{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LHHIIPK4YSNXAMJNRF3ZQV4DOD","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":"51f3b60b1d54cf1e1ffbc38f229401dcea6b6245f1b29e79b5cb42ddda66ad2b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T16:12:18Z","title_canon_sha256":"edea3371ffd87aa7505e11d9c8c58b632aff2b6736e73f84e0e42f9da44554f5"},"schema_version":"1.0","source":{"id":"2606.02441","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02441","created_at":"2026-06-02T03:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02441v1","created_at":"2026-06-02T03:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02441","created_at":"2026-06-02T03:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"LHHIIPK4YSNX","created_at":"2026-06-02T03:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"LHHIIPK4YSNXAMJN","created_at":"2026-06-02T03:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"LHHIIPK4","created_at":"2026-06-02T03:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:3c2e380c2eb9645eaa2baf19e00bad20c55fe7fe357a370292ffe678dfa727cf","target":"graph","created_at":"2026-06-02T03:05:06Z","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/2606.02441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identity-preserving video generation (IPVG) aims to synthesize high-fidelity videos that follow text prompts while faithfully preserving a reference identity. Despite recent progress, existing IPVG methods still struggle to balance high-level semantic control and low-level identity fidelity. To bridge this gap, we propose ST-DRC, an effective Spatial-Temporal Decoupled Reference Conditioning framework for identity-preserving text-to-video generation. At the framework level, ST-DRC performs latent in-context feature injection by encoding the reference image with the video VAE and concatenating ","authors_text":"Jiangning Zhang, Lizhuang Ma, Qingdong He, Teng Hu, Yuheng Chen, Yuji Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T16:12:18Z","title":"Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02441","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":"sha256:2d20249049e1950795afe1cd4a0d9123dc976d0b8a8cc045447be172dda3a7df","target":"record","created_at":"2026-06-02T03:05:06Z","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":"51f3b60b1d54cf1e1ffbc38f229401dcea6b6245f1b29e79b5cb42ddda66ad2b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T16:12:18Z","title_canon_sha256":"edea3371ffd87aa7505e11d9c8c58b632aff2b6736e73f84e0e42f9da44554f5"},"schema_version":"1.0","source":{"id":"2606.02441","kind":"arxiv","version":1}},"canonical_sha256":"59ce843d5cc49b70312d897798578370f8336c436956d3ed8d7e7e44bcf8f887","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59ce843d5cc49b70312d897798578370f8336c436956d3ed8d7e7e44bcf8f887","first_computed_at":"2026-06-02T03:05:06.300510Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:05:06.300510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F47LOKDN87bHOgwLocIwZDfdWX3n5xP6QTfu+ar0mD1y7WLeHXDW6JLeKpk54ARJ1V/j0MR2dF4RAeYFgSCQDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T03:05:06.300935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02441","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d20249049e1950795afe1cd4a0d9123dc976d0b8a8cc045447be172dda3a7df","sha256:3c2e380c2eb9645eaa2baf19e00bad20c55fe7fe357a370292ffe678dfa727cf"],"state_sha256":"b509f2101203402f21c2a79af1f064c59853be320e689e2327ab1e4e2de911cf"}