{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LHHIIPK4YSNXAMJNRF3ZQV4DOD","short_pith_number":"pith:LHHIIPK4","schema_version":"1.0","canonical_sha256":"59ce843d5cc49b70312d897798578370f8336c436956d3ed8d7e7e44bcf8f887","source":{"kind":"arxiv","id":"2606.02441","version":1},"attestation_state":"computed","paper":{"title":"Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Lizhuang Ma, Qingdong He, Teng Hu, Yuheng Chen, Yuji Wang","submitted_at":"2026-06-01T16:12:18Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T16:12:18Z","cross_cats_sorted":[],"title_canon_sha256":"edea3371ffd87aa7505e11d9c8c58b632aff2b6736e73f84e0e42f9da44554f5","abstract_canon_sha256":"51f3b60b1d54cf1e1ffbc38f229401dcea6b6245f1b29e79b5cb42ddda66ad2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:05:06.300935Z","signature_b64":"F47LOKDN87bHOgwLocIwZDfdWX3n5xP6QTfu+ar0mD1y7WLeHXDW6JLeKpk54ARJ1V/j0MR2dF4RAeYFgSCQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59ce843d5cc49b70312d897798578370f8336c436956d3ed8d7e7e44bcf8f887","last_reissued_at":"2026-06-02T03:05:06.300510Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:05:06.300510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangning Zhang, Lizhuang Ma, Qingdong He, Teng Hu, Yuheng Chen, Yuji Wang","submitted_at":"2026-06-01T16:12:18Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02441","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/2606.02441/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02441","created_at":"2026-06-02T03:05:06.300579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02441v1","created_at":"2026-06-02T03:05:06.300579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02441","created_at":"2026-06-02T03:05:06.300579+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHHIIPK4YSNX","created_at":"2026-06-02T03:05:06.300579+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHHIIPK4YSNXAMJN","created_at":"2026-06-02T03:05:06.300579+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHHIIPK4","created_at":"2026-06-02T03:05:06.300579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD","json":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD.json","graph_json":"https://pith.science/api/pith-number/LHHIIPK4YSNXAMJNRF3ZQV4DOD/graph.json","events_json":"https://pith.science/api/pith-number/LHHIIPK4YSNXAMJNRF3ZQV4DOD/events.json","paper":"https://pith.science/paper/LHHIIPK4"},"agent_actions":{"view_html":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD","download_json":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD.json","view_paper":"https://pith.science/paper/LHHIIPK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02441&json=true","fetch_graph":"https://pith.science/api/pith-number/LHHIIPK4YSNXAMJNRF3ZQV4DOD/graph.json","fetch_events":"https://pith.science/api/pith-number/LHHIIPK4YSNXAMJNRF3ZQV4DOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD/action/storage_attestation","attest_author":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD/action/author_attestation","sign_citation":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD/action/citation_signature","submit_replication":"https://pith.science/pith/LHHIIPK4YSNXAMJNRF3ZQV4DOD/action/replication_record"}},"created_at":"2026-06-02T03:05:06.300579+00:00","updated_at":"2026-06-02T03:05:06.300579+00:00"}