{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GVSWYOECY7OGNBAGRD6DV7WR5O","short_pith_number":"pith:GVSWYOEC","schema_version":"1.0","canonical_sha256":"35656c3882c7dc66840688fc3afed1ebbfbdcee8ee6dc6eaff9b564a2820a2a3","source":{"kind":"arxiv","id":"2410.14945","version":2},"attestation_state":"computed","paper":{"title":"ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bruno Conejo, Joshua Atkins, Mehrez Souden, Mojtaba Heydari","submitted_at":"2024-10-19T02:28:53Z","abstract_excerpt":"We introduce ImmerseDiffusion, an end-to-end generative audio model that produces 3D immersive soundscapes conditioned on the spatial, temporal, and environmental conditions of sound objects. ImmerseDiffusion is trained to generate first-order ambisonics (FOA) audio, which is a conventional spatial audio format comprising four channels that can be rendered to multichannel spatial output. The proposed generative system is composed of a spatial audio codec that maps FOA audio to latent components, a latent diffusion model trained based on various user input types, namely, text prompts, spatial, "},"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":"2410.14945","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-19T02:28:53Z","cross_cats_sorted":["cs.ET","cs.LG","eess.AS"],"title_canon_sha256":"ddaad0576b456b19aa6f705eb5df266a680369efc5e81aa01161d04fe940e039","abstract_canon_sha256":"43c6b1115e67735386db8a8e0fc415e7c836e6e20e675618faf84c606cbec2e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:26.677177Z","signature_b64":"o0+48RkKNsOTa+qqTwQlKY/lta+OIa8qPIDW3ukULXMumpiVKLFK+CFc6niIUj8mle8WtbiZq103FFtEC4Y9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35656c3882c7dc66840688fc3afed1ebbfbdcee8ee6dc6eaff9b564a2820a2a3","last_reissued_at":"2026-07-05T10:11:26.676670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:26.676670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImmerseDiffusion: A Generative Spatial Audio Latent Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bruno Conejo, Joshua Atkins, Mehrez Souden, Mojtaba Heydari","submitted_at":"2024-10-19T02:28:53Z","abstract_excerpt":"We introduce ImmerseDiffusion, an end-to-end generative audio model that produces 3D immersive soundscapes conditioned on the spatial, temporal, and environmental conditions of sound objects. ImmerseDiffusion is trained to generate first-order ambisonics (FOA) audio, which is a conventional spatial audio format comprising four channels that can be rendered to multichannel spatial output. The proposed generative system is composed of a spatial audio codec that maps FOA audio to latent components, a latent diffusion model trained based on various user input types, namely, text prompts, spatial, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14945","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/2410.14945/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":"2410.14945","created_at":"2026-07-05T10:11:26.676731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14945v2","created_at":"2026-07-05T10:11:26.676731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14945","created_at":"2026-07-05T10:11:26.676731+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVSWYOECY7OG","created_at":"2026-07-05T10:11:26.676731+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVSWYOECY7OGNBAG","created_at":"2026-07-05T10:11:26.676731+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVSWYOEC","created_at":"2026-07-05T10:11:26.676731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12918","citing_title":"FoleySpace: Vision-Aligned Binaural Spatial Audio Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O","json":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O.json","graph_json":"https://pith.science/api/pith-number/GVSWYOECY7OGNBAGRD6DV7WR5O/graph.json","events_json":"https://pith.science/api/pith-number/GVSWYOECY7OGNBAGRD6DV7WR5O/events.json","paper":"https://pith.science/paper/GVSWYOEC"},"agent_actions":{"view_html":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O","download_json":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O.json","view_paper":"https://pith.science/paper/GVSWYOEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14945&json=true","fetch_graph":"https://pith.science/api/pith-number/GVSWYOECY7OGNBAGRD6DV7WR5O/graph.json","fetch_events":"https://pith.science/api/pith-number/GVSWYOECY7OGNBAGRD6DV7WR5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O/action/storage_attestation","attest_author":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O/action/author_attestation","sign_citation":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O/action/citation_signature","submit_replication":"https://pith.science/pith/GVSWYOECY7OGNBAGRD6DV7WR5O/action/replication_record"}},"created_at":"2026-07-05T10:11:26.676731+00:00","updated_at":"2026-07-05T10:11:26.676731+00:00"}