{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MPHVRMY2Z7EDJ5CVEDB2QGRC5L","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":"010e9aeeb5c03f45f4e67ae0f6cb2882747f3876b78dd185d2329049dc0b4422","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-26T17:59:57Z","title_canon_sha256":"a6c2c3a7d880a3c10b869eb42da881180d2c5ce7292e3d342e9e8e056de2bede"},"schema_version":"1.0","source":{"id":"2603.25743","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.25743","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2603.25743v2","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.25743","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"MPHVRMY2Z7ED","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"MPHVRMY2Z7EDJ5CV","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"MPHVRMY2","created_at":"2026-06-30T02:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:20357f934cd1451304fbc1e467a9b331f7907430245cae53af1082dc8145e8c7","target":"graph","created_at":"2026-06-30T02:17:19Z","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/2603.25743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typically introduce additional high-level semantic or cross-modal features alongside the VAE latent representation of the reference image and jointly feed them into the diffusion Transformer (DiT). These auxiliary representations provide semantic guidance and act as implicit alignment signals, which can partially alleviate pi","authors_text":"Ge Wu, Hang Zhou, Haocheng Feng, Jian Yang, Jingdong Wang, Lei Wang, Yaxing Wang, Yuxin Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-26T17:59:57Z","title":"RefAlign: Representation Alignment for Reference-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.25743","kind":"arxiv","version":2},"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":"sha256:48c579ceb597f8eeec28d0a317ab9a7e1e9fb8b2ed40718616fcf9157a0b1d20","target":"record","created_at":"2026-06-30T02:17:19Z","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":"010e9aeeb5c03f45f4e67ae0f6cb2882747f3876b78dd185d2329049dc0b4422","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-26T17:59:57Z","title_canon_sha256":"a6c2c3a7d880a3c10b869eb42da881180d2c5ce7292e3d342e9e8e056de2bede"},"schema_version":"1.0","source":{"id":"2603.25743","kind":"arxiv","version":2}},"canonical_sha256":"63cf58b31acfc834f45520c3a81a22eac61f894737e6eef78477281493e0c701","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63cf58b31acfc834f45520c3a81a22eac61f894737e6eef78477281493e0c701","first_computed_at":"2026-06-30T02:17:19.266904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:19.266904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+GGWF7WJOUKyHGxgYMJFb5RP6BSaVYlHJnYaE7Rl7Q6pfmrQwYYchhkpNlrZ0Gk0KCj18Zz+e2qTcuJ1L2mBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:19.267505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.25743","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48c579ceb597f8eeec28d0a317ab9a7e1e9fb8b2ed40718616fcf9157a0b1d20","sha256:20357f934cd1451304fbc1e467a9b331f7907430245cae53af1082dc8145e8c7"],"state_sha256":"f01e50b68299feb11efbb0d1ea304b856693754662fc3438982a6508fc4ba681"}