{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:46AFKBCPA3OAWJBXVUE2DAQYU5","short_pith_number":"pith:46AFKBCP","canonical_record":{"source":{"id":"2412.15191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"45339ab807f2d9a2f8b70f895ad550ee3e59ae520be2486b9b3753f71991ca79","abstract_canon_sha256":"29dd374d00d3ba23b8fd3df1f58a3f39528e4c4a6b6d03998fd8eb95761d18ff"},"schema_version":"1.0"},"canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","source":{"kind":"arxiv","id":"2412.15191","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15191","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15191v2","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15191","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"46AFKBCPA3OA","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"46AFKBCPA3OAWJBX","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"46AFKBCP","created_at":"2026-07-05T10:28:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:46AFKBCPA3OAWJBXVUE2DAQYU5","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"45339ab807f2d9a2f8b70f895ad550ee3e59ae520be2486b9b3753f71991ca79","abstract_canon_sha256":"29dd374d00d3ba23b8fd3df1f58a3f39528e4c4a6b6d03998fd8eb95761d18ff"},"schema_version":"1.0"},"canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:31.288688Z","signature_b64":"QHBXG1RvblfNPfETzgcehrZ5OY6B3JVn7MMHPhLkCXQNBZ2gVs6JfsSH9YjTZZUHsVlolP3h2UalKlQ2QwZeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","last_reissued_at":"2026-07-05T10:28:31.287801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:31.287801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15191","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":"2026-07-05T10:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0WTrkDNBhaN6PJ23utGHbgzEs3uJpjKcq8+oFUJPJ8Cg41nxaWq9D5hWdyipp8vC+kuKG1h1N6uPU+osWBafAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:16:15.030621Z"},"content_sha256":"bbb386001d2716d1c28319aa621c019a51d3b504776cbb637130903d41de4856","schema_version":"1.0","event_id":"sha256:bbb386001d2716d1c28319aa621c019a51d3b504776cbb637130903d41de4856"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:46AFKBCPA3OAWJBXVUE2DAQYU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Alper Canberk, Ivan Skorokhodov, Kwot Sin Lee, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","submitted_at":"2024-12-19T18:57:21Z","abstract_excerpt":"We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15191","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/2412.15191/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":"2026-07-05T10:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k50o93faSi753AwJaHwqlr4XBDnYF2iU5DOYLs4leVs3aG02xxPX+zBKzYPYo5wywqE048iBS44ocwOG8QaXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:16:15.031004Z"},"content_sha256":"740f8d76a694831f556a74d2ff59694dca7e8f92b4ce9ff4f2515d78b9237387","schema_version":"1.0","event_id":"sha256:740f8d76a694831f556a74d2ff59694dca7e8f92b4ce9ff4f2515d78b9237387"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/bundle.json","state_url":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/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":"2026-08-04T02:16:15Z","links":{"resolver":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5","bundle":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/bundle.json","state":"https://pith.science/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46AFKBCPA3OAWJBXVUE2DAQYU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:46AFKBCPA3OAWJBXVUE2DAQYU5","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":"29dd374d00d3ba23b8fd3df1f58a3f39528e4c4a6b6d03998fd8eb95761d18ff","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","title_canon_sha256":"45339ab807f2d9a2f8b70f895ad550ee3e59ae520be2486b9b3753f71991ca79"},"schema_version":"1.0","source":{"id":"2412.15191","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15191","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15191v2","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15191","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"46AFKBCPA3OA","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"46AFKBCPA3OAWJBX","created_at":"2026-07-05T10:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"46AFKBCP","created_at":"2026-07-05T10:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:740f8d76a694831f556a74d2ff59694dca7e8f92b4ce9ff4f2515d78b9237387","target":"graph","created_at":"2026-07-05T10:28:31Z","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/2412.15191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly","authors_text":"Aliaksandr Siarohin, Alper Canberk, Ivan Skorokhodov, Kwot Sin Lee, Moayed Haji-Ali, Sergey Tulyakov, Vicente Ordonez, Willi Menapace","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15191","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:bbb386001d2716d1c28319aa621c019a51d3b504776cbb637130903d41de4856","target":"record","created_at":"2026-07-05T10:28:31Z","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":"29dd374d00d3ba23b8fd3df1f58a3f39528e4c4a6b6d03998fd8eb95761d18ff","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T18:57:21Z","title_canon_sha256":"45339ab807f2d9a2f8b70f895ad550ee3e59ae520be2486b9b3753f71991ca79"},"schema_version":"1.0","source":{"id":"2412.15191","kind":"arxiv","version":2}},"canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e78055044f06dc0b2437ad09a18218a75772f2270f3ff96839087bb104ba4b7d","first_computed_at":"2026-07-05T10:28:31.287801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:31.287801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHBXG1RvblfNPfETzgcehrZ5OY6B3JVn7MMHPhLkCXQNBZ2gVs6JfsSH9YjTZZUHsVlolP3h2UalKlQ2QwZeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:31.288688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15191","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbb386001d2716d1c28319aa621c019a51d3b504776cbb637130903d41de4856","sha256:740f8d76a694831f556a74d2ff59694dca7e8f92b4ce9ff4f2515d78b9237387"],"state_sha256":"6c484714f3c8bf093a42c90f5417fa23c67300ca32925faf5433887d9b7219f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXAInJSTvQt2SQBLcf8pUsfyTcYkBTRpo8wrpAI5AfU41UPwF7+gi5a+1KGVSjvqNCb7EVaaQqrXeFnLwqfpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:16:15.033781Z","bundle_sha256":"0b191d2bddf478c0b755ad48dc76c0b8027c6a44a4c1751eefd7706f447fa3f7"}}