{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J3XRWPSOMRPQ6JROWS26K5CGIQ","short_pith_number":"pith:J3XRWPSO","canonical_record":{"source":{"id":"2507.05092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T15:13:46Z","cross_cats_sorted":[],"title_canon_sha256":"52f26a4696dfa93b95685a14d4bcec903400c83aab1879338551b207ef4160ac","abstract_canon_sha256":"2add1cd7e9659df19872852514e166068792ae80ff2913e13a93b7466a1d8ec4"},"schema_version":"1.0"},"canonical_sha256":"4eef1b3e4e645f0f262eb4b5e574464437ca65a1c84bb3ca6a2b3f19cf3afa20","source":{"kind":"arxiv","id":"2507.05092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05092","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05092v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05092","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"J3XRWPSOMRPQ","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"J3XRWPSOMRPQ6JRO","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"J3XRWPSO","created_at":"2026-07-05T11:33:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J3XRWPSOMRPQ6JROWS26K5CGIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T15:13:46Z","cross_cats_sorted":[],"title_canon_sha256":"52f26a4696dfa93b95685a14d4bcec903400c83aab1879338551b207ef4160ac","abstract_canon_sha256":"2add1cd7e9659df19872852514e166068792ae80ff2913e13a93b7466a1d8ec4"},"schema_version":"1.0"},"canonical_sha256":"4eef1b3e4e645f0f262eb4b5e574464437ca65a1c84bb3ca6a2b3f19cf3afa20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:08.908068Z","signature_b64":"VNY9f7Ll4A2yiMAKH+YCl94oEd6VcfVYuDpqhL5nIhI9TBVvZd4dlzCZjTJXAbsb1UOWmBVSf8r+7O2PC7iLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eef1b3e4e645f0f262eb4b5e574464437ca65a1c84bb3ca6a2b3f19cf3afa20","last_reissued_at":"2026-07-05T11:33:08.907625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:08.907625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05092","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iiOSWXXer5KnSEeHt4M5Iq1ztuhDATrsqc2MHPsTX9gcMn4/oSmEOgbzqlacSNs1fwLLDUbMcQ1z86VZTizXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:36.705362Z"},"content_sha256":"f365c69cde3153c25023f385ebbf2604b86c746bc82c26566d78730f4cb89018","schema_version":"1.0","event_id":"sha256:f365c69cde3153c25023f385ebbf2604b86c746bc82c26566d78730f4cb89018"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J3XRWPSOMRPQ6JROWS26K5CGIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Yucheng Wang","submitted_at":"2025-07-07T15:13:46Z","abstract_excerpt":"Audio-driven talking head generation is critical for applications such as virtual assistants, video games, and films, where natural lip movements are essential. Despite progress in this field, challenges remain in producing both consistent and realistic facial animations. Existing methods, often based on GANs or UNet-based diffusion models, face three major limitations: (i) temporal jittering caused by weak temporal constraints, resulting in frame inconsistencies; (ii) identity drift due to insufficient 3D information extraction, leading to poor preservation of facial identity; and (iii) unnat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05092","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/2507.05092/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYZxUxdlMGkYPWP8oYjCXzGjGBqyMVu0o7/zMk5CVcyOaZoVXS6m1rUaVaIWGF7uX9LOZqYZHzyXgl6CGNLZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:36.705907Z"},"content_sha256":"0979c9066f77eb2de4f993e05f65ecbc20de0e5396e96d0472e95dc131061cb7","schema_version":"1.0","event_id":"sha256:0979c9066f77eb2de4f993e05f65ecbc20de0e5396e96d0472e95dc131061cb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/bundle.json","state_url":"https://pith.science/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:45:36Z","links":{"resolver":"https://pith.science/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ","bundle":"https://pith.science/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/bundle.json","state":"https://pith.science/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J3XRWPSOMRPQ6JROWS26K5CGIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J3XRWPSOMRPQ6JROWS26K5CGIQ","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":"2add1cd7e9659df19872852514e166068792ae80ff2913e13a93b7466a1d8ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T15:13:46Z","title_canon_sha256":"52f26a4696dfa93b95685a14d4bcec903400c83aab1879338551b207ef4160ac"},"schema_version":"1.0","source":{"id":"2507.05092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05092","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05092v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05092","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"J3XRWPSOMRPQ","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"J3XRWPSOMRPQ6JRO","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"J3XRWPSO","created_at":"2026-07-05T11:33:08Z"}],"graph_snapshots":[{"event_id":"sha256:0979c9066f77eb2de4f993e05f65ecbc20de0e5396e96d0472e95dc131061cb7","target":"graph","created_at":"2026-07-05T11:33:08Z","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/2507.05092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-driven talking head generation is critical for applications such as virtual assistants, video games, and films, where natural lip movements are essential. Despite progress in this field, challenges remain in producing both consistent and realistic facial animations. Existing methods, often based on GANs or UNet-based diffusion models, face three major limitations: (i) temporal jittering caused by weak temporal constraints, resulting in frame inconsistencies; (ii) identity drift due to insufficient 3D information extraction, leading to poor preservation of facial identity; and (iii) unnat","authors_text":"Dan Xu, Yucheng Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T15:13:46Z","title":"MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05092","kind":"arxiv","version":1},"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:f365c69cde3153c25023f385ebbf2604b86c746bc82c26566d78730f4cb89018","target":"record","created_at":"2026-07-05T11:33:08Z","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":"2add1cd7e9659df19872852514e166068792ae80ff2913e13a93b7466a1d8ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T15:13:46Z","title_canon_sha256":"52f26a4696dfa93b95685a14d4bcec903400c83aab1879338551b207ef4160ac"},"schema_version":"1.0","source":{"id":"2507.05092","kind":"arxiv","version":1}},"canonical_sha256":"4eef1b3e4e645f0f262eb4b5e574464437ca65a1c84bb3ca6a2b3f19cf3afa20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eef1b3e4e645f0f262eb4b5e574464437ca65a1c84bb3ca6a2b3f19cf3afa20","first_computed_at":"2026-07-05T11:33:08.907625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:08.907625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VNY9f7Ll4A2yiMAKH+YCl94oEd6VcfVYuDpqhL5nIhI9TBVvZd4dlzCZjTJXAbsb1UOWmBVSf8r+7O2PC7iLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:08.908068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f365c69cde3153c25023f385ebbf2604b86c746bc82c26566d78730f4cb89018","sha256:0979c9066f77eb2de4f993e05f65ecbc20de0e5396e96d0472e95dc131061cb7"],"state_sha256":"5444215716fcf8ae8b25f8aeb9f2b21032311318c1a5c57497ab502f4c576d51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/r3VLbeOlpapHqdJxux02o4JraPzkSTCwjC98KoqmWp0FQOkxk/4rkFcvaqgOIKz4PqqtL+eAzeD11cAJgmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:36.709669Z","bundle_sha256":"b4dff3a26150d75098ba816ed2c5b20bd6834bc4e6bc3a7af01358e05bf178c5"}}