{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AIU6S2CDYAS2QYY73QLRLKO5JI","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":"e4a73ad71ddd6c419abe2664f98c4090c4abdf172dfd1f7add82c8d5c863a087","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T17:58:24Z","title_canon_sha256":"c90aaa6dd6f2308c028d9e9b39658dfaa721c99cd3b3aac907add43bcc5cf65e"},"schema_version":"1.0","source":{"id":"2508.08248","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.08248","created_at":"2026-07-05T11:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.08248v1","created_at":"2026-07-05T11:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08248","created_at":"2026-07-05T11:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"AIU6S2CDYAS2","created_at":"2026-07-05T11:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"AIU6S2CDYAS2QYY7","created_at":"2026-07-05T11:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"AIU6S2CD","created_at":"2026-07-05T11:52:10Z"}],"graph_snapshots":[{"event_id":"sha256:a73b8933e5a84f4cbc1a6b651780abd6f410ec1e831d778e1b3621220a6d1d56","target":"graph","created_at":"2026-07-05T11:52:10Z","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/2508.08248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current diffusion models for audio-driven avatar video generation struggle to synthesize long videos with natural audio synchronization and identity consistency. This paper presents StableAvatar, the first end-to-end video diffusion transformer that synthesizes infinite-length high-quality videos without post-processing. Conditioned on a reference image and audio, StableAvatar integrates tailored training and inference modules to enable infinite-length video generation. We observe that the main reason preventing existing models from generating long videos lies in their audio modeling. They typ","authors_text":"Chong Luo, Qi Dai, Shuyuan Tu, Xintong Han, Yinming Huang, Yueming Pan, Yu-Gang Jiang, Zhen Xing, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T17:58:24Z","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08248","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":"sha256:64938b5c769b64aef5f811e612c12b63e4f759458f54952fafd3efacc77ddc8f","target":"record","created_at":"2026-07-05T11:52:10Z","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":"e4a73ad71ddd6c419abe2664f98c4090c4abdf172dfd1f7add82c8d5c863a087","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T17:58:24Z","title_canon_sha256":"c90aaa6dd6f2308c028d9e9b39658dfaa721c99cd3b3aac907add43bcc5cf65e"},"schema_version":"1.0","source":{"id":"2508.08248","kind":"arxiv","version":1}},"canonical_sha256":"0229e96843c025a8631fdc1715a9dd4a190bbe98730335fc0fd591d9dd8e1cf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0229e96843c025a8631fdc1715a9dd4a190bbe98730335fc0fd591d9dd8e1cf8","first_computed_at":"2026-07-05T11:52:10.286439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:10.286439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lyhJqE9SuRcAmNqEXEYPr6mFdgxVnTYl40CJ0lrTdVV1KCNli5TPK+ES2PIOCdKVvp4SzjrE22V8pP5VC9XeAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:10.286916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.08248","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64938b5c769b64aef5f811e612c12b63e4f759458f54952fafd3efacc77ddc8f","sha256:a73b8933e5a84f4cbc1a6b651780abd6f410ec1e831d778e1b3621220a6d1d56"],"state_sha256":"fa13aa1062e32425febb67c03b07c9a6da580733961288d359c929fe68c0d933"}