{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PM5BTJR36W5L5CS2H7UWNVGLRZ","short_pith_number":"pith:PM5BTJR3","schema_version":"1.0","canonical_sha256":"7b3a19a63bf5babe8a5a3fe966d4cb8e657f4fe06fa1ea55bb19aea3ace6eaa5","source":{"kind":"arxiv","id":"2508.02944","version":1},"attestation_state":"computed","paper":{"title":"X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liang, Chenxu Zhang, Guoxian Song, Hongyi Xu, Jianwen Jiang, Linjie Luo, Tianpei Gu, Xiaochen Zhao, Xin Chen, You Xie, Zenan Li","submitted_at":"2025-08-04T22:57:01Z","abstract_excerpt":"We present X-Actor, a novel audio-driven portrait animation framework that generates lifelike, emotionally expressive talking head videos from a single reference image and an input audio clip. Unlike prior methods that emphasize lip synchronization and short-range visual fidelity in constrained speaking scenarios, X-Actor enables actor-quality, long-form portrait performance capturing nuanced, dynamically evolving emotions that flow coherently with the rhythm and content of speech. Central to our approach is a two-stage decoupled generation pipeline: an audio-conditioned autoregressive diffusi"},"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":"2508.02944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-04T22:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"49a9b1a5fbece3bd82dc928d72caffb14f6de4277e12ebc30e38d3a71ab622c9","abstract_canon_sha256":"0890d9cbbe0dae2afe8b0373f42b10b24e54cf202542de1eec0a572c006ac992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:33.334436Z","signature_b64":"Pj6cVqSfKUtbNVHYPdzwT1aZNKyyPOjrjQfHCRmc6BhXxZ1T1/8nmw+0IUze/xR4Il5HqUvHY0npyFeUJ9HFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3a19a63bf5babe8a5a3fe966d4cb8e657f4fe06fa1ea55bb19aea3ace6eaa5","last_reissued_at":"2026-07-05T11:48:33.333849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:33.333849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liang, Chenxu Zhang, Guoxian Song, Hongyi Xu, Jianwen Jiang, Linjie Luo, Tianpei Gu, Xiaochen Zhao, Xin Chen, You Xie, Zenan Li","submitted_at":"2025-08-04T22:57:01Z","abstract_excerpt":"We present X-Actor, a novel audio-driven portrait animation framework that generates lifelike, emotionally expressive talking head videos from a single reference image and an input audio clip. Unlike prior methods that emphasize lip synchronization and short-range visual fidelity in constrained speaking scenarios, X-Actor enables actor-quality, long-form portrait performance capturing nuanced, dynamically evolving emotions that flow coherently with the rhythm and content of speech. Central to our approach is a two-stage decoupled generation pipeline: an audio-conditioned autoregressive diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02944","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/2508.02944/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":"2508.02944","created_at":"2026-07-05T11:48:33.333923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02944v1","created_at":"2026-07-05T11:48:33.333923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02944","created_at":"2026-07-05T11:48:33.333923+00:00"},{"alias_kind":"pith_short_12","alias_value":"PM5BTJR36W5L","created_at":"2026-07-05T11:48:33.333923+00:00"},{"alias_kind":"pith_short_16","alias_value":"PM5BTJR36W5L5CS2","created_at":"2026-07-05T11:48:33.333923+00:00"},{"alias_kind":"pith_short_8","alias_value":"PM5BTJR3","created_at":"2026-07-05T11:48:33.333923+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/PM5BTJR36W5L5CS2H7UWNVGLRZ","json":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ.json","graph_json":"https://pith.science/api/pith-number/PM5BTJR36W5L5CS2H7UWNVGLRZ/graph.json","events_json":"https://pith.science/api/pith-number/PM5BTJR36W5L5CS2H7UWNVGLRZ/events.json","paper":"https://pith.science/paper/PM5BTJR3"},"agent_actions":{"view_html":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ","download_json":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ.json","view_paper":"https://pith.science/paper/PM5BTJR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02944&json=true","fetch_graph":"https://pith.science/api/pith-number/PM5BTJR36W5L5CS2H7UWNVGLRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PM5BTJR36W5L5CS2H7UWNVGLRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ/action/storage_attestation","attest_author":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ/action/author_attestation","sign_citation":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ/action/citation_signature","submit_replication":"https://pith.science/pith/PM5BTJR36W5L5CS2H7UWNVGLRZ/action/replication_record"}},"created_at":"2026-07-05T11:48:33.333923+00:00","updated_at":"2026-07-05T11:48:33.333923+00:00"}