{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W3KMAIXQS5ANM7O4OF7PNKWDEX","short_pith_number":"pith:W3KMAIXQ","schema_version":"1.0","canonical_sha256":"b6d4c022f09740d67ddc717ef6aac325efb89323a2a246880370186d218856e4","source":{"kind":"arxiv","id":"2502.16794","version":3},"attestation_state":"computed","paper":{"title":"AAD-LLM: Neural Attention-Driven Auditory Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adeen Flinker, Ashesh Mehta, Daniel Friedman, Guy M McKhann, Nima Mesgarani, Stephan Bickel, Sukru Samet Dindar, Vishal Choudhari, Xilin Jiang","submitted_at":"2025-02-24T03:06:45Z","abstract_excerpt":"Auditory foundation models, including auditory large language models (LLMs), process all sound inputs equally, independent of listener perception. However, human auditory perception is inherently selective: listeners focus on specific speakers while ignoring others in complex auditory scenes. Existing models do not incorporate this selectivity, limiting their ability to generate perception-aligned responses. To address this, we introduce Intention-Informed Auditory Scene Understanding (II-ASU) and present Auditory Attention-Driven LLM (AAD-LLM), a prototype system that integrates brain signals"},"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":"2502.16794","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-24T03:06:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","eess.AS"],"title_canon_sha256":"15f2ae0074c2488e66e7bd92fa81a03430b664ece92325906e6ff004359c1c1b","abstract_canon_sha256":"31c6bb10c7e4d6772a301b6a340a8ae9ba8a7de5acef8ab55fd965ca28353555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:24.886125Z","signature_b64":"CmYJ7FJ2w+gIiaNkrEcktlIxWcX117qkwVRi7qQIsbO7buT4MxTCjhRU9VlnseOegZZhvllDFjeuW/G7iOs9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6d4c022f09740d67ddc717ef6aac325efb89323a2a246880370186d218856e4","last_reissued_at":"2026-07-05T11:19:24.885646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:24.885646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AAD-LLM: Neural Attention-Driven Auditory Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adeen Flinker, Ashesh Mehta, Daniel Friedman, Guy M McKhann, Nima Mesgarani, Stephan Bickel, Sukru Samet Dindar, Vishal Choudhari, Xilin Jiang","submitted_at":"2025-02-24T03:06:45Z","abstract_excerpt":"Auditory foundation models, including auditory large language models (LLMs), process all sound inputs equally, independent of listener perception. However, human auditory perception is inherently selective: listeners focus on specific speakers while ignoring others in complex auditory scenes. Existing models do not incorporate this selectivity, limiting their ability to generate perception-aligned responses. To address this, we introduce Intention-Informed Auditory Scene Understanding (II-ASU) and present Auditory Attention-Driven LLM (AAD-LLM), a prototype system that integrates brain signals"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16794","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/2502.16794/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":"2502.16794","created_at":"2026-07-05T11:19:24.885707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16794v3","created_at":"2026-07-05T11:19:24.885707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16794","created_at":"2026-07-05T11:19:24.885707+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3KMAIXQS5AN","created_at":"2026-07-05T11:19:24.885707+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3KMAIXQS5ANM7O4","created_at":"2026-07-05T11:19:24.885707+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3KMAIXQ","created_at":"2026-07-05T11:19:24.885707+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/W3KMAIXQS5ANM7O4OF7PNKWDEX","json":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX.json","graph_json":"https://pith.science/api/pith-number/W3KMAIXQS5ANM7O4OF7PNKWDEX/graph.json","events_json":"https://pith.science/api/pith-number/W3KMAIXQS5ANM7O4OF7PNKWDEX/events.json","paper":"https://pith.science/paper/W3KMAIXQ"},"agent_actions":{"view_html":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX","download_json":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX.json","view_paper":"https://pith.science/paper/W3KMAIXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16794&json=true","fetch_graph":"https://pith.science/api/pith-number/W3KMAIXQS5ANM7O4OF7PNKWDEX/graph.json","fetch_events":"https://pith.science/api/pith-number/W3KMAIXQS5ANM7O4OF7PNKWDEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX/action/storage_attestation","attest_author":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX/action/author_attestation","sign_citation":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX/action/citation_signature","submit_replication":"https://pith.science/pith/W3KMAIXQS5ANM7O4OF7PNKWDEX/action/replication_record"}},"created_at":"2026-07-05T11:19:24.885707+00:00","updated_at":"2026-07-05T11:19:24.885707+00:00"}