{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DDCLH5IHQQYDCRWJVBWA3DAREF","short_pith_number":"pith:DDCLH5IH","canonical_record":{"source":{"id":"2412.20378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T06:46:24Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"88e38639de5c64dab9b535c9d8d742cbaf8870b320f7009aa1385c7e72fb6c6a","abstract_canon_sha256":"e880f5a16baa1a2c0d7b509fc9db88d84857594a84f11bd5c04a41006a0adee4"},"schema_version":"1.0"},"canonical_sha256":"18c4b3f50784303146c9a86c0d8c112159c0576a150ec14e2072098d5774e3fd","source":{"kind":"arxiv","id":"2412.20378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20378","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20378v1","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20378","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"DDCLH5IHQQYD","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"DDCLH5IHQQYDCRWJ","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"DDCLH5IH","created_at":"2026-07-05T09:54:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DDCLH5IHQQYDCRWJVBWA3DAREF","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T06:46:24Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"88e38639de5c64dab9b535c9d8d742cbaf8870b320f7009aa1385c7e72fb6c6a","abstract_canon_sha256":"e880f5a16baa1a2c0d7b509fc9db88d84857594a84f11bd5c04a41006a0adee4"},"schema_version":"1.0"},"canonical_sha256":"18c4b3f50784303146c9a86c0d8c112159c0576a150ec14e2072098d5774e3fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:58.407375Z","signature_b64":"Zg/D6foiSIx62KySpzj7qz6foYWQ4/YE2W4HfvJyCGn2FsUGzYZoVePoK36VfARh12zh+bzrmFaKZIaTl6YlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18c4b3f50784303146c9a86c0d8c112159c0576a150ec14e2072098d5774e3fd","last_reissued_at":"2026-07-05T09:54:58.406906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:58.406906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20378","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":"2026-07-05T09:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bstK4n3Copujhh8FijGCmWFJ2all4lddnFvUv0zjBmyh40EHT3UMJFQja6hvcLiMAyz1vPW4Rxrr6N6H5cCbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:57:14.844286Z"},"content_sha256":"c74fb1f013d53e78bf594f11c9276d53f675e03abc496b9753df7662296a3f87","schema_version":"1.0","event_id":"sha256:c74fb1f013d53e78bf594f11c9276d53f675e03abc496b9753df7662296a3f87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DDCLH5IHQQYDCRWJVBWA3DAREF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Bingliang Li, Fengyu Yang, Hongkai Chen, Qingwen Ye, Yiran Zhong, Yuxin Mao","submitted_at":"2024-12-29T06:46:24Z","abstract_excerpt":"Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained control over the generated audio, especially in terms of loudness variation and the incorporation of multi-modal conditions. To overcome these limitations, we introduce Tri-Ergon, a diffusion-based V2A model that incorporates textual, auditory, and pixel-level visual prompts to enable detailed and semantically rich audio synthesis. Additionally, we introduce Loudness Units relative to Full Scale (LUFS) embedding, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20378","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/2412.20378/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":"2026-07-05T09:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICohSjuqbPqohNo/YEvuTKik3L9VdBqhtkJTuwyAu451T032H0XqRpvK0+GD8tvH+oAXEeXS7jaTGB016IcYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:57:14.845050Z"},"content_sha256":"a83027f99691e8489650271625701116cc4a7fa2b9894cc4474ea41dc9da1386","schema_version":"1.0","event_id":"sha256:a83027f99691e8489650271625701116cc4a7fa2b9894cc4474ea41dc9da1386"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/bundle.json","state_url":"https://pith.science/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/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":"2026-08-21T18:57:14Z","links":{"resolver":"https://pith.science/pith/DDCLH5IHQQYDCRWJVBWA3DAREF","bundle":"https://pith.science/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/bundle.json","state":"https://pith.science/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDCLH5IHQQYDCRWJVBWA3DAREF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DDCLH5IHQQYDCRWJVBWA3DAREF","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":"e880f5a16baa1a2c0d7b509fc9db88d84857594a84f11bd5c04a41006a0adee4","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T06:46:24Z","title_canon_sha256":"88e38639de5c64dab9b535c9d8d742cbaf8870b320f7009aa1385c7e72fb6c6a"},"schema_version":"1.0","source":{"id":"2412.20378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20378","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20378v1","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20378","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"DDCLH5IHQQYD","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"DDCLH5IHQQYDCRWJ","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"DDCLH5IH","created_at":"2026-07-05T09:54:58Z"}],"graph_snapshots":[{"event_id":"sha256:a83027f99691e8489650271625701116cc4a7fa2b9894cc4474ea41dc9da1386","target":"graph","created_at":"2026-07-05T09:54:58Z","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/2412.20378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation utilizes visual-only video features to produce realistic sounds that correspond to the scene. However, current V2A models often lack fine-grained control over the generated audio, especially in terms of loudness variation and the incorporation of multi-modal conditions. To overcome these limitations, we introduce Tri-Ergon, a diffusion-based V2A model that incorporates textual, auditory, and pixel-level visual prompts to enable detailed and semantically rich audio synthesis. Additionally, we introduce Loudness Units relative to Full Scale (LUFS) embedding, which","authors_text":"Bingliang Li, Fengyu Yang, Hongkai Chen, Qingwen Ye, Yiran Zhong, Yuxin Mao","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T06:46:24Z","title":"Tri-Ergon: Fine-grained Video-to-Audio Generation with Multi-modal Conditions and LUFS Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20378","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:c74fb1f013d53e78bf594f11c9276d53f675e03abc496b9753df7662296a3f87","target":"record","created_at":"2026-07-05T09:54:58Z","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":"e880f5a16baa1a2c0d7b509fc9db88d84857594a84f11bd5c04a41006a0adee4","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-29T06:46:24Z","title_canon_sha256":"88e38639de5c64dab9b535c9d8d742cbaf8870b320f7009aa1385c7e72fb6c6a"},"schema_version":"1.0","source":{"id":"2412.20378","kind":"arxiv","version":1}},"canonical_sha256":"18c4b3f50784303146c9a86c0d8c112159c0576a150ec14e2072098d5774e3fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c4b3f50784303146c9a86c0d8c112159c0576a150ec14e2072098d5774e3fd","first_computed_at":"2026-07-05T09:54:58.406906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:58.406906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zg/D6foiSIx62KySpzj7qz6foYWQ4/YE2W4HfvJyCGn2FsUGzYZoVePoK36VfARh12zh+bzrmFaKZIaTl6YlCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:58.407375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c74fb1f013d53e78bf594f11c9276d53f675e03abc496b9753df7662296a3f87","sha256:a83027f99691e8489650271625701116cc4a7fa2b9894cc4474ea41dc9da1386"],"state_sha256":"8cc37a29139a61ff6371f8d4c53d6048a5004e7aa1d30c00a60cd0f1f8e8ab3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMWgkOMUzJuI0Hqrt2nKU7VbglRvZxw6zj+NqK+LNyYzhnME5o7QtknY52tQoUatCsVEfCB1aOFe+zBzpIAHAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:57:14.850838Z","bundle_sha256":"fc19f46697e103f92fec28b5b309b12cbafbabb6b3bcf62307d26901fd06f15b"}}