{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PUBU7QBY4IUVCTFTOCIYMRXWZH","short_pith_number":"pith:PUBU7QBY","schema_version":"1.0","canonical_sha256":"7d034fc038e229514cb370918646f6c9d3bdeaafe86d7f1e8bb187b258bb1d2a","source":{"kind":"arxiv","id":"2506.23552","version":2},"attestation_state":"computed","paper":{"title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jaeseok Jung, Jaesik Park, Joonghyuk Shin, Mingi Kwon, Youngjung Uh","submitted_at":"2025-06-30T06:51:40Z","abstract_excerpt":"The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified framework to simultaneously synthesize and condition on both facial motion and speech. Our approach leverages flow matching and a novel Multi-Modal Diffusion Transformer (MM-DiT) architecture, integrating specialized Motion-DiT and Audio-DiT modules. These are coupled via selective joint attention layers and incorporate key architectural choices, such as temporal"},"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":"2506.23552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T06:51:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0a7c081376ed92c3b160c2b898c76b0540614c1ccbafadb458fe49ec1ca2f901","abstract_canon_sha256":"9dcee5a5b73c97229e8a357d34f5e24996f16d4e358e7b8586ac237a2ff1a1e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:21.733966Z","signature_b64":"dGLBFX/CwgHM7qREFaPxDpECKXxZh33sFLmPUqWtEyVFONh5kGtH8oVuANJZHbOm2FNE08rFoEs0YOs/jIlACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d034fc038e229514cb370918646f6c9d3bdeaafe86d7f1e8bb187b258bb1d2a","last_reissued_at":"2026-05-20T00:00:21.733200Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:21.733200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jaeseok Jung, Jaesik Park, Joonghyuk Shin, Mingi Kwon, Youngjung Uh","submitted_at":"2025-06-30T06:51:40Z","abstract_excerpt":"The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified framework to simultaneously synthesize and condition on both facial motion and speech. Our approach leverages flow matching and a novel Multi-Modal Diffusion Transformer (MM-DiT) architecture, integrating specialized Motion-DiT and Audio-DiT modules. These are coupled via selective joint attention layers and incorporate key architectural choices, such as temporal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23552","kind":"arxiv","version":2},"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/2506.23552/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":"2506.23552","created_at":"2026-05-20T00:00:21.733335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23552v2","created_at":"2026-05-20T00:00:21.733335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23552","created_at":"2026-05-20T00:00:21.733335+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUBU7QBY4IUV","created_at":"2026-05-20T00:00:21.733335+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUBU7QBY4IUVCTFT","created_at":"2026-05-20T00:00:21.733335+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUBU7QBY","created_at":"2026-05-20T00:00:21.733335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH","json":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH.json","graph_json":"https://pith.science/api/pith-number/PUBU7QBY4IUVCTFTOCIYMRXWZH/graph.json","events_json":"https://pith.science/api/pith-number/PUBU7QBY4IUVCTFTOCIYMRXWZH/events.json","paper":"https://pith.science/paper/PUBU7QBY"},"agent_actions":{"view_html":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH","download_json":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH.json","view_paper":"https://pith.science/paper/PUBU7QBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23552&json=true","fetch_graph":"https://pith.science/api/pith-number/PUBU7QBY4IUVCTFTOCIYMRXWZH/graph.json","fetch_events":"https://pith.science/api/pith-number/PUBU7QBY4IUVCTFTOCIYMRXWZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH/action/storage_attestation","attest_author":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH/action/author_attestation","sign_citation":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH/action/citation_signature","submit_replication":"https://pith.science/pith/PUBU7QBY4IUVCTFTOCIYMRXWZH/action/replication_record"}},"created_at":"2026-05-20T00:00:21.733335+00:00","updated_at":"2026-05-20T00:00:21.733335+00:00"}