{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QC7CIPJY3UYJKVZAZ2PBGBCP67","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":"3b145f9d3abebef1b72521419d65a776e1da8c0dd6aa769f06a2b1605f14210d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T16:44:50Z","title_canon_sha256":"c583dba26866ed36769fdc8e35a528eb69c905640b482ab97f2730d55e2c22e6"},"schema_version":"1.0","source":{"id":"2406.08394","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08394","created_at":"2026-07-05T09:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08394v3","created_at":"2026-07-05T09:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08394","created_at":"2026-07-05T09:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"QC7CIPJY3UYJ","created_at":"2026-07-05T09:55:33Z"},{"alias_kind":"pith_short_16","alias_value":"QC7CIPJY3UYJKVZA","created_at":"2026-07-05T09:55:33Z"},{"alias_kind":"pith_short_8","alias_value":"QC7CIPJY","created_at":"2026-07-05T09:55:33Z"}],"graph_snapshots":[{"event_id":"sha256:232c3af364ada7bd23d49b7d84c1a2fc8c2f0062b0c8f96fcd9a42ff8f264bea","target":"graph","created_at":"2026-07-05T09:55:33Z","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/2406.08394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VisionLLM v2, an end-to-end generalist multimodal large model (MLLM) that unifies visual perception, understanding, and generation within a single framework. Unlike traditional MLLMs limited to text output, VisionLLM v2 significantly broadens its application scope. It excels not only in conventional visual question answering (VQA) but also in open-ended, cross-domain vision tasks such as object localization, pose estimation, and image generation and editing. To this end, we propose a new information transmission mechanism termed \"super link\", as a medium to connect MLLM with task-sp","authors_text":"Jiannan Wu, Jifeng Dai, Lewei Lu, Muyan Zhong, Ping Luo, Sen Xing, Tong Lu, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zeqiang Lai, Zhaoyang Liu, Zhe Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T16:44:50Z","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08394","kind":"arxiv","version":3},"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":"sha256:12cd4b6ef05e08c55b29c5d474b2ce3aeb09c2a370f3128cdead32f0a3d315ad","target":"record","created_at":"2026-07-05T09:55:33Z","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":"3b145f9d3abebef1b72521419d65a776e1da8c0dd6aa769f06a2b1605f14210d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-12T16:44:50Z","title_canon_sha256":"c583dba26866ed36769fdc8e35a528eb69c905640b482ab97f2730d55e2c22e6"},"schema_version":"1.0","source":{"id":"2406.08394","kind":"arxiv","version":3}},"canonical_sha256":"80be243d38dd30955720ce9e13044ff7d85ddf082465710d5d51a2406fc933ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80be243d38dd30955720ce9e13044ff7d85ddf082465710d5d51a2406fc933ba","first_computed_at":"2026-07-05T09:55:33.600240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:33.600240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jyqfyuiDtirVAAhiEoPfhX7/Vew6zGKKpkWBA7UYUNx3HAmArDA0OgDVjyg7IwRu1h/atmZxulBHOAxjxpYpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:33.600835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08394","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12cd4b6ef05e08c55b29c5d474b2ce3aeb09c2a370f3128cdead32f0a3d315ad","sha256:232c3af364ada7bd23d49b7d84c1a2fc8c2f0062b0c8f96fcd9a42ff8f264bea"],"state_sha256":"ff6083c815587f34bba91efe7d957f9f935338a6b69d49b926ef51dba197dee7"}