{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XPQ6XSXSAXLS4HYYW5ZN3KW45","short_pith_number":"pith:5XPQ6XSX","schema_version":"1.0","canonical_sha256":"eddf0f5e57902eb970f8c5bb96ed56e753061bad458f0126740746223168f08b","source":{"kind":"arxiv","id":"2407.11333","version":1},"attestation_state":"computed","paper":{"title":"Disentangled Acoustic Fields For Multimodal Physical Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.RO","authors_text":"Andrew Luo, Anoop Cherian, Chuang Gan, Jie Yin, Jonathan Le Roux, Tim K. Marks, Yilun Du","submitted_at":"2024-07-16T02:54:54Z","abstract_excerpt":"We study the problem of multimodal physical scene understanding, where an embodied agent needs to find fallen objects by inferring object properties, direction, and distance of an impact sound source. Previous works adopt feed-forward neural networks to directly regress the variables from sound, leading to poor generalization and domain adaptation issues. In this paper, we illustrate that learning a disentangled model of acoustic formation, referred to as disentangled acoustic field (DAF), to capture the sound generation and propagation process, enables the embodied agent to construct a spatia"},"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":"2407.11333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-16T02:54:54Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"68523fcb0523e0ebb3453e753ec508504732ed1a3a1b99b3a37e575b7054a462","abstract_canon_sha256":"10b95a31be8c373ca099ac9909b700cb547a7123c3e9c20afbcf0346f618fdd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:22.536639Z","signature_b64":"2HtX7AfLQcx5sCSKU6fCTp/GF5sq6ibYq/d1h80bQoyUKvCehrOrqjPpl8Q+lXuVfqjhCcWMdJZDXjA4Zth1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eddf0f5e57902eb970f8c5bb96ed56e753061bad458f0126740746223168f08b","last_reissued_at":"2026-07-05T08:44:22.536145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:22.536145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangled Acoustic Fields For Multimodal Physical Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.RO","authors_text":"Andrew Luo, Anoop Cherian, Chuang Gan, Jie Yin, Jonathan Le Roux, Tim K. Marks, Yilun Du","submitted_at":"2024-07-16T02:54:54Z","abstract_excerpt":"We study the problem of multimodal physical scene understanding, where an embodied agent needs to find fallen objects by inferring object properties, direction, and distance of an impact sound source. Previous works adopt feed-forward neural networks to directly regress the variables from sound, leading to poor generalization and domain adaptation issues. In this paper, we illustrate that learning a disentangled model of acoustic formation, referred to as disentangled acoustic field (DAF), to capture the sound generation and propagation process, enables the embodied agent to construct a spatia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11333","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/2407.11333/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":"2407.11333","created_at":"2026-07-05T08:44:22.536205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11333v1","created_at":"2026-07-05T08:44:22.536205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11333","created_at":"2026-07-05T08:44:22.536205+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XPQ6XSXSAXL","created_at":"2026-07-05T08:44:22.536205+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XPQ6XSXSAXLS4HY","created_at":"2026-07-05T08:44:22.536205+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XPQ6XSX","created_at":"2026-07-05T08:44:22.536205+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/5XPQ6XSXSAXLS4HYYW5ZN3KW45","json":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45.json","graph_json":"https://pith.science/api/pith-number/5XPQ6XSXSAXLS4HYYW5ZN3KW45/graph.json","events_json":"https://pith.science/api/pith-number/5XPQ6XSXSAXLS4HYYW5ZN3KW45/events.json","paper":"https://pith.science/paper/5XPQ6XSX"},"agent_actions":{"view_html":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45","download_json":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45.json","view_paper":"https://pith.science/paper/5XPQ6XSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11333&json=true","fetch_graph":"https://pith.science/api/pith-number/5XPQ6XSXSAXLS4HYYW5ZN3KW45/graph.json","fetch_events":"https://pith.science/api/pith-number/5XPQ6XSXSAXLS4HYYW5ZN3KW45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45/action/storage_attestation","attest_author":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45/action/author_attestation","sign_citation":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45/action/citation_signature","submit_replication":"https://pith.science/pith/5XPQ6XSXSAXLS4HYYW5ZN3KW45/action/replication_record"}},"created_at":"2026-07-05T08:44:22.536205+00:00","updated_at":"2026-07-05T08:44:22.536205+00:00"}