{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QZ2R3MV2TFNNXKKVQ3KWVNOHS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3422bbadba54413932cec5509ad2cfa0e07b0c82bd12e0f28e5bcd519c536040","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-05T15:05:01Z","title_canon_sha256":"0d29a62ce86955e29e0251f05115395a787062eef7314655f800a858977816b4"},"schema_version":"1.0","source":{"id":"2505.02707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02707","created_at":"2026-07-05T10:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02707v1","created_at":"2026-07-05T10:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02707","created_at":"2026-07-05T10:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"5QZ2R3MV2TFN","created_at":"2026-07-05T10:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"5QZ2R3MV2TFNNXKK","created_at":"2026-07-05T10:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"5QZ2R3MV","created_at":"2026-07-05T10:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:3be112e86c6984a0d8fd17e7e2d06510ceecab0138c0142c65881632ec46cb93","target":"graph","created_at":"2026-07-05T10:58:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.02707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangyi Liu, Jaward Sesay, Jingwen Li, Siwei Dong, Yemin Shi, Yu Shu, Zhiting Hu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-05T15:05:01Z","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02707","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:440512880f440ba2d14af52758df75366384aa95b9de554affca2f8b6703f68e","target":"record","created_at":"2026-07-05T10:58:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3422bbadba54413932cec5509ad2cfa0e07b0c82bd12e0f28e5bcd519c536040","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-05T15:05:01Z","title_canon_sha256":"0d29a62ce86955e29e0251f05115395a787062eef7314655f800a858977816b4"},"schema_version":"1.0","source":{"id":"2505.02707","kind":"arxiv","version":1}},"canonical_sha256":"ec33a8ed95d4cad6dd4aac36ab55ae3c8df3f6af2cb926b5cce2417456789aec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec33a8ed95d4cad6dd4aac36ab55ae3c8df3f6af2cb926b5cce2417456789aec","first_computed_at":"2026-07-05T10:58:41.627698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:41.627698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W28W77IL/wVU869y314matEWYKi6pzZYZO6hXHvg2wCuRRyYUmY614MGJJjp5X0sBPUASljCsHvB7RkGgnWJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:41.628187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:440512880f440ba2d14af52758df75366384aa95b9de554affca2f8b6703f68e","sha256:3be112e86c6984a0d8fd17e7e2d06510ceecab0138c0142c65881632ec46cb93"],"state_sha256":"c8d17fda6316be643a85ac3f073bce82b0a4618e12a309b6748863ffb51fb718"}