w8saNb6k4nMXQSrm6GZnllfG/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:12.408134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15157","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62746b92bf55115d479ca536ac9b94ab7e67c3dceb53e54a57d64eca95d90a42","sha256:783e04240b46fb5e730e8aba4b1c3683b583e4e4b11975322a68c307a1dd0f79"],"state_sha256":"c2123ac8c0acc2649e9e3616dc69c9cde77b7b844716e8b580d1e2012d995413"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDlNxyM97PGSfLMRUObZeGgv2qaferce/y09m3T2PMMP3zm6Ug5qdkoSpNHskywiLBTZctqjJqE9f5rb+k6PAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:23:11.527348Z","bundle_sha256":"4179d26a9883b5951148b27d1f917f693036a03e2d0ddc0cd1ca8e0d0f87561d"}}