{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5QZ2R3MV2TFNNXKKVQ3KWVNOHS","short_pith_number":"pith:5QZ2R3MV","schema_version":"1.0","canonical_sha256":"ec33a8ed95d4cad6dd4aac36ab55ae3c8df3f6af2cb926b5cce2417456789aec","source":{"kind":"arxiv","id":"2505.02707","version":1},"attestation_state":"computed","paper":{"title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.AI","authors_text":"Guangyi Liu, Jaward Sesay, Jingwen Li, Siwei Dong, Yemin Shi, Yu Shu, Zhiting Hu","submitted_at":"2025-05-05T15:05:01Z","abstract_excerpt":"A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuanc"},"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":"2505.02707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-05T15:05:01Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"0d29a62ce86955e29e0251f05115395a787062eef7314655f800a858977816b4","abstract_canon_sha256":"3422bbadba54413932cec5509ad2cfa0e07b0c82bd12e0f28e5bcd519c536040"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:41.628187Z","signature_b64":"W28W77IL/wVU869y314matEWYKi6pzZYZO6hXHvg2wCuRRyYUmY614MGJJjp5X0sBPUASljCsHvB7RkGgnWJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec33a8ed95d4cad6dd4aac36ab55ae3c8df3f6af2cb926b5cce2417456789aec","last_reissued_at":"2026-07-05T10:58:41.627698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:41.627698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"cs.AI","authors_text":"Guangyi Liu, Jaward Sesay, Jingwen Li, Siwei Dong, Yemin Shi, Yu Shu, Zhiting Hu","submitted_at":"2025-05-05T15:05:01Z","abstract_excerpt":"A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond proactively, fostering fluid, dynamic, and emotionally resonant interactions. We introduce Voila, a family of large voice-language foundation models that make a step towards this vision. Voila moves beyond traditional pipeline systems by adopting a new end-to-end architecture that enables full-duplex, low-latency conversations while preserving rich vocal nuanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02707","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/2505.02707/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":"2505.02707","created_at":"2026-07-05T10:58:41.627759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02707v1","created_at":"2026-07-05T10:58:41.627759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02707","created_at":"2026-07-05T10:58:41.627759+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QZ2R3MV2TFN","created_at":"2026-07-05T10:58:41.627759+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QZ2R3MV2TFNNXKK","created_at":"2026-07-05T10:58:41.627759+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QZ2R3MV","created_at":"2026-07-05T10:58:41.627759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30553","citing_title":"COSM: A Cooperative Scheduling Framework for Concurrent PIM and CPU Execution on Mobile Devices","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30553","citing_title":"COSM: A Cooperative Scheduling Framework for Concurrent PIM and CPU Execution on Mobile Devices","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11167","citing_title":"Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08847","citing_title":"EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS","json":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS.json","graph_json":"https://pith.science/api/pith-number/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/graph.json","events_json":"https://pith.science/api/pith-number/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/events.json","paper":"https://pith.science/paper/5QZ2R3MV"},"agent_actions":{"view_html":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS","download_json":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS.json","view_paper":"https://pith.science/paper/5QZ2R3MV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02707&json=true","fetch_graph":"https://pith.science/api/pith-number/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/graph.json","fetch_events":"https://pith.science/api/pith-number/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/action/storage_attestation","attest_author":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/action/author_attestation","sign_citation":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/action/citation_signature","submit_replication":"https://pith.science/pith/5QZ2R3MV2TFNNXKKVQ3KWVNOHS/action/replication_record"}},"created_at":"2026-07-05T10:58:41.627759+00:00","updated_at":"2026-07-05T10:58:41.627759+00:00"}