{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FTDZQ4G7T6FEBTOQWOEJU2OIAR","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":"5caad778cd0fa933d0bd102f961d9ce9ba5f374902378e4d0301da459bfb4ec1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T04:48:36Z","title_canon_sha256":"e8b8e1df291feca5c64d817cf64cec9bc11257beb5b90757ad26264e180fbba2"},"schema_version":"1.0","source":{"id":"2406.07867","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07867","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07867v2","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07867","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_12","alias_value":"FTDZQ4G7T6FE","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_16","alias_value":"FTDZQ4G7T6FEBTOQ","created_at":"2026-07-05T08:51:18Z"},{"alias_kind":"pith_short_8","alias_value":"FTDZQ4G7","created_at":"2026-07-05T08:51:18Z"}],"graph_snapshots":[{"event_id":"sha256:b9107858496a165f9945c930cfe72be8937626d3a28369da78a4235f9fdf5612","target":"graph","created_at":"2026-07-05T08:51:18Z","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/2406.07867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation par","authors_text":"Chae Won Kim, Hyeongseop Rha, Jeong Hun Yeo, Joanna Hong, Minsu Kim, Se Jin Park, Yong Man Ro","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T04:48:36Z","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07867","kind":"arxiv","version":2},"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":"sha256:167fcaccc1ad2fbe7b2f1c7b17f6ec1bf772dc0910d5d34b0a168d3e4a98f55f","target":"record","created_at":"2026-07-05T08:51:18Z","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":"5caad778cd0fa933d0bd102f961d9ce9ba5f374902378e4d0301da459bfb4ec1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T04:48:36Z","title_canon_sha256":"e8b8e1df291feca5c64d817cf64cec9bc11257beb5b90757ad26264e180fbba2"},"schema_version":"1.0","source":{"id":"2406.07867","kind":"arxiv","version":2}},"canonical_sha256":"2cc79870df9f8a40cdd0b3889a69c8044a67e30ecca2a9b99e26d78584e0ee95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cc79870df9f8a40cdd0b3889a69c8044a67e30ecca2a9b99e26d78584e0ee95","first_computed_at":"2026-07-05T08:51:18.238506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:18.238506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/bbKGpFU20iKebZ47XRiJia7HqBlhqJhpgL/HKEBEpttgq01G4L6YErcBX5uGXZmIhHD8VGt4Rs++0U3jsLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:18.239005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07867","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:167fcaccc1ad2fbe7b2f1c7b17f6ec1bf772dc0910d5d34b0a168d3e4a98f55f","sha256:b9107858496a165f9945c930cfe72be8937626d3a28369da78a4235f9fdf5612"],"state_sha256":"123dc10c4be972febeb5968b670723ffd76f25e919516e18b99eef00db0bb7f0"}