{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XYS7RZSLGGAWMOOW24JFCP4Z6O","short_pith_number":"pith:XYS7RZSL","canonical_record":{"source":{"id":"2504.04842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T08:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"1a65b8747869a0125709e2b4fda69d0850cedb84666e19af03eca616409280e5","abstract_canon_sha256":"a1cea97541e6030294838791df771c2a4fd78e0038f6c63242dec9ae9e4220cc"},"schema_version":"1.0"},"canonical_sha256":"be25f8e64b31816639d6d712513f99f3ba0def7b194e750ab71a906aaa0787f8","source":{"kind":"arxiv","id":"2504.04842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04842","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04842v1","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04842","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"XYS7RZSLGGAW","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"XYS7RZSLGGAWMOOW","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"XYS7RZSL","created_at":"2026-07-05T10:45:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XYS7RZSLGGAWMOOW24JFCP4Z6O","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T08:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"1a65b8747869a0125709e2b4fda69d0850cedb84666e19af03eca616409280e5","abstract_canon_sha256":"a1cea97541e6030294838791df771c2a4fd78e0038f6c63242dec9ae9e4220cc"},"schema_version":"1.0"},"canonical_sha256":"be25f8e64b31816639d6d712513f99f3ba0def7b194e750ab71a906aaa0787f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:30.575305Z","signature_b64":"DTR9rLAlvzioLtWx7l2tDH42umIPHbA5hLM6x89mY30qRjYxGoBLSXHK85gmPopsDJ1B4Pgz+fobN1RdwVC/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be25f8e64b31816639d6d712513f99f3ba0def7b194e750ab71a906aaa0787f8","last_reissued_at":"2026-07-05T10:45:30.574818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:30.574818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04842","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":"2026-07-05T10:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/bDlOFie1KEGxVlH0ECwY75wWDHUU/f89QIdmhKJc4G7q09BJGZTW1C6AY5TdFA/dnwk9CM6Abw+N5NTahADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:32:33.535942Z"},"content_sha256":"70e8d633b1a015acb7aab73c720c6d4d6efe24e2f9e69a706522db256936a097","schema_version":"1.0","event_id":"sha256:70e8d633b1a015acb7aab73c720c6d4d6efe24e2f9e69a706522db256936a097"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XYS7RZSLGGAWMOOW24JFCP4Z6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Jiang, Kun Zhao, Mengchao Wang, Mu Xu, Qiang Wang, Yaqi Fan, Yonggang Qi, Yunpeng Zhang","submitted_at":"2025-04-07T08:56:01Z","abstract_excerpt":"Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated global body movements, and the dynamic background. To address these limitations, we propose a novel framework that leverages a pretrained video diffusion transformer model to generate high-fidelity, coherent talking portraits with controllable motion dynamics. At the core of our work is a dual-stage audio-visual alignment strategy. In the first stage, we employ a clip-level training scheme to establish coherent global "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04842","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/2504.04842/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":"2026-07-05T10:45:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"az/kIWnXHiUznSqoInr6lpFwf8UDJismRbvnpnQRsp8Y+sceAV/77Fw64rZF9p/lulANM+i2HQMKTFskD06fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:32:33.536937Z"},"content_sha256":"f3652b2355266d7000a30eaacc6dc033ac1d6e73b2fd9d5d865c4ae638caf97c","schema_version":"1.0","event_id":"sha256:f3652b2355266d7000a30eaacc6dc033ac1d6e73b2fd9d5d865c4ae638caf97c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/bundle.json","state_url":"https://pith.science/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/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":"2026-08-03T15:32:33Z","links":{"resolver":"https://pith.science/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O","bundle":"https://pith.science/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/bundle.json","state":"https://pith.science/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYS7RZSLGGAWMOOW24JFCP4Z6O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYS7RZSLGGAWMOOW24JFCP4Z6O","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":"a1cea97541e6030294838791df771c2a4fd78e0038f6c63242dec9ae9e4220cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T08:56:01Z","title_canon_sha256":"1a65b8747869a0125709e2b4fda69d0850cedb84666e19af03eca616409280e5"},"schema_version":"1.0","source":{"id":"2504.04842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04842","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04842v1","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04842","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_12","alias_value":"XYS7RZSLGGAW","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_16","alias_value":"XYS7RZSLGGAWMOOW","created_at":"2026-07-05T10:45:30Z"},{"alias_kind":"pith_short_8","alias_value":"XYS7RZSL","created_at":"2026-07-05T10:45:30Z"}],"graph_snapshots":[{"event_id":"sha256:f3652b2355266d7000a30eaacc6dc033ac1d6e73b2fd9d5d865c4ae638caf97c","target":"graph","created_at":"2026-07-05T10:45:30Z","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/2504.04842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated global body movements, and the dynamic background. To address these limitations, we propose a novel framework that leverages a pretrained video diffusion transformer model to generate high-fidelity, coherent talking portraits with controllable motion dynamics. At the core of our work is a dual-stage audio-visual alignment strategy. In the first stage, we employ a clip-level training scheme to establish coherent global ","authors_text":"Fan Jiang, Kun Zhao, Mengchao Wang, Mu Xu, Qiang Wang, Yaqi Fan, Yonggang Qi, Yunpeng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T08:56:01Z","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04842","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":"sha256:70e8d633b1a015acb7aab73c720c6d4d6efe24e2f9e69a706522db256936a097","target":"record","created_at":"2026-07-05T10:45:30Z","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":"a1cea97541e6030294838791df771c2a4fd78e0038f6c63242dec9ae9e4220cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T08:56:01Z","title_canon_sha256":"1a65b8747869a0125709e2b4fda69d0850cedb84666e19af03eca616409280e5"},"schema_version":"1.0","source":{"id":"2504.04842","kind":"arxiv","version":1}},"canonical_sha256":"be25f8e64b31816639d6d712513f99f3ba0def7b194e750ab71a906aaa0787f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be25f8e64b31816639d6d712513f99f3ba0def7b194e750ab71a906aaa0787f8","first_computed_at":"2026-07-05T10:45:30.574818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:30.574818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DTR9rLAlvzioLtWx7l2tDH42umIPHbA5hLM6x89mY30qRjYxGoBLSXHK85gmPopsDJ1B4Pgz+fobN1RdwVC/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:30.575305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70e8d633b1a015acb7aab73c720c6d4d6efe24e2f9e69a706522db256936a097","sha256:f3652b2355266d7000a30eaacc6dc033ac1d6e73b2fd9d5d865c4ae638caf97c"],"state_sha256":"049b0ea0be4d105da022c6859ecf96b2c7893266bb43495a60381a811a72c2d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uCq16hbHLyt8AV4S8TqIO0TIqLvN5lRoea2agi6ZPFVs2Cn1bOHJFJXKNUzYKLG7VPB3JFW/0qggcMIRj9enBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:32:33.542821Z","bundle_sha256":"d319c919c4a02bdade658175a6d639db0d76f58927b4c88066158837b6537137"}}