{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NAVCG2HS7ZQNYIL7ECT5R33YV5","short_pith_number":"pith:NAVCG2HS","schema_version":"1.0","canonical_sha256":"682a2368f2fe60dc217f20a7d8ef78af7c7d1785a98941c111d0295edb7580d0","source":{"kind":"arxiv","id":"2506.23049","version":1},"attestation_state":"computed","paper":{"title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Gayathri Ganesh Lakshmy, Leander Melroy Maben, Shinji Watanabe, Siddhant Arora, Srijith Radhakrishnan","submitted_at":"2025-06-29T01:13:15Z","abstract_excerpt":"Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools such as calendar booking, contact lookup, web search, and email. Its modular design allows easy integ"},"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":"2506.23049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-29T01:13:15Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"f504d3b51e9c9813d93114dbf4b190600baae8da3cb07a4476f29e84ad4887e8","abstract_canon_sha256":"823fcc6e3ae8b94e089d1255e25eafb18adf0bb423bb810c6d8fc7b72d5acd07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:49.731793Z","signature_b64":"31VfWt7B7hUbEOuii6gUpQafoeHYciBI3+2VeLBuXFwk4hmrLbRNf27KQk/IB6bLiNvDoaawbuBFkcZUhlnYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682a2368f2fe60dc217f20a7d8ef78af7c7d1785a98941c111d0295edb7580d0","last_reissued_at":"2026-07-05T11:28:49.731208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:49.731208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Gayathri Ganesh Lakshmy, Leander Melroy Maben, Shinji Watanabe, Siddhant Arora, Srijith Radhakrishnan","submitted_at":"2025-06-29T01:13:15Z","abstract_excerpt":"Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and Automated Tool Use), the first open-source, speech-native assistant capable of completing complex, goal-driven tasks through dynamic tool invocation and multi-turn conversation. AURA combines open-weight ASR, TTS, and LLMs in a cascaded pipeline and supports tools such as calendar booking, contact lookup, web search, and email. Its modular design allows easy integ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23049","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/2506.23049/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":"2506.23049","created_at":"2026-07-05T11:28:49.731268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23049v1","created_at":"2026-07-05T11:28:49.731268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23049","created_at":"2026-07-05T11:28:49.731268+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAVCG2HS7ZQN","created_at":"2026-07-05T11:28:49.731268+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAVCG2HS7ZQNYIL7","created_at":"2026-07-05T11:28:49.731268+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAVCG2HS","created_at":"2026-07-05T11:28:49.731268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15037","citing_title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5","json":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5.json","graph_json":"https://pith.science/api/pith-number/NAVCG2HS7ZQNYIL7ECT5R33YV5/graph.json","events_json":"https://pith.science/api/pith-number/NAVCG2HS7ZQNYIL7ECT5R33YV5/events.json","paper":"https://pith.science/paper/NAVCG2HS"},"agent_actions":{"view_html":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5","download_json":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5.json","view_paper":"https://pith.science/paper/NAVCG2HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23049&json=true","fetch_graph":"https://pith.science/api/pith-number/NAVCG2HS7ZQNYIL7ECT5R33YV5/graph.json","fetch_events":"https://pith.science/api/pith-number/NAVCG2HS7ZQNYIL7ECT5R33YV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5/action/storage_attestation","attest_author":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5/action/author_attestation","sign_citation":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5/action/citation_signature","submit_replication":"https://pith.science/pith/NAVCG2HS7ZQNYIL7ECT5R33YV5/action/replication_record"}},"created_at":"2026-07-05T11:28:49.731268+00:00","updated_at":"2026-07-05T11:28:49.731268+00:00"}