{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4NXKEOGOFKDG76IYOGYA4MJWT2","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":"93b600de12b12e730bcb563c4bac7ba755a708a64f493d6f722179654b128fda","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-26T05:39:52Z","title_canon_sha256":"69419929a328812ce88de9de21c50f01ef2410fbebc09972bd62af4872e166af"},"schema_version":"1.0","source":{"id":"2409.17550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17550","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17550v3","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17550","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"4NXKEOGOFKDG","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"4NXKEOGOFKDG76IY","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"4NXKEOGO","created_at":"2026-07-05T10:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:6ea15258d459aab01d048f732eb27552b7eb9d5f262499ca865e7404c825b8aa","target":"graph","created_at":"2026-07-05T10:46:20Z","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/2409.17550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional mo","authors_text":"Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-26T05:39:52Z","title":"A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17550","kind":"arxiv","version":3},"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:b34ceebc67ad89dbfb767541bb538780affe027b3cf9f804188034d1123778a2","target":"record","created_at":"2026-07-05T10:46:20Z","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":"93b600de12b12e730bcb563c4bac7ba755a708a64f493d6f722179654b128fda","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-26T05:39:52Z","title_canon_sha256":"69419929a328812ce88de9de21c50f01ef2410fbebc09972bd62af4872e166af"},"schema_version":"1.0","source":{"id":"2409.17550","kind":"arxiv","version":3}},"canonical_sha256":"e36ea238ce2a866ff91871b00e31369eb196c57835d9974f86b39cbcf29f38a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e36ea238ce2a866ff91871b00e31369eb196c57835d9974f86b39cbcf29f38a0","first_computed_at":"2026-07-05T10:46:20.379211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:20.379211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y9nw2646DiS2Piv+X0nKO+zyizeWSCo89NFyocpV1dcZHY/2g9Ygpu3DDJ+vaku022njL9KU5sG/0bE+PXgnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:20.379682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34ceebc67ad89dbfb767541bb538780affe027b3cf9f804188034d1123778a2","sha256:6ea15258d459aab01d048f732eb27552b7eb9d5f262499ca865e7404c825b8aa"],"state_sha256":"bac09920d1da7cb8ae47e415101c12723a8a43110f3505a2583a5c212f9063f4"}