{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GBCVWHUXMQAQQCXGHEE2WLQG3O","short_pith_number":"pith:GBCVWHUX","canonical_record":{"source":{"id":"2406.17770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"b260c63c914c3b710bbbe9c0bf046455b919f0dea1feb66ac1196d76c402f254","abstract_canon_sha256":"ebd563ae03523808367e704334aef967ea41a6891e4bd050ff5fe0412a24a959"},"schema_version":"1.0"},"canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","source":{"kind":"arxiv","id":"2406.17770","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GBCVWHUXMQAQQCXGHEE2WLQG3O","target":"record","payload":{"canonical_record":{"source":{"id":"2406.17770","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T17:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"b260c63c914c3b710bbbe9c0bf046455b919f0dea1feb66ac1196d76c402f254","abstract_canon_sha256":"ebd563ae03523808367e704334aef967ea41a6891e4bd050ff5fe0412a24a959"},"schema_version":"1.0"},"canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:21.356779Z","signature_b64":"Mx5n0GQqsjxx+FGqVYMPq86IBPq0+rPp1QCUdEiyRxNnvbV3bRDg7RK6UBlyloB5aYjB04BIlyKjLGgZXqtPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30455b1e976401080ae63909ab2e06dbb766ade082219de9b1a78f5f05a8f4fe","last_reissued_at":"2026-07-05T08:37:21.356304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:21.356304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.17770","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3+VbUsVoko0SHg4coHQbPUk9WcvBz9KLR8phz7Jl700c3m9OuP952ftkd4Mm5FGNr9aVcfLk1BiApyiqhqoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:21:32.864016Z"},"content_sha256":"86c255c14f20c7eb5a9b124b0f7fe9f47febc19d5d42a9e2aaa5955ca4d3b851","schema_version":"1.0","event_id":"sha256:86c255c14f20c7eb5a9b124b0f7fe9f47febc19d5d42a9e2aaa5955ca4d3b851"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GBCVWHUXMQAQQCXGHEE2WLQG3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Huang, Haodong Duan, Hua Yang, Kai Chen, Xiangtai Li, Xiangyu Zhao, Yining Li","submitted_at":"2024-06-25T17:55:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17770","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/2406.17770/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":"2026-07-05T08:37:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7hN7JXIxXdz11/DFg3f1FrdX4bYIrjeXdcFxzqD9LqyO098rGp7JnXP83ZycDHQstNXurKr/zO5EOjFJ7VcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:21:32.864606Z"},"content_sha256":"c5dccb5e1e91d86578266d6e5284a7a5e784597a1426e817c57d171e14dfd514","schema_version":"1.0","event_id":"sha256:c5dccb5e1e91d86578266d6e5284a7a5e784597a1426e817c57d171e14dfd514"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/bundle.json","state_url":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/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":"2026-08-09T01:21:32Z","links":{"resolver":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O","bundle":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/bundle.json","state":"https://pith.science/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBCVWHUXMQAQQCXGHEE2WLQG3O/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BTSpBZ3MnxuCdHsvBvbpzE3dcFbrIuc1ZtB2hw1+wS1/6fjWIoSX4/CX6Fh0YwfFkp4ABGt8vFSq+Xq0rPlgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:21:32.869804Z","bundle_sha256":"2fd71223b672f4dda05a694064b307c41450884102ea114d908ba3ad6348ecba"}}