{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GBCVWHUXMQAQQCXGHEE2WLQG3O","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":"ebd563ae03523808367e704334aef967ea41a6891e4bd050ff5fe0412a24a959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","title_canon_sha256":"b260c63c914c3b710bbbe9c0bf046455b919f0dea1feb66ac1196d76c402f254"},"schema_version":"1.0","source":{"id":"2406.17770","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17770","created_at":"2026-07-05T08:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17770v2","created_at":"2026-07-05T08:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17770","created_at":"2026-07-05T08:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"GBCVWHUXMQAQ","created_at":"2026-07-05T08:37:21Z"},{"alias_kind":"pith_short_16","alias_value":"GBCVWHUXMQAQQCXG","created_at":"2026-07-05T08:37:21Z"},{"alias_kind":"pith_short_8","alias_value":"GBCVWHUX","created_at":"2026-07-05T08:37:21Z"}],"graph_snapshots":[{"event_id":"sha256:c5dccb5e1e91d86578266d6e5284a7a5e784597a1426e817c57d171e14dfd514","target":"graph","created_at":"2026-07-05T08:37:21Z","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/2406.17770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in perception tasks that necessitate detailed visual information. In our study, we present MG-LLaVA, an innovative MLLM that enhances the model's visual processing capabilities by incorporating a multi-granularity vision flow, which includes low-resolution, high-resolution, and object-centric features. We propose the integration of an additional high-resolution visu","authors_text":"Haian Huang, Haodong Duan, Hua Yang, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yining Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17770","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":"sha256:86c255c14f20c7eb5a9b124b0f7fe9f47febc19d5d42a9e2aaa5955ca4d3b851","target":"record","created_at":"2026-07-05T08:37:21Z","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":"ebd563ae03523808367e704334aef967ea41a6891e4bd050ff5fe0412a24a959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","title_canon_sha256":"b260c63c914c3b710bbbe9c0bf046455b919f0dea1feb66ac1196d76c402f254"},"schema_version":"1.0","source":{"id":"2406.17770","kind":"arxiv","version":2}},"canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","first_computed_at":"2026-07-05T08:37:21.356304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:21.356304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mx5n0GQqsjxx+FGqVYMPq86IBPq0+rPp1QCUdEiyRxNnvbV3bRDg7RK6UBlyloB5aYjB04BIlyKjLGgZXqtPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:21.356779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17770","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86c255c14f20c7eb5a9b124b0f7fe9f47febc19d5d42a9e2aaa5955ca4d3b851","sha256:c5dccb5e1e91d86578266d6e5284a7a5e784597a1426e817c57d171e14dfd514"],"state_sha256":"78e4b822f1226cce8fb39ca21181e1b8a424695608155fd5000c89d8abd459e9"}