{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHYNX4CG2CPVQRV4XDFTD7MVEW","short_pith_number":"pith:HHYNX4CG","schema_version":"1.0","canonical_sha256":"39f0dbf046d09f5846bcb8cb31fd9525bb2cc2d5b33806bd76d765b67f6f0c58","source":{"kind":"arxiv","id":"2506.08524","version":2},"attestation_state":"computed","paper":{"title":"Teaching Physical Awareness to LLMs through Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.RO","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andy Nie, Chengchen Hu, Weiguo Wang, Wenrui Zhou, Yi Kai","submitted_at":"2025-06-10T07:42:56Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities in text and multimodal processing, yet they fundamentally lack physical awareness--understanding of real-world physical phenomena. In this work, we present ACORN, a framework that teaches LLMs physical awareness through sound, focusing on fundamental physical phenomena like the Doppler effect, multipath effect, and spatial relationships. To overcome data scarcity, ACORN introduce a physics-based simulator combining real-world sound sources with controlled physical channels to generate diverse training data. Using this simulator, w"},"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":"2506.08524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-10T07:42:56Z","cross_cats_sorted":["cs.AI","cs.MM","cs.RO","eess.AS"],"title_canon_sha256":"529fa4dc1997eedf3a6f2a8b4a94b6c3af2fb0a4ab7ea1d3ef71acbd42f78f69","abstract_canon_sha256":"985b73d811e02e9198998f0cf11a13a4af9d047ff236263ee49d2719ced4bddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:29.701070Z","signature_b64":"kA8MR5r0hmaK+Vq5Do7A7MTbLwFtZduuYHQVg6LcxCBFoqCHXUM1OmIHY2FbX/+AorBnybIa5twIJmKvCywkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f0dbf046d09f5846bcb8cb31fd9525bb2cc2d5b33806bd76d765b67f6f0c58","last_reissued_at":"2026-07-05T11:19:29.700586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:29.700586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching Physical Awareness to LLMs through Sounds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.RO","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andy Nie, Chengchen Hu, Weiguo Wang, Wenrui Zhou, Yi Kai","submitted_at":"2025-06-10T07:42:56Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities in text and multimodal processing, yet they fundamentally lack physical awareness--understanding of real-world physical phenomena. In this work, we present ACORN, a framework that teaches LLMs physical awareness through sound, focusing on fundamental physical phenomena like the Doppler effect, multipath effect, and spatial relationships. To overcome data scarcity, ACORN introduce a physics-based simulator combining real-world sound sources with controlled physical channels to generate diverse training data. Using this simulator, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08524","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/2506.08524/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":"2506.08524","created_at":"2026-07-05T11:19:29.700647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08524v2","created_at":"2026-07-05T11:19:29.700647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08524","created_at":"2026-07-05T11:19:29.700647+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHYNX4CG2CPV","created_at":"2026-07-05T11:19:29.700647+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHYNX4CG2CPVQRV4","created_at":"2026-07-05T11:19:29.700647+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHYNX4CG","created_at":"2026-07-05T11:19:29.700647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW","json":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW.json","graph_json":"https://pith.science/api/pith-number/HHYNX4CG2CPVQRV4XDFTD7MVEW/graph.json","events_json":"https://pith.science/api/pith-number/HHYNX4CG2CPVQRV4XDFTD7MVEW/events.json","paper":"https://pith.science/paper/HHYNX4CG"},"agent_actions":{"view_html":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW","download_json":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW.json","view_paper":"https://pith.science/paper/HHYNX4CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08524&json=true","fetch_graph":"https://pith.science/api/pith-number/HHYNX4CG2CPVQRV4XDFTD7MVEW/graph.json","fetch_events":"https://pith.science/api/pith-number/HHYNX4CG2CPVQRV4XDFTD7MVEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW/action/storage_attestation","attest_author":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW/action/author_attestation","sign_citation":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW/action/citation_signature","submit_replication":"https://pith.science/pith/HHYNX4CG2CPVQRV4XDFTD7MVEW/action/replication_record"}},"created_at":"2026-07-05T11:19:29.700647+00:00","updated_at":"2026-07-05T11:19:29.700647+00:00"}