{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4MNOUESS5YHBHSLTWC3QLL7SAL","short_pith_number":"pith:4MNOUESS","canonical_record":{"source":{"id":"2408.16224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T02:43:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ac3ec1547cad9877d55bc9db74c36e3de8bc32736272efdbce9997fa4ae02dd","abstract_canon_sha256":"a3f6cd4929918b6e1f224415eabc99da6ee14520db16482a0f51e086b177ee13"},"schema_version":"1.0"},"canonical_sha256":"e31aea1252ee0e13c973b0b705aff202c373fa45d1f3a7d1618e051ebcbb855a","source":{"kind":"arxiv","id":"2408.16224","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4MNOUESS5YHBHSLTWC3QLL7SAL","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-29T02:43:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ac3ec1547cad9877d55bc9db74c36e3de8bc32736272efdbce9997fa4ae02dd","abstract_canon_sha256":"a3f6cd4929918b6e1f224415eabc99da6ee14520db16482a0f51e086b177ee13"},"schema_version":"1.0"},"canonical_sha256":"e31aea1252ee0e13c973b0b705aff202c373fa45d1f3a7d1618e051ebcbb855a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:05.518138Z","signature_b64":"T6ghu0LKwz8ofL9QKkjJLW50NOx9asP34jlA416ZlOW/yZrLYrUqDnXpM6Rub20gZhKr3Q/MDgo+zsQ007cSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e31aea1252ee0e13c973b0b705aff202c373fa45d1f3a7d1618e051ebcbb855a","last_reissued_at":"2026-07-05T09:01:05.517623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:05.517623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16224","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":"2026-07-05T09:01:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HutlR8Ea8Qx4ZJ+U7C8Z1FJRUXnonburSBBRM5YqLmnHnIie4nSeqipTsDE5kIDg9K/Ri6B2GYtevwsPEof5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:40:46.996491Z"},"content_sha256":"f5bc91413aa77721dc69a59aad5197d0474ceb6dd8040290442739f186245811","schema_version":"1.0","event_id":"sha256:f5bc91413aa77721dc69a59aad5197d0474ceb6dd8040290442739f186245811"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4MNOUESS5YHBHSLTWC3QLL7SAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-SG: Leveraging Scene Graphs as Visual Semantic Expression in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jian Luan, Jianzhong Ju, Jingyi Wang, Zhidong Deng","submitted_at":"2024-08-29T02:43:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16224","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/2408.16224/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":"2026-07-05T09:01:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LVXuuv7rrudtCcICLty6b2tCHy+K6L4JgA3+mjvG808QlYJE6xMCRn5g0x/XbaaEUqinqeEiHiHYavA4eGTYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:40:46.997132Z"},"content_sha256":"3b1ddca20d1149aef7fca51192bb5fb14b84ea7de3b5f84babd75748bd2eeaca","schema_version":"1.0","event_id":"sha256:3b1ddca20d1149aef7fca51192bb5fb14b84ea7de3b5f84babd75748bd2eeaca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/bundle.json","state_url":"https://pith.science/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/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":"2026-08-04T00:40:47Z","links":{"resolver":"https://pith.science/pith/4MNOUESS5YHBHSLTWC3QLL7SAL","bundle":"https://pith.science/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/bundle.json","state":"https://pith.science/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4MNOUESS5YHBHSLTWC3QLL7SAL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kLvQbvQGKJxvWSZ9A5GChXcdvp0LwJypThAm1yLH4e5ThfzdAIu2+IaxZq6t9fb0QHdfwsHoaDmRKJwLlHSsCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:40:47.002510Z","bundle_sha256":"15b80e20c08ca91d991c5165ff93dbf586b3ba773fa8b7b88dae46e242009f52"}}