{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VVDREWALDJIVBAPAJY4SYY64VP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a99cb77cbdc6a9205740ea4123567c7ce2740a56a91ca6b58574883b6eaab5d1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-07-04T02:25:10Z","title_canon_sha256":"95316c2527f22d68e05bfe7727a48f37f7d2c5b0a4900c071cfc5bc4521dc486"},"schema_version":"1.0","source":{"id":"2507.03256","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03256","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03256v3","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03256","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"VVDREWALDJIV","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"VVDREWALDJIVBAPA","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"VVDREWAL","created_at":"2026-07-05T11:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:d364ac21f34c56edbcf050ec7852f92d4cbafeb5a1ec62c526e62502f7e4aea6","target":"graph","created_at":"2026-07-05T11:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.03256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong generation capabilities. However, several challenges remain for diffusion-based methods: 1) inefficient inference and visual artifacts caused by the implicit latent space of Variational Auto-Encoders (VAE), which complicates the diffusion process; 2) a lack of authentic facial expressions and head movements due to inadequate multi-modal information fusion. In this","authors_text":"Aowen Wang, Fan Wang, Gen Li, Gongxin Yao, Weihua Chen, Weinan Jia, Xinyang Li, Yichen Qian, Zhihui Lin","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-07-04T02:25:10Z","title":"MoDA: Multi-modal Diffusion Architecture for Talking Head Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03256","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c0ffac40b51035f3de28a22fc33881eba79979fe14af811e62ebe13959883b2","target":"record","created_at":"2026-07-05T11:50:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a99cb77cbdc6a9205740ea4123567c7ce2740a56a91ca6b58574883b6eaab5d1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-07-04T02:25:10Z","title_canon_sha256":"95316c2527f22d68e05bfe7727a48f37f7d2c5b0a4900c071cfc5bc4521dc486"},"schema_version":"1.0","source":{"id":"2507.03256","kind":"arxiv","version":3}},"canonical_sha256":"ad4712580b1a515081e04e392c63dcabc1847c6ec3ef4046b13aa053e9bd7ca8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4712580b1a515081e04e392c63dcabc1847c6ec3ef4046b13aa053e9bd7ca8","first_computed_at":"2026-07-05T11:50:38.141594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:38.141594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DeSqWp9J6Q8BacZFNhhaNhqb+ekxN978vknCx9uzCsYt5sskIgzEFb9gW2LKsD8ldeZPwAN7Obw5/OnzrDbuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:38.142074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03256","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c0ffac40b51035f3de28a22fc33881eba79979fe14af811e62ebe13959883b2","sha256:d364ac21f34c56edbcf050ec7852f92d4cbafeb5a1ec62c526e62502f7e4aea6"],"state_sha256":"badfcab93c44dbc94f1db31dc724e5d9cf6e74a9ed417c3d1926e89b0d8ee99a"}