{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UEN7XH6QJQAHDTPLII3YAXC6SI","short_pith_number":"pith:UEN7XH6Q","schema_version":"1.0","canonical_sha256":"a11bfb9fd04c0071cdeb4237805c5e9209e417e909e25b834e3aac0b22abad6a","source":{"kind":"arxiv","id":"2608.05145","version":1},"attestation_state":"computed","paper":{"title":"Objects as Audio-Visual Modal Sound Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derong Jin, Ruohan Gao, Zihao Wei, Zisen Shao","submitted_at":"2026-08-05T17:59:19Z","abstract_excerpt":"While modern 3D reconstruction excels at modeling object geometry and appearance, it largely ignores the rich acoustic cues revealed through physical interaction. Object impact sounds convey material, stiffness, and structural properties that complement vision, yet existing impact sound modeling approaches either rely on expensive physics-based simulation or require large datasets to generalize in a purely data-driven manner. We introduce Audio-Visual Modal Sound Field (AV-MSF), a novel object-level acoustic representation reconstructed from multi-view images and only a few impact sound record"},"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":"2608.05145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T17:59:19Z","cross_cats_sorted":[],"title_canon_sha256":"44ab65c055c3f9c7be687fd4d5c6c08b7944dd07679073dc6905d2d82ee2cecc","abstract_canon_sha256":"0e99ed98ade53cacbd56234ea5c7479379699d731b044e5bffd302a4dc508cde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:49:17.662957Z","signature_b64":"Q/X1nSn1c2Sd6OWZ6nNWbVPIGR6Prs+iwzFqkuFB33hTb9cPoEC9P0mcxd+w52XHDiDsUje52RHwOA01GbhUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a11bfb9fd04c0071cdeb4237805c5e9209e417e909e25b834e3aac0b22abad6a","last_reissued_at":"2026-08-06T01:49:17.661184Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:49:17.661184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Objects as Audio-Visual Modal Sound Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derong Jin, Ruohan Gao, Zihao Wei, Zisen Shao","submitted_at":"2026-08-05T17:59:19Z","abstract_excerpt":"While modern 3D reconstruction excels at modeling object geometry and appearance, it largely ignores the rich acoustic cues revealed through physical interaction. Object impact sounds convey material, stiffness, and structural properties that complement vision, yet existing impact sound modeling approaches either rely on expensive physics-based simulation or require large datasets to generalize in a purely data-driven manner. We introduce Audio-Visual Modal Sound Field (AV-MSF), a novel object-level acoustic representation reconstructed from multi-view images and only a few impact sound record"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05145","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/2608.05145/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":"2608.05145","created_at":"2026-08-06T01:49:17.663321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05145v1","created_at":"2026-08-06T01:49:17.663321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05145","created_at":"2026-08-06T01:49:17.663321+00:00"},{"alias_kind":"pith_short_12","alias_value":"UEN7XH6QJQAH","created_at":"2026-08-06T01:49:17.663321+00:00"},{"alias_kind":"pith_short_16","alias_value":"UEN7XH6QJQAHDTPL","created_at":"2026-08-06T01:49:17.663321+00:00"},{"alias_kind":"pith_short_8","alias_value":"UEN7XH6Q","created_at":"2026-08-06T01:49:17.663321+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/UEN7XH6QJQAHDTPLII3YAXC6SI","json":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI.json","graph_json":"https://pith.science/api/pith-number/UEN7XH6QJQAHDTPLII3YAXC6SI/graph.json","events_json":"https://pith.science/api/pith-number/UEN7XH6QJQAHDTPLII3YAXC6SI/events.json","paper":"https://pith.science/paper/UEN7XH6Q"},"agent_actions":{"view_html":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI","download_json":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI.json","view_paper":"https://pith.science/paper/UEN7XH6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05145&json=true","fetch_graph":"https://pith.science/api/pith-number/UEN7XH6QJQAHDTPLII3YAXC6SI/graph.json","fetch_events":"https://pith.science/api/pith-number/UEN7XH6QJQAHDTPLII3YAXC6SI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI/action/storage_attestation","attest_author":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI/action/author_attestation","sign_citation":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI/action/citation_signature","submit_replication":"https://pith.science/pith/UEN7XH6QJQAHDTPLII3YAXC6SI/action/replication_record"}},"created_at":"2026-08-06T01:49:17.663321+00:00","updated_at":"2026-08-06T01:49:17.663321+00:00"}