{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6MDF2NZI5E6SVRKCCEUFVFNW63","short_pith_number":"pith:6MDF2NZI","schema_version":"1.0","canonical_sha256":"f3065d3728e93d2ac54211285a95b6f6f9b2d71612a475af3f2badc3072c296c","source":{"kind":"arxiv","id":"2309.04509","version":1},"attestation_state":"computed","paper":{"title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dabin Seo, Jinkyu Kim, Sangpil Kim, Seunghyun Lee, Wonjeong Ryoo, Wonmin Byeon, Yujin Jeong","submitted_at":"2023-09-08T12:21:01Z","abstract_excerpt":"In recent years, video generation has become a prominent generative tool and has drawn significant attention. However, there is little consideration in audio-to-video generation, though audio contains unique qualities like temporal semantics and magnitude. Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude. To generate video frames, TPoS utilizes a latent stable diffusion model with textual semantic information, which is then guided by the sequential audio embedding from our pretrained Audio Encoder. As a "},"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":"2309.04509","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-08T12:21:01Z","cross_cats_sorted":["cs.CV","cs.GR","eess.AS"],"title_canon_sha256":"f861eebc992d929fce6cb1b12646ed5aa358955e63f5bbe25efb52be848b5d2b","abstract_canon_sha256":"705805ed31439f756df449f0b78e4a71211cbff06234e6f59d65875d5d4c37d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:04.040132Z","signature_b64":"67dYfveNBCXq8Uo7IqYf6ba4I89ioIscyxhUozWRvtIsLuUB8tWihl9LOm/CA0Ux4pOjakbbaI1bJrmdtP27Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3065d3728e93d2ac54211285a95b6f6f9b2d71612a475af3f2badc3072c296c","last_reissued_at":"2026-07-05T06:49:04.039578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:04.039578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dabin Seo, Jinkyu Kim, Sangpil Kim, Seunghyun Lee, Wonjeong Ryoo, Wonmin Byeon, Yujin Jeong","submitted_at":"2023-09-08T12:21:01Z","abstract_excerpt":"In recent years, video generation has become a prominent generative tool and has drawn significant attention. However, there is little consideration in audio-to-video generation, though audio contains unique qualities like temporal semantics and magnitude. Hence, we propose The Power of Sound (TPoS) model to incorporate audio input that includes both changeable temporal semantics and magnitude. To generate video frames, TPoS utilizes a latent stable diffusion model with textual semantic information, which is then guided by the sequential audio embedding from our pretrained Audio Encoder. As a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04509","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/2309.04509/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":"2309.04509","created_at":"2026-07-05T06:49:04.039636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04509v1","created_at":"2026-07-05T06:49:04.039636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04509","created_at":"2026-07-05T06:49:04.039636+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MDF2NZI5E6S","created_at":"2026-07-05T06:49:04.039636+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MDF2NZI5E6SVRKC","created_at":"2026-07-05T06:49:04.039636+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MDF2NZI","created_at":"2026-07-05T06:49:04.039636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03238","citing_title":"When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63","json":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63.json","graph_json":"https://pith.science/api/pith-number/6MDF2NZI5E6SVRKCCEUFVFNW63/graph.json","events_json":"https://pith.science/api/pith-number/6MDF2NZI5E6SVRKCCEUFVFNW63/events.json","paper":"https://pith.science/paper/6MDF2NZI"},"agent_actions":{"view_html":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63","download_json":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63.json","view_paper":"https://pith.science/paper/6MDF2NZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04509&json=true","fetch_graph":"https://pith.science/api/pith-number/6MDF2NZI5E6SVRKCCEUFVFNW63/graph.json","fetch_events":"https://pith.science/api/pith-number/6MDF2NZI5E6SVRKCCEUFVFNW63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63/action/storage_attestation","attest_author":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63/action/author_attestation","sign_citation":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63/action/citation_signature","submit_replication":"https://pith.science/pith/6MDF2NZI5E6SVRKCCEUFVFNW63/action/replication_record"}},"created_at":"2026-07-05T06:49:04.039636+00:00","updated_at":"2026-07-05T06:49:04.039636+00:00"}