{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3XTUKCEQUPKYWY5ZI7GPTVNVYH","short_pith_number":"pith:3XTUKCEQ","canonical_record":{"source":{"id":"2607.04311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:54:33Z","cross_cats_sorted":[],"title_canon_sha256":"9b7c098fe008e9bd4cf6153fac9a03c135496a5f624d0fa0a3a4486fd31996f1","abstract_canon_sha256":"9a74ee0b68dcedf27c62204e5312f8e0d5cbc9c41c08fb773454dcddac362b05"},"schema_version":"1.0"},"canonical_sha256":"dde7450890a3d58b63b947ccf9d5b5c1fce106359c782fab3bb1841a9fed94d3","source":{"kind":"arxiv","id":"2607.04311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04311","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04311v1","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04311","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"3XTUKCEQUPKY","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_16","alias_value":"3XTUKCEQUPKYWY5Z","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_8","alias_value":"3XTUKCEQ","created_at":"2026-07-07T02:19:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3XTUKCEQUPKYWY5ZI7GPTVNVYH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:54:33Z","cross_cats_sorted":[],"title_canon_sha256":"9b7c098fe008e9bd4cf6153fac9a03c135496a5f624d0fa0a3a4486fd31996f1","abstract_canon_sha256":"9a74ee0b68dcedf27c62204e5312f8e0d5cbc9c41c08fb773454dcddac362b05"},"schema_version":"1.0"},"canonical_sha256":"dde7450890a3d58b63b947ccf9d5b5c1fce106359c782fab3bb1841a9fed94d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:08.065827Z","signature_b64":"BYD8vZSsiU8pwvvSxBdwrefdcPLYMVgtY/w7DjcFvRQJW9t7TjKBzV7B4X6HLPk+Al9t67i3I+j22vy+4CV6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dde7450890a3d58b63b947ccf9d5b5c1fce106359c782fab3bb1841a9fed94d3","last_reissued_at":"2026-07-07T02:19:08.065103Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:08.065103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04311","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NGW8FS6sTM047XDDNCv4/+HzmvPgloWms+Vp7YHQXp2e8aBkxwLd2EXACojE5SlKWpyX8FWZSAvBF+dBPBPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:46:20.111670Z"},"content_sha256":"aecfd21d81673fec3e51e591d4bb786e3da79ea02643c41aa665e0b354d2dcbe","schema_version":"1.0","event_id":"sha256:aecfd21d81673fec3e51e591d4bb786e3da79ea02643c41aa665e0b354d2dcbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3XTUKCEQUPKYWY5ZI7GPTVNVYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Hongmei Wang, Jiarong Ou, Qinglin Lu, Rui Chen, Wenqing Yu, Yezhou Liu, Yifeng Ma, Yuan Zhou, Zhentao Yu, Zilin Yang, Zixiang Zhou","submitted_at":"2026-07-05T13:54:33Z","abstract_excerpt":"Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity consistency and model complex relationships among multiple subjects. In this paper, we propose Aura, a unified framework for high-fidelity and identity-consistent video generation. To better capture scene dynamics and subject interactions, we introduce AI director-level captions that provide dense and structured descriptions of video content. We further leverage a vision-language model (VLM) with learnable queries to extract multimodal semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04311","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/2607.04311/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6Gq24ekvR5Bil1fSQpNJT62cVi+/kNARgdl9B4SZoM2QkK06EbZdm58jiUTFetYcCkOo15+/iC4pWTcZTU7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:46:20.112196Z"},"content_sha256":"3c1786f9339bac54404c3388a41376e7c0006004d9508d1a3c065aafb8db9de9","schema_version":"1.0","event_id":"sha256:3c1786f9339bac54404c3388a41376e7c0006004d9508d1a3c065aafb8db9de9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/bundle.json","state_url":"https://pith.science/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T14:46:20Z","links":{"resolver":"https://pith.science/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH","bundle":"https://pith.science/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/bundle.json","state":"https://pith.science/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XTUKCEQUPKYWY5ZI7GPTVNVYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3XTUKCEQUPKYWY5ZI7GPTVNVYH","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":"9a74ee0b68dcedf27c62204e5312f8e0d5cbc9c41c08fb773454dcddac362b05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:54:33Z","title_canon_sha256":"9b7c098fe008e9bd4cf6153fac9a03c135496a5f624d0fa0a3a4486fd31996f1"},"schema_version":"1.0","source":{"id":"2607.04311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04311","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04311v1","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04311","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_12","alias_value":"3XTUKCEQUPKY","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_16","alias_value":"3XTUKCEQUPKYWY5Z","created_at":"2026-07-07T02:19:08Z"},{"alias_kind":"pith_short_8","alias_value":"3XTUKCEQ","created_at":"2026-07-07T02:19:08Z"}],"graph_snapshots":[{"event_id":"sha256:3c1786f9339bac54404c3388a41376e7c0006004d9508d1a3c065aafb8db9de9","target":"graph","created_at":"2026-07-07T02:19:08Z","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/2607.04311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subject-driven and multi-element video generation are central to controllable video synthesis, but existing methods still struggle to preserve identity consistency and model complex relationships among multiple subjects. In this paper, we propose Aura, a unified framework for high-fidelity and identity-consistent video generation. To better capture scene dynamics and subject interactions, we introduce AI director-level captions that provide dense and structured descriptions of video content. We further leverage a vision-language model (VLM) with learnable queries to extract multimodal semantic","authors_text":"Cong Wang, Hongmei Wang, Jiarong Ou, Qinglin Lu, Rui Chen, Wenqing Yu, Yezhou Liu, Yifeng Ma, Yuan Zhou, Zhentao Yu, Zilin Yang, Zixiang Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:54:33Z","title":"Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04311","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:aecfd21d81673fec3e51e591d4bb786e3da79ea02643c41aa665e0b354d2dcbe","target":"record","created_at":"2026-07-07T02:19:08Z","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":"9a74ee0b68dcedf27c62204e5312f8e0d5cbc9c41c08fb773454dcddac362b05","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-05T13:54:33Z","title_canon_sha256":"9b7c098fe008e9bd4cf6153fac9a03c135496a5f624d0fa0a3a4486fd31996f1"},"schema_version":"1.0","source":{"id":"2607.04311","kind":"arxiv","version":1}},"canonical_sha256":"dde7450890a3d58b63b947ccf9d5b5c1fce106359c782fab3bb1841a9fed94d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dde7450890a3d58b63b947ccf9d5b5c1fce106359c782fab3bb1841a9fed94d3","first_computed_at":"2026-07-07T02:19:08.065103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:08.065103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BYD8vZSsiU8pwvvSxBdwrefdcPLYMVgtY/w7DjcFvRQJW9t7TjKBzV7B4X6HLPk+Al9t67i3I+j22vy+4CV6BA==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:08.065827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aecfd21d81673fec3e51e591d4bb786e3da79ea02643c41aa665e0b354d2dcbe","sha256:3c1786f9339bac54404c3388a41376e7c0006004d9508d1a3c065aafb8db9de9"],"state_sha256":"7b36fe93600d4dc8372e932c7de35ad4c1fdd1af9f3ded9b070eb799d9603db9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J0qLk1YgIiljNFSPCEyQb2Cd6ImMZOEGEWTP1b1DB5OdSsDzOMpcDgfsttAuURluOiC8oPruxOKsiRmQrdSmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:46:20.117556Z","bundle_sha256":"83b5f646251484f43684c5d8d64ff90c6afb760631956e36d0f8bfda3874d1b2"}}