{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VGL5Q6ZA42KN2GJGNE3TATLEJX","short_pith_number":"pith:VGL5Q6ZA","schema_version":"1.0","canonical_sha256":"a997d87b20e694dd19266937304d644dfbc2b471af74c58d7f3bd35f4f480063","source":{"kind":"arxiv","id":"2408.02879","version":1},"attestation_state":"computed","paper":{"title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tenglong Ao","submitted_at":"2024-08-06T01:13:09Z","abstract_excerpt":"Interactive virtual humanoid agent is a crucial interface with the physical world. A relatively complete humanoid agent first needs to have face and body, then possess both verbal and non-verbal (such as eye contact, facial expression, lip motion, gesture, and manipulation) abilities, and finally, it is capable of real-time duplex communication, e.g., the ability to actively interrupt conversations. Most prior systems typically only consider a subset of these elements, leaving a gap from realistic humanoid agent. In this work, we propose a real-time, duplex, interactive end-to-end network capa"},"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":"2408.02879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-06T01:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"96dce537a08aa6f964314ede8287865038cac95dd1d0cd8358b8699315956042","abstract_canon_sha256":"13c76db7479a0d3adc3dea278c1705a04dc28d459a0d36cc2651c27a441f3ed0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:41.685986Z","signature_b64":"uFo2HqjWQVAJ5ApdJLuFrkkajkLfNzjRFS1iB2lTfNLvqIK82alUOUyQJIcsETb9n6B/9vv1/BrE5ZHkf86GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a997d87b20e694dd19266937304d644dfbc2b471af74c58d7f3bd35f4f480063","last_reissued_at":"2026-07-05T08:52:41.685544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:41.685544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Body of Her: A Preliminary Study on End-to-End Humanoid Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tenglong Ao","submitted_at":"2024-08-06T01:13:09Z","abstract_excerpt":"Interactive virtual humanoid agent is a crucial interface with the physical world. A relatively complete humanoid agent first needs to have face and body, then possess both verbal and non-verbal (such as eye contact, facial expression, lip motion, gesture, and manipulation) abilities, and finally, it is capable of real-time duplex communication, e.g., the ability to actively interrupt conversations. Most prior systems typically only consider a subset of these elements, leaving a gap from realistic humanoid agent. In this work, we propose a real-time, duplex, interactive end-to-end network capa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02879","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/2408.02879/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":"2408.02879","created_at":"2026-07-05T08:52:41.685602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02879v1","created_at":"2026-07-05T08:52:41.685602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02879","created_at":"2026-07-05T08:52:41.685602+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGL5Q6ZA42KN","created_at":"2026-07-05T08:52:41.685602+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGL5Q6ZA42KN2GJG","created_at":"2026-07-05T08:52:41.685602+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGL5Q6ZA","created_at":"2026-07-05T08:52:41.685602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25041","citing_title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04677","citing_title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX","json":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX.json","graph_json":"https://pith.science/api/pith-number/VGL5Q6ZA42KN2GJGNE3TATLEJX/graph.json","events_json":"https://pith.science/api/pith-number/VGL5Q6ZA42KN2GJGNE3TATLEJX/events.json","paper":"https://pith.science/paper/VGL5Q6ZA"},"agent_actions":{"view_html":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX","download_json":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX.json","view_paper":"https://pith.science/paper/VGL5Q6ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02879&json=true","fetch_graph":"https://pith.science/api/pith-number/VGL5Q6ZA42KN2GJGNE3TATLEJX/graph.json","fetch_events":"https://pith.science/api/pith-number/VGL5Q6ZA42KN2GJGNE3TATLEJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX/action/storage_attestation","attest_author":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX/action/author_attestation","sign_citation":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX/action/citation_signature","submit_replication":"https://pith.science/pith/VGL5Q6ZA42KN2GJGNE3TATLEJX/action/replication_record"}},"created_at":"2026-07-05T08:52:41.685602+00:00","updated_at":"2026-07-05T08:52:41.685602+00:00"}