{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNHLL526LQVRCTYMHYFP4CKLOQ","short_pith_number":"pith:DNHLL526","schema_version":"1.0","canonical_sha256":"1b4eb5f75e5c2b114f0c3e0afe094b74007f8e0054fdab7455041fbf0c71716a","source":{"kind":"arxiv","id":"2403.09333","version":2},"attestation_state":"computed","paper":{"title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fan Yang, Hongyin Zhao, Jinqiao Wang, Ming Tang, Shurong Zheng, Yousong Zhu, Yufei Zhan","submitted_at":"2024-03-14T12:21:37Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.09333","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T12:21:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd810027f8bd1fe5819174ea1933299015a6b4a5c8311e7dff1230321de7c920","abstract_canon_sha256":"240224326e70c07f3bb3b4aa0f1ba6783488c90eb7f319c5da65484035bd2fc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:15.196433Z","signature_b64":"jsIlKE3N0GgPwn0YCr+ogfgsRNmTt1fzYudDajkXrTpgIPbxBo5RoeXTfPZBnnePcll3Kb9P77WMy/APq5hNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b4eb5f75e5c2b114f0c3e0afe094b74007f8e0054fdab7455041fbf0c71716a","last_reissued_at":"2026-07-05T11:51:15.195939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:15.195939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fan Yang, Hongyin Zhao, Jinqiao Wang, Ming Tang, Shurong Zheng, Yousong Zhu, Yufei Zhan","submitted_at":"2024-03-14T12:21:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09333","kind":"arxiv","version":2},"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/2403.09333/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.09333","created_at":"2026-07-05T11:51:15.195996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09333v2","created_at":"2026-07-05T11:51:15.195996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09333","created_at":"2026-07-05T11:51:15.195996+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNHLL526LQVR","created_at":"2026-07-05T11:51:15.195996+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNHLL526LQVRCTYM","created_at":"2026-07-05T11:51:15.195996+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNHLL526","created_at":"2026-07-05T11:51:15.195996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ","json":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ.json","graph_json":"https://pith.science/api/pith-number/DNHLL526LQVRCTYMHYFP4CKLOQ/graph.json","events_json":"https://pith.science/api/pith-number/DNHLL526LQVRCTYMHYFP4CKLOQ/events.json","paper":"https://pith.science/paper/DNHLL526"},"agent_actions":{"view_html":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ","download_json":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ.json","view_paper":"https://pith.science/paper/DNHLL526","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09333&json=true","fetch_graph":"https://pith.science/api/pith-number/DNHLL526LQVRCTYMHYFP4CKLOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DNHLL526LQVRCTYMHYFP4CKLOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ/action/storage_attestation","attest_author":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ/action/author_attestation","sign_citation":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ/action/citation_signature","submit_replication":"https://pith.science/pith/DNHLL526LQVRCTYMHYFP4CKLOQ/action/replication_record"}},"created_at":"2026-07-05T11:51:15.195996+00:00","updated_at":"2026-07-05T11:51:15.195996+00:00"}