{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZK2BFSLOJYSTNWLEVADBQHNGRQ","short_pith_number":"pith:ZK2BFSLO","canonical_record":{"source":{"id":"2507.00505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"0cf1c769a2dabb3e7996a4ba94503cacf7cde13532a52e9b44931ad228af1ee6","abstract_canon_sha256":"9117be6ff65f0ac3ee34b601ae6fc072732c665f6e6380423e0d115e40d636ff"},"schema_version":"1.0"},"canonical_sha256":"cab412c96e4e2536d964a806181da68c0ae64608f01a0d42a61837b247cd806f","source":{"kind":"arxiv","id":"2507.00505","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00505","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00505v3","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00505","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZK2BFSLOJYST","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZK2BFSLOJYSTNWLE","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZK2BFSLO","created_at":"2026-07-05T11:31:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZK2BFSLOJYSTNWLEVADBQHNGRQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"0cf1c769a2dabb3e7996a4ba94503cacf7cde13532a52e9b44931ad228af1ee6","abstract_canon_sha256":"9117be6ff65f0ac3ee34b601ae6fc072732c665f6e6380423e0d115e40d636ff"},"schema_version":"1.0"},"canonical_sha256":"cab412c96e4e2536d964a806181da68c0ae64608f01a0d42a61837b247cd806f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:47.124150Z","signature_b64":"bE93EEydiBj9eIoliIEk76VT96wZ4yDT2sVmG/U/66o42JRICbugbsf0BXg3zpSMp9N4Rk+rVkWAleQe8559Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab412c96e4e2536d964a806181da68c0ae64608f01a0d42a61837b247cd806f","last_reissued_at":"2026-07-05T11:31:47.123609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:47.123609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00505","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o2Nl8QuxYJfCS2QBFfsLInImPRHhZBvkE7I1xJ40DO7zvp4UAFd+eILcgSlC7S99PmFvBrAXq3RxmSDkiue/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:41:16.636849Z"},"content_sha256":"8df44ee010ce036d8cb30b136a1a7b12e5243d5e250dcc7db3a97c1a4c0e0399","schema_version":"1.0","event_id":"sha256:8df44ee010ce036d8cb30b136a1a7b12e5243d5e250dcc7db3a97c1a4c0e0399"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZK2BFSLOJYSTNWLEVADBQHNGRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunxiao Fan, Haoran Lou, Xinliang Wang, Yuexin Wu, Ziyan Liu","submitted_at":"2025-07-01T07:20:11Z","abstract_excerpt":"The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local relationships between adjacent patches, leading to weaker visual representation, which in turn affects the detailed understanding ability of MLLMs. To solve this, we propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation. Our approach offers three key advantages: 1) We propose a novel Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00505","kind":"arxiv","version":3},"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/2507.00505/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":"2026-07-05T11:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+RA6DDo147xqRrtSVV6PEau3HRMIgodVfwz/r9Rmy+ra0TLJHodEF4sPy9RJyczhWMHMMQKfUERLYkFRyH/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:41:16.637848Z"},"content_sha256":"61b0ff0ea25554c50791a4b5eddd06e504de6a6f799caf9e75cf6646c80b73a9","schema_version":"1.0","event_id":"sha256:61b0ff0ea25554c50791a4b5eddd06e504de6a6f799caf9e75cf6646c80b73a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/bundle.json","state_url":"https://pith.science/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/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":"2026-08-06T11:41:16Z","links":{"resolver":"https://pith.science/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ","bundle":"https://pith.science/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/bundle.json","state":"https://pith.science/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZK2BFSLOJYSTNWLEVADBQHNGRQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZK2BFSLOJYSTNWLEVADBQHNGRQ","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":"9117be6ff65f0ac3ee34b601ae6fc072732c665f6e6380423e0d115e40d636ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:20:11Z","title_canon_sha256":"0cf1c769a2dabb3e7996a4ba94503cacf7cde13532a52e9b44931ad228af1ee6"},"schema_version":"1.0","source":{"id":"2507.00505","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00505","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00505v3","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00505","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZK2BFSLOJYST","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZK2BFSLOJYSTNWLE","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZK2BFSLO","created_at":"2026-07-05T11:31:47Z"}],"graph_snapshots":[{"event_id":"sha256:61b0ff0ea25554c50791a4b5eddd06e504de6a6f799caf9e75cf6646c80b73a9","target":"graph","created_at":"2026-07-05T11:31:47Z","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/2507.00505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local relationships between adjacent patches, leading to weaker visual representation, which in turn affects the detailed understanding ability of MLLMs. To solve this, we propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation. Our approach offers three key advantages: 1) We propose a novel Pr","authors_text":"Chunxiao Fan, Haoran Lou, Xinliang Wang, Yuexin Wu, Ziyan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:20:11Z","title":"LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00505","kind":"arxiv","version":3},"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":"sha256:8df44ee010ce036d8cb30b136a1a7b12e5243d5e250dcc7db3a97c1a4c0e0399","target":"record","created_at":"2026-07-05T11:31:47Z","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":"9117be6ff65f0ac3ee34b601ae6fc072732c665f6e6380423e0d115e40d636ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T07:20:11Z","title_canon_sha256":"0cf1c769a2dabb3e7996a4ba94503cacf7cde13532a52e9b44931ad228af1ee6"},"schema_version":"1.0","source":{"id":"2507.00505","kind":"arxiv","version":3}},"canonical_sha256":"cab412c96e4e2536d964a806181da68c0ae64608f01a0d42a61837b247cd806f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab412c96e4e2536d964a806181da68c0ae64608f01a0d42a61837b247cd806f","first_computed_at":"2026-07-05T11:31:47.123609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:47.123609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bE93EEydiBj9eIoliIEk76VT96wZ4yDT2sVmG/U/66o42JRICbugbsf0BXg3zpSMp9N4Rk+rVkWAleQe8559Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:47.124150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00505","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8df44ee010ce036d8cb30b136a1a7b12e5243d5e250dcc7db3a97c1a4c0e0399","sha256:61b0ff0ea25554c50791a4b5eddd06e504de6a6f799caf9e75cf6646c80b73a9"],"state_sha256":"76dc4ef66fff9cf1a1bd9dc0333f51c0d3bc4de862d502308389c6500ecd0df4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypMIRfxNX5Lz0bsQ3685GjWIPTty4kpGaVQ4TqSe37o/LhddrbTSMwBldQNQbz2fgTxW+Z8kzfZgZnevgLIVBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:41:16.644661Z","bundle_sha256":"c4bb545268f7f07d0f99214edce8223b514ac04205c6f358be4a33a385927218"}}