{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GHTB5AKAOJSF5A6A23TISQAXGD","short_pith_number":"pith:GHTB5AKA","schema_version":"1.0","canonical_sha256":"31e61e814072645e83c0d6e689401730e8f5ecfea12e0cacb85de854e63871fe","source":{"kind":"arxiv","id":"2608.00463","version":1},"attestation_state":"computed","paper":{"title":"Scene2Sound: Auditory-Grounded Soundscape Generation for 3D Gaussian Worlds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Masaki Yoshida, Miki Haseyama, Ren Togo, Takahiro Ogawa","submitted_at":"2026-08-01T06:04:34Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these worlds remain silent. Because existing audio generation methods condition on a single image or viewpoint, their sound is tied to that observation and cannot stay consistent while a listener moves. We introduce the task of generating a spatially consistent soundscape for a given 3DGS world through auditory grounding, identifying which objects in the world should emit sound and anchoring each to a persistent 3D position, and present Scene2Sound, a tra"},"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":"2608.00463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-01T06:04:34Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"9b69e46b431d45fa48e5f77be9de91fda44c3fbc8b46d456df36c2fba85a2ab1","abstract_canon_sha256":"f8fc33009fec250e95fcddc18038d9995d507c9c2ab7d214d25c874fc43378d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:36:43.984602Z","signature_b64":"RauAXvhUyEa9U1yhwTJNRXSr3YBwksQyliLZ1E/jgin2B+P5A0kmKAnXISUixXN/KkgZwW6bEBEWcamebk/iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e61e814072645e83c0d6e689401730e8f5ecfea12e0cacb85de854e63871fe","last_reissued_at":"2026-08-04T00:36:43.983163Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:36:43.983163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scene2Sound: Auditory-Grounded Soundscape Generation for 3D Gaussian Worlds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Masaki Yoshida, Miki Haseyama, Ren Togo, Takahiro Ogawa","submitted_at":"2026-08-01T06:04:34Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) turns captured or generated imagery into photorealistic 3D world simulations that users can freely explore, yet these worlds remain silent. Because existing audio generation methods condition on a single image or viewpoint, their sound is tied to that observation and cannot stay consistent while a listener moves. We introduce the task of generating a spatially consistent soundscape for a given 3DGS world through auditory grounding, identifying which objects in the world should emit sound and anchoring each to a persistent 3D position, and present Scene2Sound, a tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00463","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/2608.00463/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":"2608.00463","created_at":"2026-08-04T00:36:43.984367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00463v1","created_at":"2026-08-04T00:36:43.984367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00463","created_at":"2026-08-04T00:36:43.984367+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHTB5AKAOJSF","created_at":"2026-08-04T00:36:43.984367+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHTB5AKAOJSF5A6A","created_at":"2026-08-04T00:36:43.984367+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHTB5AKA","created_at":"2026-08-04T00:36:43.984367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD","json":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD.json","graph_json":"https://pith.science/api/pith-number/GHTB5AKAOJSF5A6A23TISQAXGD/graph.json","events_json":"https://pith.science/api/pith-number/GHTB5AKAOJSF5A6A23TISQAXGD/events.json","paper":"https://pith.science/paper/GHTB5AKA"},"agent_actions":{"view_html":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD","download_json":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD.json","view_paper":"https://pith.science/paper/GHTB5AKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00463&json=true","fetch_graph":"https://pith.science/api/pith-number/GHTB5AKAOJSF5A6A23TISQAXGD/graph.json","fetch_events":"https://pith.science/api/pith-number/GHTB5AKAOJSF5A6A23TISQAXGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD/action/storage_attestation","attest_author":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD/action/author_attestation","sign_citation":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD/action/citation_signature","submit_replication":"https://pith.science/pith/GHTB5AKAOJSF5A6A23TISQAXGD/action/replication_record"}},"created_at":"2026-08-04T00:36:43.984367+00:00","updated_at":"2026-08-04T00:36:43.984367+00:00"}