{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OSXLWJWWC3R77YEEMFDYCD62RE","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":"c628a2d13f5cbfcb04cf38fffd41f81f7c150d1f67382ff29020837e308873f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:11:09Z","title_canon_sha256":"5c32db7d53af7f89e00e2e68447327bf79d7d3e45e25676380de66eb99e9a7fe"},"schema_version":"1.0","source":{"id":"2506.07848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07848","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07848v1","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07848","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"OSXLWJWWC3R7","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"OSXLWJWWC3R77YEE","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"OSXLWJWW","created_at":"2026-07-05T11:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:c72e28559fd34786ec8e4f883b8bbbe3406d970a8533732fad5a146ba84cecfb","target":"graph","created_at":"2026-07-05T11:18:34Z","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/2506.07848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in video generation, existing models still lack fine-grained controllability, especially for multi-subject customization with consistent identity and interaction. In this paper, we propose PolyVivid, a multi-subject video customization framework that enables flexible and identity-consistent generation. To establish accurate correspondences between subject images and textual entities, we design a VLLM-based text-image fusion module that embeds visual identities into the textual space for precise grounding. To further enhance identity preservation and subject interaction,","authors_text":"Jiangning Zhang, Qinglin Lu, Ran Yi, Teng Hu, Yuan Zhou, Zhengguang Zhou, Zhentao Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:11:09Z","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07848","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":"sha256:948c48bc048b74d2b21e4ac63f19ea0eaf26a1e23d68b58c141955b595378a18","target":"record","created_at":"2026-07-05T11:18:34Z","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":"c628a2d13f5cbfcb04cf38fffd41f81f7c150d1f67382ff29020837e308873f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T15:11:09Z","title_canon_sha256":"5c32db7d53af7f89e00e2e68447327bf79d7d3e45e25676380de66eb99e9a7fe"},"schema_version":"1.0","source":{"id":"2506.07848","kind":"arxiv","version":1}},"canonical_sha256":"74aebb26d616e3ffe0846147810fda89007093ba0d8b3f72949f2baa7840a260","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74aebb26d616e3ffe0846147810fda89007093ba0d8b3f72949f2baa7840a260","first_computed_at":"2026-07-05T11:18:34.392989Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:34.392989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uqLrSGYpYbSlK2IfAFhrIHJkIQ6xw0cL3wOhHscjeGCbu42mmcMPHijLVJcZjrWQZ1d7OgvSposLgphceq5YBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:34.393497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:948c48bc048b74d2b21e4ac63f19ea0eaf26a1e23d68b58c141955b595378a18","sha256:c72e28559fd34786ec8e4f883b8bbbe3406d970a8533732fad5a146ba84cecfb"],"state_sha256":"d94646aad6ca0d5838dddf6e471d6e158da998a41a73888e9fc61c1b9e74ffd6"}