{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3SUFYTLHJ4RAZXUB72JJYMPRG","short_pith_number":"pith:P3SUFYTL","schema_version":"1.0","canonical_sha256":"7ee542e26b3a791066f40ff494e18f89a43acb9b4346dcc7b6599ef29d201860","source":{"kind":"arxiv","id":"2608.01978","version":1},"attestation_state":"computed","paper":{"title":"Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haijie Yang, Hao Tang, Hongliang Zhang, Jian Bi, Jianjun Qian, Jian Yang, Jindi Bao, Yixuan Dong, Zhenyu Zhang","submitted_at":"2026-08-03T09:41:59Z","abstract_excerpt":"Audio-driven portrait animation has advanced rapidly with diffusion-based generative models, yet real-time one-shot generation with expressive emotion control remains challenging. Existing methods often suffer from insufficient emotion-aware motion priors and expensive appearance computation during multi-step denoising. To address these issues, we propose Proxy Avatar Meets Low-Rank Caching, a cascaded framework for real-time one-shot emotion-controllable portrait animation. Instead of directly generating the target portrait from audio, our method uses a Gaussian-based emotion proxy avatar as "},"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":"2608.01978","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T09:41:59Z","cross_cats_sorted":[],"title_canon_sha256":"f96b6db61fdbc3070c849aa3da22a40096f59bb7301a5cca69df07345f9e6fff","abstract_canon_sha256":"4b524bf1635197c1145d31c2f46b5382346aa163e350c510512c75957b7b43bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:25.789064Z","signature_b64":"ErIB9L9Dux12WPhJ2+oSuzDla2j45M9hKJKhJHq9eR3fKSXtCkACm4L/phrLyD/Tk3KKyci9YOkl7RgMEzZiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ee542e26b3a791066f40ff494e18f89a43acb9b4346dcc7b6599ef29d201860","last_reissued_at":"2026-08-04T02:10:25.787445Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:25.787445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haijie Yang, Hao Tang, Hongliang Zhang, Jian Bi, Jianjun Qian, Jian Yang, Jindi Bao, Yixuan Dong, Zhenyu Zhang","submitted_at":"2026-08-03T09:41:59Z","abstract_excerpt":"Audio-driven portrait animation has advanced rapidly with diffusion-based generative models, yet real-time one-shot generation with expressive emotion control remains challenging. Existing methods often suffer from insufficient emotion-aware motion priors and expensive appearance computation during multi-step denoising. To address these issues, we propose Proxy Avatar Meets Low-Rank Caching, a cascaded framework for real-time one-shot emotion-controllable portrait animation. Instead of directly generating the target portrait from audio, our method uses a Gaussian-based emotion proxy avatar as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01978","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/2608.01978/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":"2608.01978","created_at":"2026-08-04T02:10:25.789056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01978v1","created_at":"2026-08-04T02:10:25.789056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01978","created_at":"2026-08-04T02:10:25.789056+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3SUFYTLHJ4R","created_at":"2026-08-04T02:10:25.789056+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3SUFYTLHJ4RAZXU","created_at":"2026-08-04T02:10:25.789056+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3SUFYTL","created_at":"2026-08-04T02:10:25.789056+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/P3SUFYTLHJ4RAZXUB72JJYMPRG","json":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG.json","graph_json":"https://pith.science/api/pith-number/P3SUFYTLHJ4RAZXUB72JJYMPRG/graph.json","events_json":"https://pith.science/api/pith-number/P3SUFYTLHJ4RAZXUB72JJYMPRG/events.json","paper":"https://pith.science/paper/P3SUFYTL"},"agent_actions":{"view_html":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG","download_json":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG.json","view_paper":"https://pith.science/paper/P3SUFYTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01978&json=true","fetch_graph":"https://pith.science/api/pith-number/P3SUFYTLHJ4RAZXUB72JJYMPRG/graph.json","fetch_events":"https://pith.science/api/pith-number/P3SUFYTLHJ4RAZXUB72JJYMPRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG/action/storage_attestation","attest_author":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG/action/author_attestation","sign_citation":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG/action/citation_signature","submit_replication":"https://pith.science/pith/P3SUFYTLHJ4RAZXUB72JJYMPRG/action/replication_record"}},"created_at":"2026-08-04T02:10:25.789056+00:00","updated_at":"2026-08-04T02:10:25.789056+00:00"}