{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EKMP7IXHG5EWMR25PBGMS6YU3Y","short_pith_number":"pith:EKMP7IXH","schema_version":"1.0","canonical_sha256":"2298ffa2e7374966475d784cc97b14de2e7080495bc3ba4a17f9f99fb2464d85","source":{"kind":"arxiv","id":"2505.01319","version":2},"attestation_state":"computed","paper":{"title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Karan Singh, Luiz Gustavo Hafemann, Yifang Pan","submitted_at":"2025-05-02T14:47:21Z","abstract_excerpt":"Speech-driven 3D facial animation plays a key role in applications such as virtual avatars, gaming, and digital content creation. While existing methods have made significant progress in achieving accurate lip synchronization and generating basic emotional expressions, they often struggle to capture and effectively transfer nuanced performance styles. We propose a novel example-based generation framework that conditions a latent diffusion model on a reference style clip to produce highly expressive and temporally coherent facial animations. To address the challenge of accurately adhering to th"},"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":"2505.01319","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-05-02T14:47:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ce98a5a098f3e98b6a77e6701893da73a72810ef7d2661720a18e4b51952b86","abstract_canon_sha256":"8bfdee11c7adcdfda04695cb6976ba0b1619f43feb861967318ad335c50d15f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:19.229668Z","signature_b64":"JgXlb8peaO5tBL8LMv2K5iuLxlUVMMemONHCr5GS7Lyh2Tq7XmCrJLuR4Rr8meeW2is1TkZEwR+/on/oLn0xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2298ffa2e7374966475d784cc97b14de2e7080495bc3ba4a17f9f99fb2464d85","last_reissued_at":"2026-07-05T11:37:19.229173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:19.229173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model See Model Do: Speech-Driven Facial Animation with Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Karan Singh, Luiz Gustavo Hafemann, Yifang Pan","submitted_at":"2025-05-02T14:47:21Z","abstract_excerpt":"Speech-driven 3D facial animation plays a key role in applications such as virtual avatars, gaming, and digital content creation. While existing methods have made significant progress in achieving accurate lip synchronization and generating basic emotional expressions, they often struggle to capture and effectively transfer nuanced performance styles. We propose a novel example-based generation framework that conditions a latent diffusion model on a reference style clip to produce highly expressive and temporally coherent facial animations. To address the challenge of accurately adhering to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01319","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/2505.01319/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":"2505.01319","created_at":"2026-07-05T11:37:19.229229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01319v2","created_at":"2026-07-05T11:37:19.229229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01319","created_at":"2026-07-05T11:37:19.229229+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKMP7IXHG5EW","created_at":"2026-07-05T11:37:19.229229+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKMP7IXHG5EWMR25","created_at":"2026-07-05T11:37:19.229229+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKMP7IXH","created_at":"2026-07-05T11:37:19.229229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21541","citing_title":"DiffDecompose: Layer-Wise Decomposition of Alpha-Composited Images via Diffusion Transformers","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y","json":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y.json","graph_json":"https://pith.science/api/pith-number/EKMP7IXHG5EWMR25PBGMS6YU3Y/graph.json","events_json":"https://pith.science/api/pith-number/EKMP7IXHG5EWMR25PBGMS6YU3Y/events.json","paper":"https://pith.science/paper/EKMP7IXH"},"agent_actions":{"view_html":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y","download_json":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y.json","view_paper":"https://pith.science/paper/EKMP7IXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01319&json=true","fetch_graph":"https://pith.science/api/pith-number/EKMP7IXHG5EWMR25PBGMS6YU3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/EKMP7IXHG5EWMR25PBGMS6YU3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y/action/storage_attestation","attest_author":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y/action/author_attestation","sign_citation":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y/action/citation_signature","submit_replication":"https://pith.science/pith/EKMP7IXHG5EWMR25PBGMS6YU3Y/action/replication_record"}},"created_at":"2026-07-05T11:37:19.229229+00:00","updated_at":"2026-07-05T11:37:19.229229+00:00"}