{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SRPIE3JEHWAGFPFC6674XP42X","short_pith_number":"pith:4SRPIE3J","schema_version":"1.0","canonical_sha256":"e4a2f4136921ec0315e517bdfe5dfcd5f325a97da2e6b04034a135de1f6fbb01","source":{"kind":"arxiv","id":"2512.13247","version":2},"attestation_state":"computed","paper":{"title":"STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Foivos Paraperas Papantoniou, Rolandos Alexandros Potamias, Stathis Galanakis, Stefanos Zafeiriou","submitted_at":"2025-12-15T11:59:01Z","abstract_excerpt":"This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and dynamic viewpoint control, given an identity embedding or reference image, within a unified framework. Existing 2D speech-to-video diffusion models depend heavily on reference guidance, leading to limited motion diversity. At the same time, 3D-aware animation typically relies on inversion through pretrained tri-plane generators, which often leads to imperfect reconstructions and identity drift. We rethink reference- and geometry-based paradigms in two"},"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":"2512.13247","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-15T11:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"a636b27d929a75489abf070c2ff5528ca6ff7e5530853080c6c14ed90f2d5035","abstract_canon_sha256":"43d40056fa26a78b24c633a5c50b4b1fd08dd23444b75218f8157aa37c613d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:19:54.165475Z","signature_b64":"dJVndU5/VtuWCaZUPGQ92Iy2s5RLlIj+QgeyWBWb8GcCXDu+r42SUzWjBpj3PghExaIKdeneh96Ow0kWk8ziCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4a2f4136921ec0315e517bdfe5dfcd5f325a97da2e6b04034a135de1f6fbb01","last_reissued_at":"2026-07-21T00:19:54.164459Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:19:54.164459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Foivos Paraperas Papantoniou, Rolandos Alexandros Potamias, Stathis Galanakis, Stefanos Zafeiriou","submitted_at":"2025-12-15T11:59:01Z","abstract_excerpt":"This paper presents STARCaster, an identity-aware spatio-temporal video diffusion model that addresses both speech-driven portrait animation and dynamic viewpoint control, given an identity embedding or reference image, within a unified framework. Existing 2D speech-to-video diffusion models depend heavily on reference guidance, leading to limited motion diversity. At the same time, 3D-aware animation typically relies on inversion through pretrained tri-plane generators, which often leads to imperfect reconstructions and identity drift. We rethink reference- and geometry-based paradigms in two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.13247","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/2512.13247/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":"2512.13247","created_at":"2026-07-21T00:19:54.164928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.13247v2","created_at":"2026-07-21T00:19:54.164928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13247","created_at":"2026-07-21T00:19:54.164928+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SRPIE3JEHWA","created_at":"2026-07-21T00:19:54.164928+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SRPIE3JEHWAGFPF","created_at":"2026-07-21T00:19:54.164928+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SRPIE3J","created_at":"2026-07-21T00:19:54.164928+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/4SRPIE3JEHWAGFPFC6674XP42X","json":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X.json","graph_json":"https://pith.science/api/pith-number/4SRPIE3JEHWAGFPFC6674XP42X/graph.json","events_json":"https://pith.science/api/pith-number/4SRPIE3JEHWAGFPFC6674XP42X/events.json","paper":"https://pith.science/paper/4SRPIE3J"},"agent_actions":{"view_html":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X","download_json":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X.json","view_paper":"https://pith.science/paper/4SRPIE3J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.13247&json=true","fetch_graph":"https://pith.science/api/pith-number/4SRPIE3JEHWAGFPFC6674XP42X/graph.json","fetch_events":"https://pith.science/api/pith-number/4SRPIE3JEHWAGFPFC6674XP42X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X/action/storage_attestation","attest_author":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X/action/author_attestation","sign_citation":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X/action/citation_signature","submit_replication":"https://pith.science/pith/4SRPIE3JEHWAGFPFC6674XP42X/action/replication_record"}},"created_at":"2026-07-21T00:19:54.164928+00:00","updated_at":"2026-07-21T00:19:54.164928+00:00"}