{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EJ76GVNAIB356LHYHYHVQ4GSK6","short_pith_number":"pith:EJ76GVNA","schema_version":"1.0","canonical_sha256":"227fe355a04077df2cf83e0f5870d25786dff1af5c156d7683f968ce4cfa21ea","source":{"kind":"arxiv","id":"2309.16429","version":1},"attestation_state":"computed","paper":{"title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guy Yariv, Idan Schwartz, Itai Gat, Lior Wolf, Sagie Benaim, Yossi Adi","submitted_at":"2023-09-28T13:26:26Z","abstract_excerpt":"We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio: globally, the input audio is semantically associated with the entire output video, and temporally, each segment of the input audio is associated with a corresponding segment of that video. We utilize an existing text-conditioned video generation model and a pre-trained audio encoder model. The proposed method is based on a lightweight adaptor network, which"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.16429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T13:26:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61281256ad3649a4a36985acf8df8b893db55e1dcabca1619220ffdfa4a20198","abstract_canon_sha256":"dfe1d8755bf9ee17272142daff334dd3583bcbc80b72ccb5973a847a99b7b7b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:16.730041Z","signature_b64":"ogXyZoon74V/Cr9hrAT1IUDOFqvfzLs1ufy6rcusoORF65UaE2UPmIlYBD3HPsqUK0kMWV2kK6SJ+4TLwhE0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"227fe355a04077df2cf83e0f5870d25786dff1af5c156d7683f968ce4cfa21ea","last_reissued_at":"2026-07-05T06:55:16.729601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:16.729601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guy Yariv, Idan Schwartz, Itai Gat, Lior Wolf, Sagie Benaim, Yossi Adi","submitted_at":"2023-09-28T13:26:26Z","abstract_excerpt":"We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio: globally, the input audio is semantically associated with the entire output video, and temporally, each segment of the input audio is associated with a corresponding segment of that video. We utilize an existing text-conditioned video generation model and a pre-trained audio encoder model. The proposed method is based on a lightweight adaptor network, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16429","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/2309.16429/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.16429","created_at":"2026-07-05T06:55:16.729651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16429v1","created_at":"2026-07-05T06:55:16.729651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16429","created_at":"2026-07-05T06:55:16.729651+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJ76GVNAIB35","created_at":"2026-07-05T06:55:16.729651+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJ76GVNAIB356LHY","created_at":"2026-07-05T06:55:16.729651+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJ76GVNA","created_at":"2026-07-05T06:55:16.729651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01809","citing_title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6","json":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6.json","graph_json":"https://pith.science/api/pith-number/EJ76GVNAIB356LHYHYHVQ4GSK6/graph.json","events_json":"https://pith.science/api/pith-number/EJ76GVNAIB356LHYHYHVQ4GSK6/events.json","paper":"https://pith.science/paper/EJ76GVNA"},"agent_actions":{"view_html":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6","download_json":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6.json","view_paper":"https://pith.science/paper/EJ76GVNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16429&json=true","fetch_graph":"https://pith.science/api/pith-number/EJ76GVNAIB356LHYHYHVQ4GSK6/graph.json","fetch_events":"https://pith.science/api/pith-number/EJ76GVNAIB356LHYHYHVQ4GSK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6/action/storage_attestation","attest_author":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6/action/author_attestation","sign_citation":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6/action/citation_signature","submit_replication":"https://pith.science/pith/EJ76GVNAIB356LHYHYHVQ4GSK6/action/replication_record"}},"created_at":"2026-07-05T06:55:16.729651+00:00","updated_at":"2026-07-05T06:55:16.729651+00:00"}