{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DNHLL526LQVRCTYMHYFP4CKLOQ","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":"240224326e70c07f3bb3b4aa0f1ba6783488c90eb7f319c5da65484035bd2fc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T12:21:37Z","title_canon_sha256":"fd810027f8bd1fe5819174ea1933299015a6b4a5c8311e7dff1230321de7c920"},"schema_version":"1.0","source":{"id":"2403.09333","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09333","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09333v2","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09333","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_12","alias_value":"DNHLL526LQVR","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_16","alias_value":"DNHLL526LQVRCTYM","created_at":"2026-07-05T11:51:15Z"},{"alias_kind":"pith_short_8","alias_value":"DNHLL526","created_at":"2026-07-05T11:51:15Z"}],"graph_snapshots":[{"event_id":"sha256:c3dbfdcf2c3b78e2c9a73071694843ebd3ac4172dd3eeba0502d71a86017f60d","target":"graph","created_at":"2026-07-05T11:51:15Z","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/2403.09333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models have achieved fine-grained object perception, but the limitation of image resolution remains a significant obstacle to surpassing the performance of task-specific experts in complex and dense scenarios. Such limitation further restricts the model's potential to achieve nuanced visual and language referring in domains such as GUI Agents, counting, \\textit{etc}. To address this issue, we introduce a unified high-resolution generalist model, Griffon v2, enabling flexible object referring with visual and textual prompts. To efficiently scale up image resolution, we des","authors_text":"Fan Yang, Hongyin Zhao, Jinqiao Wang, Ming Tang, Shurong Zheng, Yousong Zhu, Yufei Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T12:21:37Z","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09333","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":"sha256:8a457b6ab696dba432897dee30fd17bbb7e2cd85c1022fd1a72afaf2afc0b3c8","target":"record","created_at":"2026-07-05T11:51:15Z","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":"240224326e70c07f3bb3b4aa0f1ba6783488c90eb7f319c5da65484035bd2fc4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T12:21:37Z","title_canon_sha256":"fd810027f8bd1fe5819174ea1933299015a6b4a5c8311e7dff1230321de7c920"},"schema_version":"1.0","source":{"id":"2403.09333","kind":"arxiv","version":2}},"canonical_sha256":"1b4eb5f75e5c2b114f0c3e0afe094b74007f8e0054fdab7455041fbf0c71716a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b4eb5f75e5c2b114f0c3e0afe094b74007f8e0054fdab7455041fbf0c71716a","first_computed_at":"2026-07-05T11:51:15.195939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:15.195939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jsIlKE3N0GgPwn0YCr+ogfgsRNmTt1fzYudDajkXrTpgIPbxBo5RoeXTfPZBnnePcll3Kb9P77WMy/APq5hNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:15.196433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09333","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a457b6ab696dba432897dee30fd17bbb7e2cd85c1022fd1a72afaf2afc0b3c8","sha256:c3dbfdcf2c3b78e2c9a73071694843ebd3ac4172dd3eeba0502d71a86017f60d"],"state_sha256":"cb883e272b472d21c3d8049976aede70adc47beb72bcf4287f0b33c3b02cfc50"}