{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQZNLJSQ6HGLDK6WXZZITXJP4V","short_pith_number":"pith:XQZNLJSQ","schema_version":"1.0","canonical_sha256":"bc32d5a650f1ccb1abd6be7289dd2fe56ab808aa7207755f30a86d2ea5a16fc9","source":{"kind":"arxiv","id":"2412.02419","version":1},"attestation_state":"computed","paper":{"title":"It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dafei Qin, Junichi Yamagishi, Leo Ho, Mingyi Shi, Taku Komura, Yinghao Huang, Zhouyingcheng Liao","submitted_at":"2024-12-03T12:31:44Z","abstract_excerpt":"Conversational scenarios are very common in real-world settings, yet existing co-speech motion synthesis approaches often fall short in these contexts, where one person's audio and gestures will influence the other's responses. Additionally, most existing methods rely on offline sequence-to-sequence frameworks, which are unsuitable for online applications. In this work, we introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation. At the core of our approach is a diffusion-based full-body motion synthesis model, which is"},"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":"2412.02419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-03T12:31:44Z","cross_cats_sorted":["cs.CV","cs.GR","cs.MM","eess.AS"],"title_canon_sha256":"a9b0ac2412883a07fe8bd848a54b6a7f20ac3e4c41ce5591c5f916a0da7ccc32","abstract_canon_sha256":"ceaf30bcaa47730585861311ff89049bb55e7c5c0aadfe92e364dae2776983a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:49.538193Z","signature_b64":"BNgAW6QT+EfmccQw+FrlhmXJiCHlf9OWfVKvdxftNy6iPDBIjIzx4DRTcEGbRV66hZhVzloaIF3L5JJ7uRYAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc32d5a650f1ccb1abd6be7289dd2fe56ab808aa7207755f30a86d2ea5a16fc9","last_reissued_at":"2026-07-05T09:43:49.537736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:49.537736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It Takes Two: Real-time Co-Speech Two-person's Interaction Generation via Reactive Auto-regressive Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dafei Qin, Junichi Yamagishi, Leo Ho, Mingyi Shi, Taku Komura, Yinghao Huang, Zhouyingcheng Liao","submitted_at":"2024-12-03T12:31:44Z","abstract_excerpt":"Conversational scenarios are very common in real-world settings, yet existing co-speech motion synthesis approaches often fall short in these contexts, where one person's audio and gestures will influence the other's responses. Additionally, most existing methods rely on offline sequence-to-sequence frameworks, which are unsuitable for online applications. In this work, we introduce an audio-driven, auto-regressive system designed to synthesize dynamic movements for two characters during a conversation. At the core of our approach is a diffusion-based full-body motion synthesis model, which is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02419","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/2412.02419/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":"2412.02419","created_at":"2026-07-05T09:43:49.537796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02419v1","created_at":"2026-07-05T09:43:49.537796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02419","created_at":"2026-07-05T09:43:49.537796+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQZNLJSQ6HGL","created_at":"2026-07-05T09:43:49.537796+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQZNLJSQ6HGLDK6W","created_at":"2026-07-05T09:43:49.537796+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQZNLJSQ","created_at":"2026-07-05T09:43:49.537796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00173","citing_title":"MotionPersona: Characteristics-aware Locomotion Control","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V","json":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V.json","graph_json":"https://pith.science/api/pith-number/XQZNLJSQ6HGLDK6WXZZITXJP4V/graph.json","events_json":"https://pith.science/api/pith-number/XQZNLJSQ6HGLDK6WXZZITXJP4V/events.json","paper":"https://pith.science/paper/XQZNLJSQ"},"agent_actions":{"view_html":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V","download_json":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V.json","view_paper":"https://pith.science/paper/XQZNLJSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02419&json=true","fetch_graph":"https://pith.science/api/pith-number/XQZNLJSQ6HGLDK6WXZZITXJP4V/graph.json","fetch_events":"https://pith.science/api/pith-number/XQZNLJSQ6HGLDK6WXZZITXJP4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V/action/storage_attestation","attest_author":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V/action/author_attestation","sign_citation":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V/action/citation_signature","submit_replication":"https://pith.science/pith/XQZNLJSQ6HGLDK6WXZZITXJP4V/action/replication_record"}},"created_at":"2026-07-05T09:43:49.537796+00:00","updated_at":"2026-07-05T09:43:49.537796+00:00"}