{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P67RDH4AIL54ITW74355HIWGXF","short_pith_number":"pith:P67RDH4A","schema_version":"1.0","canonical_sha256":"7fbf119f8042fbc44edfe6fbd3a2c6b94e533b6b42fcfbea9d43c99704385b30","source":{"kind":"arxiv","id":"2507.20987","version":2},"attestation_state":"computed","paper":{"title":"JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kristin Qi, Pengqian Yu, Xinhan Di","submitted_at":"2025-07-28T16:47:44Z","abstract_excerpt":"Recent advances in diffusion-based video generation have enabled photo-realistic short clips, but current methods still struggle to achieve multi-modal consistency when jointly generating whole-body motion and natural speech. Current approaches lack comprehensive evaluation frameworks that assess both visual and audio quality, and there are insufficient benchmarks for region-specific performance analysis. To address these gaps, we introduce the Joint Whole-Body Talking Avatar and Speech Generation Version I(JWB-DH-V1), comprising a large-scale multi-modal dataset with 10,000 unique identities "},"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":"2507.20987","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T16:47:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46d0c59f045cd5a77dec67b2b1930df3f9df69e1bbf3c8b6bd147c5aba7fde71","abstract_canon_sha256":"1602ce9e97947634e0c8ea13099774e501118c5ada6aae9087b522008b4c5c5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:53.945207Z","signature_b64":"goRMMKFTnSKrvNysEez+9zfStNI0qo9F2ppcEvXQrqTMmHnItURqOm2vKRIMugk/KbfPFjgfnAzZprIs6dwEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fbf119f8042fbc44edfe6fbd3a2c6b94e533b6b42fcfbea9d43c99704385b30","last_reissued_at":"2026-07-05T11:44:53.944528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:53.944528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kristin Qi, Pengqian Yu, Xinhan Di","submitted_at":"2025-07-28T16:47:44Z","abstract_excerpt":"Recent advances in diffusion-based video generation have enabled photo-realistic short clips, but current methods still struggle to achieve multi-modal consistency when jointly generating whole-body motion and natural speech. Current approaches lack comprehensive evaluation frameworks that assess both visual and audio quality, and there are insufficient benchmarks for region-specific performance analysis. To address these gaps, we introduce the Joint Whole-Body Talking Avatar and Speech Generation Version I(JWB-DH-V1), comprising a large-scale multi-modal dataset with 10,000 unique identities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20987","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/2507.20987/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":"2507.20987","created_at":"2026-07-05T11:44:53.944611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20987v2","created_at":"2026-07-05T11:44:53.944611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20987","created_at":"2026-07-05T11:44:53.944611+00:00"},{"alias_kind":"pith_short_12","alias_value":"P67RDH4AIL54","created_at":"2026-07-05T11:44:53.944611+00:00"},{"alias_kind":"pith_short_16","alias_value":"P67RDH4AIL54ITW7","created_at":"2026-07-05T11:44:53.944611+00:00"},{"alias_kind":"pith_short_8","alias_value":"P67RDH4A","created_at":"2026-07-05T11:44:53.944611+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/P67RDH4AIL54ITW74355HIWGXF","json":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF.json","graph_json":"https://pith.science/api/pith-number/P67RDH4AIL54ITW74355HIWGXF/graph.json","events_json":"https://pith.science/api/pith-number/P67RDH4AIL54ITW74355HIWGXF/events.json","paper":"https://pith.science/paper/P67RDH4A"},"agent_actions":{"view_html":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF","download_json":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF.json","view_paper":"https://pith.science/paper/P67RDH4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20987&json=true","fetch_graph":"https://pith.science/api/pith-number/P67RDH4AIL54ITW74355HIWGXF/graph.json","fetch_events":"https://pith.science/api/pith-number/P67RDH4AIL54ITW74355HIWGXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF/action/storage_attestation","attest_author":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF/action/author_attestation","sign_citation":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF/action/citation_signature","submit_replication":"https://pith.science/pith/P67RDH4AIL54ITW74355HIWGXF/action/replication_record"}},"created_at":"2026-07-05T11:44:53.944611+00:00","updated_at":"2026-07-05T11:44:53.944611+00:00"}