{"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"}