{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SCPKYW2DBYLL4BMWFHQ6PZDXAG","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":"52057e406c51d9df0eeac35b945b4acb57037c0bac81498a89e1150597f722cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T15:33:18Z","title_canon_sha256":"b1a3f7a332ce3878a5628023284a380795bbce321bd3af781fad78d8eebc43cf"},"schema_version":"1.0","source":{"id":"2505.04512","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04512","created_at":"2026-07-05T11:00:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04512v2","created_at":"2026-07-05T11:00:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04512","created_at":"2026-07-05T11:00:10Z"},{"alias_kind":"pith_short_12","alias_value":"SCPKYW2DBYLL","created_at":"2026-07-05T11:00:10Z"},{"alias_kind":"pith_short_16","alias_value":"SCPKYW2DBYLL4BMW","created_at":"2026-07-05T11:00:10Z"},{"alias_kind":"pith_short_8","alias_value":"SCPKYW2D","created_at":"2026-07-05T11:00:10Z"}],"graph_snapshots":[{"event_id":"sha256:631b2f3fb847e2cfea7fa57e29b01724089cd1d5f3575cb54da386e64c00ad10","target":"graph","created_at":"2026-07-05T11:00:10Z","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/2505.04512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Customized video generation aims to produce videos featuring specific subjects under flexible user-defined conditions, yet existing methods often struggle with identity consistency and limited input modalities. In this paper, we propose HunyuanCustom, a multi-modal customized video generation framework that emphasizes subject consistency while supporting image, audio, video, and text conditions. Built upon HunyuanVideo, our model first addresses the image-text conditioned generation task by introducing a text-image fusion module based on LLaVA for enhanced multi-modal understanding, along with","authors_text":"Qinglin Lu, Qin Lin, Sen Liang, Teng Hu, Yuan Zhou, Zhengguang Zhou, Zhentao Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T15:33:18Z","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04512","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":"sha256:7cbe231d7d9402cd257d992f51a1801ce118a08ef6f25c563e41ab4c65d00c29","target":"record","created_at":"2026-07-05T11:00:10Z","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":"52057e406c51d9df0eeac35b945b4acb57037c0bac81498a89e1150597f722cb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T15:33:18Z","title_canon_sha256":"b1a3f7a332ce3878a5628023284a380795bbce321bd3af781fad78d8eebc43cf"},"schema_version":"1.0","source":{"id":"2505.04512","kind":"arxiv","version":2}},"canonical_sha256":"909eac5b430e16be059629e1e7e4770196c296325a4c4aa46062cfeb8376a978","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"909eac5b430e16be059629e1e7e4770196c296325a4c4aa46062cfeb8376a978","first_computed_at":"2026-07-05T11:00:10.282142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:10.282142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gR/vZI/7AqoZ5Qh51Gdqi00sBlGDeX546HNdtYCEo/Fmg5DWClxOFMcolsHdI8Dyb8fE8NRX7Ahij3nSEpCSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:10.282791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04512","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cbe231d7d9402cd257d992f51a1801ce118a08ef6f25c563e41ab4c65d00c29","sha256:631b2f3fb847e2cfea7fa57e29b01724089cd1d5f3575cb54da386e64c00ad10"],"state_sha256":"5a8c1f8d06d82f54c6534bdb522bcb28a23fbd4f5499a7b2201086a5999357ea"}