{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JEM5VQAIEO5EBRTTCGK5XSI2B5","short_pith_number":"pith:JEM5VQAI","schema_version":"1.0","canonical_sha256":"4919dac00823ba40c6731195dbc91a0f5749dd85b22e2f57f86614c8404df3d2","source":{"kind":"arxiv","id":"2406.08920","version":3},"attestation_state":"computed","paper":{"title":"AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Diptesh Kanojia, Haosen Yang, Jiankang Deng, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2024-06-13T08:34:12Z","abstract_excerpt":"Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing binaural audio. However, in addition to low efficiency originating from heavy NeRF rendering, these methods all have a limited ability of characterizing the entire scene environment such as room geometry, material properties, and the spatial relation between the listener and sound source. To address these issues, we propose a novel 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":"2406.08920","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-13T08:34:12Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"85191464ef032a3e3d69f1e2940f9299f2685d1f97c1b3d34f3212a8e797506e","abstract_canon_sha256":"4cbd7abd17259d6351f3a3e92fbf1cac4b65eccfc6413c0f43a446e19350681d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:44.273567Z","signature_b64":"sIaMClsGAnXE3BRYdqoBTiz8CYhY7bmMXq2Ouu9KcJcgeV6MaePa147dpmUEvpMGH1BUQk1HvhVCbnUHYZm3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4919dac00823ba40c6731195dbc91a0f5749dd85b22e2f57f86614c8404df3d2","last_reissued_at":"2026-07-05T10:31:44.272812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:44.272812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Diptesh Kanojia, Haosen Yang, Jiankang Deng, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2024-06-13T08:34:12Z","abstract_excerpt":"Novel view acoustic synthesis (NVAS) aims to render binaural audio at any target viewpoint, given a mono audio emitted by a sound source at a 3D scene. Existing methods have proposed NeRF-based implicit models to exploit visual cues as a condition for synthesizing binaural audio. However, in addition to low efficiency originating from heavy NeRF rendering, these methods all have a limited ability of characterizing the entire scene environment such as room geometry, material properties, and the spatial relation between the listener and sound source. To address these issues, we propose a novel A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08920","kind":"arxiv","version":3},"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/2406.08920/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":"2406.08920","created_at":"2026-07-05T10:31:44.272909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08920v3","created_at":"2026-07-05T10:31:44.272909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08920","created_at":"2026-07-05T10:31:44.272909+00:00"},{"alias_kind":"pith_short_12","alias_value":"JEM5VQAIEO5E","created_at":"2026-07-05T10:31:44.272909+00:00"},{"alias_kind":"pith_short_16","alias_value":"JEM5VQAIEO5EBRTT","created_at":"2026-07-05T10:31:44.272909+00:00"},{"alias_kind":"pith_short_8","alias_value":"JEM5VQAI","created_at":"2026-07-05T10:31:44.272909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.15946","citing_title":"Differentiable Acoustic Radiance Transfer","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09473","citing_title":"Realizing Immersive Volumetric Video: A Multimodal Framework for 6-DoF VR Engagement","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5","json":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5.json","graph_json":"https://pith.science/api/pith-number/JEM5VQAIEO5EBRTTCGK5XSI2B5/graph.json","events_json":"https://pith.science/api/pith-number/JEM5VQAIEO5EBRTTCGK5XSI2B5/events.json","paper":"https://pith.science/paper/JEM5VQAI"},"agent_actions":{"view_html":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5","download_json":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5.json","view_paper":"https://pith.science/paper/JEM5VQAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08920&json=true","fetch_graph":"https://pith.science/api/pith-number/JEM5VQAIEO5EBRTTCGK5XSI2B5/graph.json","fetch_events":"https://pith.science/api/pith-number/JEM5VQAIEO5EBRTTCGK5XSI2B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5/action/storage_attestation","attest_author":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5/action/author_attestation","sign_citation":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5/action/citation_signature","submit_replication":"https://pith.science/pith/JEM5VQAIEO5EBRTTCGK5XSI2B5/action/replication_record"}},"created_at":"2026-07-05T10:31:44.272909+00:00","updated_at":"2026-07-05T10:31:44.272909+00:00"}