{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MS4EWTTBSKKSX4WWMYZVGBSKOZ","short_pith_number":"pith:MS4EWTTB","schema_version":"1.0","canonical_sha256":"64b84b4e6192952bf2d6663353064a7640018fda699fa8be2faa44c479ea2da5","source":{"kind":"arxiv","id":"2606.11033","version":1},"attestation_state":"computed","paper":{"title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Cheng, Jinghua Hao, Jiuchong Gao, Jun Xu, Lei Shi, Renqing He, Yuan Wu, Zhanyu Ma","submitted_at":"2026-06-09T16:05:23Z","abstract_excerpt":"Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respectively reuse strong pretrained components, enable native speech-language interaction, or offer lightweight adaptation, they often suffer from transcript-interface latency, costly multimodal training, or sequential speech-language coupling. To address these limitations, we present AuRA, a method that distills audio encoding capability into the LLM. Specifically, AuRA feeds the sam"},"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":"2606.11033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T16:05:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cbdb497fefb92bdeb6103335108aea6078c3c359dc114e47b3981f04081333cc","abstract_canon_sha256":"9c88b4dc264f4603191c4f4f01fe93cb992c1fc01bd87518f12f49102e90d807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:05.339725Z","signature_b64":"X9eNXTQgqf2FWVJ0m3qjpi8y5aF8iEZuJoGx8VWyyFEpOf/vVdfi+Ht0yeWHxqrqey6+zbF1+mCyqR6usxDmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64b84b4e6192952bf2d6663353064a7640018fda699fa8be2faa44c479ea2da5","last_reissued_at":"2026-06-10T01:11:05.338889Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:05.338889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuRA: Internalizing Audio Understanding into LLMs as LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Cheng, Jinghua Hao, Jiuchong Gao, Jun Xu, Lei Shi, Renqing He, Yuan Wu, Zhanyu Ma","submitted_at":"2026-06-09T16:05:23Z","abstract_excerpt":"Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respectively reuse strong pretrained components, enable native speech-language interaction, or offer lightweight adaptation, they often suffer from transcript-interface latency, costly multimodal training, or sequential speech-language coupling. To address these limitations, we present AuRA, a method that distills audio encoding capability into the LLM. Specifically, AuRA feeds the sam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11033","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/2606.11033/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":"2606.11033","created_at":"2026-06-10T01:11:05.339033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11033v1","created_at":"2026-06-10T01:11:05.339033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11033","created_at":"2026-06-10T01:11:05.339033+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS4EWTTBSKKS","created_at":"2026-06-10T01:11:05.339033+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS4EWTTBSKKSX4WW","created_at":"2026-06-10T01:11:05.339033+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS4EWTTB","created_at":"2026-06-10T01:11:05.339033+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/MS4EWTTBSKKSX4WWMYZVGBSKOZ","json":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ.json","graph_json":"https://pith.science/api/pith-number/MS4EWTTBSKKSX4WWMYZVGBSKOZ/graph.json","events_json":"https://pith.science/api/pith-number/MS4EWTTBSKKSX4WWMYZVGBSKOZ/events.json","paper":"https://pith.science/paper/MS4EWTTB"},"agent_actions":{"view_html":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ","download_json":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ.json","view_paper":"https://pith.science/paper/MS4EWTTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11033&json=true","fetch_graph":"https://pith.science/api/pith-number/MS4EWTTBSKKSX4WWMYZVGBSKOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MS4EWTTBSKKSX4WWMYZVGBSKOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ/action/storage_attestation","attest_author":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ/action/author_attestation","sign_citation":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ/action/citation_signature","submit_replication":"https://pith.science/pith/MS4EWTTBSKKSX4WWMYZVGBSKOZ/action/replication_record"}},"created_at":"2026-06-10T01:11:05.339033+00:00","updated_at":"2026-06-10T01:11:05.339033+00:00"}