{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4MNOUESS5YHBHSLTWC3QLL7SAL","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":"a3f6cd4929918b6e1f224415eabc99da6ee14520db16482a0f51e086b177ee13","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T02:43:20Z","title_canon_sha256":"3ac3ec1547cad9877d55bc9db74c36e3de8bc32736272efdbce9997fa4ae02dd"},"schema_version":"1.0","source":{"id":"2408.16224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16224","created_at":"2026-07-05T09:01:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16224v2","created_at":"2026-07-05T09:01:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16224","created_at":"2026-07-05T09:01:05Z"},{"alias_kind":"pith_short_12","alias_value":"4MNOUESS5YHB","created_at":"2026-07-05T09:01:05Z"},{"alias_kind":"pith_short_16","alias_value":"4MNOUESS5YHBHSLT","created_at":"2026-07-05T09:01:05Z"},{"alias_kind":"pith_short_8","alias_value":"4MNOUESS","created_at":"2026-07-05T09:01:05Z"}],"graph_snapshots":[{"event_id":"sha256:3b1ddca20d1149aef7fca51192bb5fb14b84ea7de3b5f84babd75748bd2eeaca","target":"graph","created_at":"2026-07-05T09:01:05Z","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/2408.16224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large vision-language models (VLMs) typically employ vision encoders based on the Vision Transformer (ViT) architecture. The division of the images into patches by ViT results in a fragmented perception, thereby hindering the visual understanding capabilities of VLMs. In this paper, we propose an innovative enhancement to address this limitation by introducing a Scene Graph Expression (SGE) module in VLMs. This module extracts and structurally expresses the complex semantic information within images, thereby improving the foundational perception and understanding abilities o","authors_text":"Jian Luan, Jianzhong Ju, Jingyi Wang, Zhidong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T02:43:20Z","title":"LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16224","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:f5bc91413aa77721dc69a59aad5197d0474ceb6dd8040290442739f186245811","target":"record","created_at":"2026-07-05T09:01:05Z","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":"a3f6cd4929918b6e1f224415eabc99da6ee14520db16482a0f51e086b177ee13","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T02:43:20Z","title_canon_sha256":"3ac3ec1547cad9877d55bc9db74c36e3de8bc32736272efdbce9997fa4ae02dd"},"schema_version":"1.0","source":{"id":"2408.16224","kind":"arxiv","version":2}},"canonical_sha256":"e31aea1252ee0e13c973b0b705aff202c373fa45d1f3a7d1618e051ebcbb855a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e31aea1252ee0e13c973b0b705aff202c373fa45d1f3a7d1618e051ebcbb855a","first_computed_at":"2026-07-05T09:01:05.517623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:05.517623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T6ghu0LKwz8ofL9QKkjJLW50NOx9asP34jlA416ZlOW/yZrLYrUqDnXpM6Rub20gZhKr3Q/MDgo+zsQ007cSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:05.518138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5bc91413aa77721dc69a59aad5197d0474ceb6dd8040290442739f186245811","sha256:3b1ddca20d1149aef7fca51192bb5fb14b84ea7de3b5f84babd75748bd2eeaca"],"state_sha256":"f5d8e481278a0f99e87fc7a7fa255e86f598d331432f787ff8b858ceb6abfa17"}